docs: record Qwen MLX benchmark results
This commit is contained in:
136
benchmarks/inference/results/20260831T114727Z/metadata.json
Normal file
136
benchmarks/inference/results/20260831T114727Z/metadata.json
Normal file
@@ -0,0 +1,136 @@
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"created_at": "2026-08-31T11:47:27.622260+00:00",
|
||||
"host": {
|
||||
"platform": "macOS-15.6-arm64-arm-64bit",
|
||||
"machine": "arm64",
|
||||
"python": "3.12.8"
|
||||
},
|
||||
"arguments": {
|
||||
"output_dir": "/Users/christianmeyer/Documents/git/lai_automatisierung/benchmarks/inference/results",
|
||||
"runtime": "vllm",
|
||||
"ollama_url": "http://127.0.0.1:11434",
|
||||
"ollama_model": "qwen3.8:27b-mlx",
|
||||
"vllm_url": "http://127.0.0.1:8001",
|
||||
"vllm_model": "qwen3.8-27b-nvfp4",
|
||||
"warmups": 2,
|
||||
"rounds": 5,
|
||||
"concurrency": [
|
||||
1,
|
||||
4
|
||||
],
|
||||
"max_tokens": 128,
|
||||
"seed": 42,
|
||||
"timeout": 600
|
||||
},
|
||||
"runtimes": [
|
||||
{
|
||||
"name": "vllm-metal",
|
||||
"kind": "openai",
|
||||
"base_url": "http://127.0.0.1:8001",
|
||||
"model": "qwen3.8-27b-nvfp4"
|
||||
}
|
||||
],
|
||||
"versions": {
|
||||
"ollama": "ollama version is 0.32.14",
|
||||
"vllm": "INFO 08-31 13:47:28 [__init__.py:52] Available plugins for group vllm.platform_plugins:\nINFO 08-31 13:47:28 [__init__.py:54] - metal -> vllm_metal:register\nINFO 08-31 13:47:28 [__init__.py:57] All plugins in this group will be loaded. Set `VLLM_PLUGINS` to control which plugins to load.\nINFO 08-31 13:47:30 [__init__.py:254] Platform plugin metal is activated\nINFO 08-31 13:47:30 [importing.py:88] Triton not installed or not compatible; certain GPU-related functions will not be available.\n0.28.0+cpu"
|
||||
},
|
||||
"model_metadata": {
|
||||
"vllm-metal": {
|
||||
"object": "list",
|
||||
"data": [
|
||||
{
|
||||
"id": "qwen3.8-27b-nvfp4",
|
||||
"object": "model",
|
||||
"created": 1788176852,
|
||||
"owned_by": "vllm",
|
||||
"root": "mlx-community/Qwen3.8-27B-nvfp4",
|
||||
"parent": null,
|
||||
"max_model_len": 8192,
|
||||
"permission": [
|
||||
{
|
||||
"id": "modelperm-956fc45cb39100d2",
|
||||
"object": "model_permission",
|
||||
"created": 1788176852,
|
||||
"allow_create_engine": false,
|
||||
"allow_sampling": true,
|
||||
"allow_logprobs": true,
|
||||
"allow_search_indices": false,
|
||||
"allow_view": true,
|
||||
"allow_fine_tuning": false,
|
||||
"organization": "*",
|
||||
"group": null,
|
||||
"is_blocking": false
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"prompts": {
|
||||
"short": "In exactly four concise bullet points, explain why database transactions are useful. Do not use a heading.",
|
||||
"medium": "You are reviewing a Laravel service that transfers money between two accounts. Explain the failure modes involving concurrency, partial writes, retries, and audit logs. Then provide a robust implementation plan. Keep the response technical and concise.",
|
||||
"code": "Write a Python 3.12 function named merge_intervals that accepts a list of integer pairs, validates each pair, merges overlapping or adjacent intervals, and returns sorted tuples. Include type hints, a short docstring, and five assert-based examples. Output only code."
|
||||
},
|
||||
"measurement_notes": {
|
||||
"ttft": "Client wall time from request start until first non-empty generated text chunk.",
|
||||
"total": "Client wall time from request start until stream completion.",
|
||||
"decode_tps": "Ollama server eval metric; otherwise output tokens / (total - TTFT).",
|
||||
"aggregate_output_tps": "Sum of successful output tokens / concurrent group wall time."
|
||||
},
|
||||
"completed_at": "2026-08-31T11:49:15.455115+00:00",
|
||||
"summary": [
|
||||
{
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"concurrency": 1,
|
||||
"requests": 5,
|
||||
"successes": 5,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 0.3338013501954265,
|
||||
"ttft_s_p50": 0.37227433401858434,
|
||||
"ttft_s_p95": 0.4201282836031169,
|
||||
"total_s_mean": 5.444907250197138,
|
||||
"total_s_p50": 5.454897999996319,
|
||||
"total_s_p95": 5.562144016823732,
|
||||
"prompt_tps_mean": null,
|
||||
"prompt_tps_p50": null,
|
||||
"prompt_tps_p95": null,
|
||||
"decode_tps_mean": 25.04504255080693,
|
||||
"decode_tps_p50": 24.962500989743333,
|
||||
"decode_tps_p95": 25.32382313060655,
|
||||
"request_tps_mean": 23.517575676354507,
|
||||
"request_tps_p50": 23.465150035818517,
|
||||
"request_tps_p95": 24.196276605031606,
|
||||
"aggregate_output_tps_mean": 23.516827822391825,
|
||||
"aggregate_output_tps_p50": 23.464397444683396,
|
||||
"aggregate_output_tps_p95": 24.195480643338048
|
||||
},
|
||||
{
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"concurrency": 4,
|
||||
"requests": 20,
|
||||
"successes": 20,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 1.1358489938022103,
|
||||
"ttft_s_p50": 1.1691114795103204,
|
||||
"ttft_s_p95": 1.2360623297834537,
|
||||
"total_s_mean": 9.343862856202758,
|
||||
"total_s_p50": 9.272835896001197,
|
||||
"total_s_p95": 9.591099269420374,
|
||||
"prompt_tps_mean": null,
|
||||
"prompt_tps_p50": null,
|
||||
"prompt_tps_p95": null,
|
||||
"decode_tps_mean": 15.572524640705884,
|
||||
"decode_tps_p50": 15.580143217705817,
|
||||
"decode_tps_p95": 15.920671319893613,
|
||||
"request_tps_mean": 13.679827878866371,
|
||||
"request_tps_p50": 13.803600866803595,
|
||||
"request_tps_p95": 13.831739950302437,
|
||||
"aggregate_output_tps_mean": 54.66256367620249,
|
||||
"aggregate_output_tps_p50": 54.89183177619698,
|
||||
"aggregate_output_tps_p95": 55.24148726503248
|
||||
}
|
||||
]
|
||||
}
|
||||
36
benchmarks/inference/results/20260831T114727Z/raw.csv
Normal file
36
benchmarks/inference/results/20260831T114727Z/raw.csv
Normal file
@@ -0,0 +1,36 @@
|
||||
run_id,runtime,model,phase,concurrency,round,slot,request_id,prompt_name,prompt_chars,max_tokens,started_at,ttft_s,total_s,prompt_tokens,output_tokens,prompt_tps,decode_tps,request_tps,group_elapsed_s,group_output_tps,error
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,1,0,0,8b712536-91f2-4ded-b334-6db253435ba3,short,106,128,2026-08-31T11:47:32.567050+00:00,0.561656582984142,5.602756957989186,20,128,,25.39128175956463,22.845895504619364,5.6035958750289865,22.842475234589944,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,1,1,0,be5a9e94-abd6-4cbc-8029-7a55e3ad129c,medium,252,128,2026-08-31T11:47:38.170087+00:00,0.3621360409888439,5.426666249986738,43,128,,25.273815086064428,23.587225398339694,5.426845958980266,23.586444311762243,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,1,0,0,e0ac985d-818e-45ec-a2c1-7e077fe0f1cd,short,106,128,2026-08-31T11:47:43.597014+00:00,0.21451262495247647,5.262066499970388,20,128,,25.358817987761604,24.325044162919706,5.262241083022673,24.324237141654443,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,1,1,0,428bad62-8fbf-41a1-9b36-07912506da11,medium,252,128,2026-08-31T11:47:48.859322+00:00,0.37227433401858434,5.454897999996319,43,128,,25.18384370198632,23.465150035818517,5.455072959011886,23.464397444683396,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,1,2,0,b2de9565-6ff0-47a1-91e6-847b83994f6c,code,267,128,2026-08-31T11:47:54.314442+00:00,0.40532424999400973,5.533015583991073,54,128,,24.962500989743333,23.13385857259254,5.533179917023517,23.13317150707355,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,1,3,0,dc02daab-d1f2-49ac-8e29-01ee86148e0a,short,106,128,2026-08-31T11:47:59.847681+00:00,0.25306625000666827,5.405130041996017,20,128,,24.844412873734196,23.681206373479203,5.405301624967251,23.680454650072466,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,1,4,0,677f2a25-31e5-43e7-b8fd-5e607453b904,medium,252,128,2026-08-31T11:48:05.253048+00:00,0.42382929200539365,5.569426125031896,43,128,,24.875637200809187,22.982619236962577,5.569605667027645,22.981878368475286,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,4,0,0,7109b7b9-3690-49d6-8b20-969734c3dcad,short,106,128,2026-08-31T11:48:10.822944+00:00,1.1026008339831606,8.694552083965391,20,128,,16.859960738064487,14.721862467884838,8.695109791995492,58.883672805527404,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,4,0,1,b34a5a99-e633-4f3a-892d-67af2b425779,medium,252,128,2026-08-31T11:48:10.823149+00:00,1.1023455830290914,8.694302666990552,43,128,,16.859947782161328,14.722284799904022,8.695109791995492,58.883672805527404,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,4,0,2,1260b39f-a4b1-4d94-9406-70028f614ce0,code,267,128,2026-08-31T11:48:10.823017+00:00,1.0163157919887453,8.694556291971821,54,128,,16.670485901070972,14.721855342772315,8.695109791995492,58.883672805527404,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,4,0,3,b43d525a-50de-4e41-b00c-d1159d1ddfd4,short,106,128,2026-08-31T11:48:10.822845+00:00,1.1026693329913542,8.694680040993262,20,128,,16.85982869664412,14.721645810600473,8.695109791995492,58.883672805527404,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,4,1,0,1da340a9-b91e-4f9b-8217-2af7c2fbc030,medium,252,128,2026-08-31T11:48:19.518058+00:00,1.245261833013501,9.168966500030365,43,128,,16.154059922603068,13.960133892906699,9.169412165996619,55.83782152346415,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,4,1,1,23e076e6-7b50-4d08-a3ff-f79ddc53bafe,code,267,128,2026-08-31T11:48:19.518183+00:00,1.2451274580089375,9.168911040993407,54,128,,16.153899038190183,13.96021833211415,9.169412165996619,55.83782152346415,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,4,1,2,c777d58b-0520-4f3f-8537-6a163ab350f5,short,106,128,2026-08-31T11:48:19.518319+00:00,1.2449699160060845,9.168749333010055,20,128,,16.153907531211612,13.960464546583719,9.169412165996619,55.83782152346415,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,warmup,4,1,3,5609655c-e54a-499f-99c6-c77c19c1a3e0,medium,252,128,2026-08-31T11:48:19.518407+00:00,1.174761500034947,9.16857587499544,43,128,,16.012380822970083,13.960728661152478,9.169412165996619,55.83782152346415,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,0,0,d2615398-7368-4f9a-9424-7a2e76d8955d,short,106,128,2026-08-31T11:48:28.687706+00:00,1.0508670000126585,9.266459833015688,20,128,,15.580129468662143,13.813257954666332,9.267125833022874,55.24906095215814,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,0,1,b307dcc2-b325-4005-a63f-54123aa28e31,medium,252,128,2026-08-31T11:48:28.687614+00:00,1.0509756249957718,9.266665957984515,43,128,,15.579944570943383,13.812950696653772,9.267125833022874,55.24906095215814,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,0,2,09c7607f-96f5-4a6d-a9e1-3637c8afc257,code,267,128,2026-08-31T11:48:28.687778+00:00,1.0507545830332674,9.266332915984094,54,128,,15.580156966749492,13.813447149001583,9.267125833022874,55.24906095215814,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,0,3,0328d6c0-e3f4-4a86-917d-dbeb5b8deee7,short,106,128,2026-08-31T11:48:28.687501+00:00,0.9898037080420181,9.266721500025596,20,128,,15.464693889308833,13.81286790583341,9.267125833022874,55.24906095215814,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,1,0,74110182-284c-4250-9395-e3d0f2772eef,medium,252,128,2026-08-31T11:48:37.954714+00:00,1.1083811249700375,9.379890666983556,43,128,,15.474805336299134,13.646214496992963,9.380457791965455,54.58155788926826,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,1,1,fca02813-8ad6-4e99-bc76-9e922ea9a63a,code,267,128,2026-08-31T11:48:37.954992+00:00,1.1690869170124643,9.379730832995847,54,128,,15.589520299476966,13.646447033397155,9.380457791965455,54.58155788926826,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,1,2,5eb13719-9063-4ddd-92c8-73332709ecfd,short,106,128,2026-08-31T11:48:37.954812+00:00,1.1692542500095442,9.37985170801403,20,128,,15.589608509574806,13.646271176189105,9.380457791965455,54.58155788926826,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,1,3,9d9a5b23-6950-4d5c-bad2-72f896d38009,medium,252,128,2026-08-31T11:48:37.954917+00:00,1.1691360420081764,9.379842250025831,43,128,,15.58940202671112,13.646284936150979,9.380457791965455,54.58155788926826,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,2,0,caf79143-9d5b-4fb2-830e-3bd2d38cc5d3,code,267,128,2026-08-31T11:48:47.335341+00:00,1.172440624970477,9.591207291989122,54,128,,15.204127286417465,13.345556623190662,9.591755541972816,53.37917524685921,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,2,1,d77a5e81-922c-49ce-96c5-1fb443746984,short,106,128,2026-08-31T11:48:47.335566+00:00,1.2360592089826241,9.591093584022019,20,128,,15.320104532711328,13.345714842490702,9.591755541972816,53.37917524685921,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,2,2,9ccc94c9-d569-4785-9f48-e48e760b0e15,medium,252,128,2026-08-31T11:48:47.335447+00:00,1.236121624999214,9.591066916007549,43,128,,15.320267882275031,13.345751950324445,9.591755541972816,53.37917524685921,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,2,3,e7c5be37-35a8-47a5-869d-a3bee16750d4,code,267,128,2026-08-31T11:48:47.335653+00:00,1.2359632499865256,9.590960291970987,54,128,,15.32017298830757,13.345900316900948,9.591755541972816,53.37917524685921,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,3,0,49d569ca-4eef-46fd-88f9-58cf68e01898,short,106,128,2026-08-31T11:48:56.927355+00:00,1.067110000003595,9.073982625035569,20,124,,15.486695718417879,13.665443843575128,9.254564541974105,54.89183177619698,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,3,1,a34ede89-ca43-4a1c-a7c8-c916bfec24a5,medium,252,128,2026-08-31T11:48:56.927278+00:00,1.0672226250171661,9.253953957988415,43,128,,15.635055652124883,13.831925313341854,9.254564541974105,54.89183177619698,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,3,2,af0dfbe9-f1a5-434a-a714-98fad2af83a3,code,267,128,2026-08-31T11:48:56.927205+00:00,1.067305459000636,9.254084500018507,54,128,,15.634964539617723,13.831730194352993,9.254564541974105,54.89183177619698,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,3,3,80dc0643-6f40-4ab5-805d-ace4e9f149bb,short,106,128,2026-08-31T11:48:56.927082+00:00,1.0054587500053458,9.254091374983545,20,128,,15.517723460297553,13.831719918610334,9.254564541974105,54.89183177619698,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,4,0,12e42bf2-6a75-4f89-a598-ac14d5b67a78,medium,252,128,2026-08-31T11:49:06.181834+00:00,1.2329518750193529,9.273020750028081,43,128,,15.920261628338482,13.803484695061464,9.273481999989599,55.21119251652985,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,4,1,5f2cf183-3654-45be-81ed-4eebfb57bce1,code,267,128,2026-08-31T11:49:06.182126+00:00,1.1721314580063336,9.272628374979831,54,128,,15.801499748959015,13.804068795141205,9.273481999989599,55.21119251652985,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,4,2,746da721-ed00-4c80-bc92-ed115313463e,short,106,128,2026-08-31T11:49:06.182026+00:00,1.2329447079682723,9.272807125002146,20,128,,15.920670449385964,13.80380269690667,9.273481999989599,55.21119251652985,
|
||||
20260831T114727Z,vllm-metal,qwen3.8-27b-nvfp4,measured,4,4,3,5c45d61d-9d4a-4fc4-931d-5193cdcaa598,medium,252,128,2026-08-31T11:49:06.181940+00:00,1.2330110420007259,9.272864667000249,43,128,,15.920687859538933,13.803717038545729,9.273481999989599,55.21119251652985,
|
||||
|
842
benchmarks/inference/results/20260831T114727Z/raw.json
Normal file
842
benchmarks/inference/results/20260831T114727Z/raw.json
Normal file
@@ -0,0 +1,842 @@
|
||||
[
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "8b712536-91f2-4ded-b334-6db253435ba3",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:47:32.567050+00:00",
|
||||
"ttft_s": 0.561656582984142,
|
||||
"total_s": 5.602756957989186,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 25.39128175956463,
|
||||
"request_tps": 22.845895504619364,
|
||||
"group_elapsed_s": 5.6035958750289865,
|
||||
"group_output_tps": 22.842475234589944,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "be5a9e94-abd6-4cbc-8029-7a55e3ad129c",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:47:38.170087+00:00",
|
||||
"ttft_s": 0.3621360409888439,
|
||||
"total_s": 5.426666249986738,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 25.273815086064428,
|
||||
"request_tps": 23.587225398339694,
|
||||
"group_elapsed_s": 5.426845958980266,
|
||||
"group_output_tps": 23.586444311762243,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "e0ac985d-818e-45ec-a2c1-7e077fe0f1cd",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:47:43.597014+00:00",
|
||||
"ttft_s": 0.21451262495247647,
|
||||
"total_s": 5.262066499970388,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 25.358817987761604,
|
||||
"request_tps": 24.325044162919706,
|
||||
"group_elapsed_s": 5.262241083022673,
|
||||
"group_output_tps": 24.324237141654443,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "428bad62-8fbf-41a1-9b36-07912506da11",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:47:48.859322+00:00",
|
||||
"ttft_s": 0.37227433401858434,
|
||||
"total_s": 5.454897999996319,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 25.18384370198632,
|
||||
"request_tps": 23.465150035818517,
|
||||
"group_elapsed_s": 5.455072959011886,
|
||||
"group_output_tps": 23.464397444683396,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "b2de9565-6ff0-47a1-91e6-847b83994f6c",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:47:54.314442+00:00",
|
||||
"ttft_s": 0.40532424999400973,
|
||||
"total_s": 5.533015583991073,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 24.962500989743333,
|
||||
"request_tps": 23.13385857259254,
|
||||
"group_elapsed_s": 5.533179917023517,
|
||||
"group_output_tps": 23.13317150707355,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "dc02daab-d1f2-49ac-8e29-01ee86148e0a",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:47:59.847681+00:00",
|
||||
"ttft_s": 0.25306625000666827,
|
||||
"total_s": 5.405130041996017,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 24.844412873734196,
|
||||
"request_tps": 23.681206373479203,
|
||||
"group_elapsed_s": 5.405301624967251,
|
||||
"group_output_tps": 23.680454650072466,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "677f2a25-31e5-43e7-b8fd-5e607453b904",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:05.253048+00:00",
|
||||
"ttft_s": 0.42382929200539365,
|
||||
"total_s": 5.569426125031896,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 24.875637200809187,
|
||||
"request_tps": 22.982619236962577,
|
||||
"group_elapsed_s": 5.569605667027645,
|
||||
"group_output_tps": 22.981878368475286,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "7109b7b9-3690-49d6-8b20-969734c3dcad",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:10.822944+00:00",
|
||||
"ttft_s": 1.1026008339831606,
|
||||
"total_s": 8.694552083965391,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 16.859960738064487,
|
||||
"request_tps": 14.721862467884838,
|
||||
"group_elapsed_s": 8.695109791995492,
|
||||
"group_output_tps": 58.883672805527404,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 1,
|
||||
"request_id": "b34a5a99-e633-4f3a-892d-67af2b425779",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:10.823149+00:00",
|
||||
"ttft_s": 1.1023455830290914,
|
||||
"total_s": 8.694302666990552,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 16.859947782161328,
|
||||
"request_tps": 14.722284799904022,
|
||||
"group_elapsed_s": 8.695109791995492,
|
||||
"group_output_tps": 58.883672805527404,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 2,
|
||||
"request_id": "1260b39f-a4b1-4d94-9406-70028f614ce0",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:10.823017+00:00",
|
||||
"ttft_s": 1.0163157919887453,
|
||||
"total_s": 8.694556291971821,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 16.670485901070972,
|
||||
"request_tps": 14.721855342772315,
|
||||
"group_elapsed_s": 8.695109791995492,
|
||||
"group_output_tps": 58.883672805527404,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 3,
|
||||
"request_id": "b43d525a-50de-4e41-b00c-d1159d1ddfd4",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:10.822845+00:00",
|
||||
"ttft_s": 1.1026693329913542,
|
||||
"total_s": 8.694680040993262,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 16.85982869664412,
|
||||
"request_tps": 14.721645810600473,
|
||||
"group_elapsed_s": 8.695109791995492,
|
||||
"group_output_tps": 58.883672805527404,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "1da340a9-b91e-4f9b-8217-2af7c2fbc030",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:19.518058+00:00",
|
||||
"ttft_s": 1.245261833013501,
|
||||
"total_s": 9.168966500030365,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 16.154059922603068,
|
||||
"request_tps": 13.960133892906699,
|
||||
"group_elapsed_s": 9.169412165996619,
|
||||
"group_output_tps": 55.83782152346415,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 1,
|
||||
"request_id": "23e076e6-7b50-4d08-a3ff-f79ddc53bafe",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:19.518183+00:00",
|
||||
"ttft_s": 1.2451274580089375,
|
||||
"total_s": 9.168911040993407,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 16.153899038190183,
|
||||
"request_tps": 13.96021833211415,
|
||||
"group_elapsed_s": 9.169412165996619,
|
||||
"group_output_tps": 55.83782152346415,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 2,
|
||||
"request_id": "c777d58b-0520-4f3f-8537-6a163ab350f5",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:19.518319+00:00",
|
||||
"ttft_s": 1.2449699160060845,
|
||||
"total_s": 9.168749333010055,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 16.153907531211612,
|
||||
"request_tps": 13.960464546583719,
|
||||
"group_elapsed_s": 9.169412165996619,
|
||||
"group_output_tps": 55.83782152346415,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 3,
|
||||
"request_id": "5609655c-e54a-499f-99c6-c77c19c1a3e0",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:19.518407+00:00",
|
||||
"ttft_s": 1.174761500034947,
|
||||
"total_s": 9.16857587499544,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 16.012380822970083,
|
||||
"request_tps": 13.960728661152478,
|
||||
"group_elapsed_s": 9.169412165996619,
|
||||
"group_output_tps": 55.83782152346415,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "d2615398-7368-4f9a-9424-7a2e76d8955d",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:28.687706+00:00",
|
||||
"ttft_s": 1.0508670000126585,
|
||||
"total_s": 9.266459833015688,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.580129468662143,
|
||||
"request_tps": 13.813257954666332,
|
||||
"group_elapsed_s": 9.267125833022874,
|
||||
"group_output_tps": 55.24906095215814,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 1,
|
||||
"request_id": "b307dcc2-b325-4005-a63f-54123aa28e31",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:28.687614+00:00",
|
||||
"ttft_s": 1.0509756249957718,
|
||||
"total_s": 9.266665957984515,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.579944570943383,
|
||||
"request_tps": 13.812950696653772,
|
||||
"group_elapsed_s": 9.267125833022874,
|
||||
"group_output_tps": 55.24906095215814,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 2,
|
||||
"request_id": "09c7607f-96f5-4a6d-a9e1-3637c8afc257",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:28.687778+00:00",
|
||||
"ttft_s": 1.0507545830332674,
|
||||
"total_s": 9.266332915984094,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.580156966749492,
|
||||
"request_tps": 13.813447149001583,
|
||||
"group_elapsed_s": 9.267125833022874,
|
||||
"group_output_tps": 55.24906095215814,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 3,
|
||||
"request_id": "0328d6c0-e3f4-4a86-917d-dbeb5b8deee7",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:28.687501+00:00",
|
||||
"ttft_s": 0.9898037080420181,
|
||||
"total_s": 9.266721500025596,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.464693889308833,
|
||||
"request_tps": 13.81286790583341,
|
||||
"group_elapsed_s": 9.267125833022874,
|
||||
"group_output_tps": 55.24906095215814,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "74110182-284c-4250-9395-e3d0f2772eef",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:37.954714+00:00",
|
||||
"ttft_s": 1.1083811249700375,
|
||||
"total_s": 9.379890666983556,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.474805336299134,
|
||||
"request_tps": 13.646214496992963,
|
||||
"group_elapsed_s": 9.380457791965455,
|
||||
"group_output_tps": 54.58155788926826,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 1,
|
||||
"request_id": "fca02813-8ad6-4e99-bc76-9e922ea9a63a",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:37.954992+00:00",
|
||||
"ttft_s": 1.1690869170124643,
|
||||
"total_s": 9.379730832995847,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.589520299476966,
|
||||
"request_tps": 13.646447033397155,
|
||||
"group_elapsed_s": 9.380457791965455,
|
||||
"group_output_tps": 54.58155788926826,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 2,
|
||||
"request_id": "5eb13719-9063-4ddd-92c8-73332709ecfd",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:37.954812+00:00",
|
||||
"ttft_s": 1.1692542500095442,
|
||||
"total_s": 9.37985170801403,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.589608509574806,
|
||||
"request_tps": 13.646271176189105,
|
||||
"group_elapsed_s": 9.380457791965455,
|
||||
"group_output_tps": 54.58155788926826,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 3,
|
||||
"request_id": "9d9a5b23-6950-4d5c-bad2-72f896d38009",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:37.954917+00:00",
|
||||
"ttft_s": 1.1691360420081764,
|
||||
"total_s": 9.379842250025831,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.58940202671112,
|
||||
"request_tps": 13.646284936150979,
|
||||
"group_elapsed_s": 9.380457791965455,
|
||||
"group_output_tps": 54.58155788926826,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "caf79143-9d5b-4fb2-830e-3bd2d38cc5d3",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:47.335341+00:00",
|
||||
"ttft_s": 1.172440624970477,
|
||||
"total_s": 9.591207291989122,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.204127286417465,
|
||||
"request_tps": 13.345556623190662,
|
||||
"group_elapsed_s": 9.591755541972816,
|
||||
"group_output_tps": 53.37917524685921,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 1,
|
||||
"request_id": "d77a5e81-922c-49ce-96c5-1fb443746984",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:47.335566+00:00",
|
||||
"ttft_s": 1.2360592089826241,
|
||||
"total_s": 9.591093584022019,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.320104532711328,
|
||||
"request_tps": 13.345714842490702,
|
||||
"group_elapsed_s": 9.591755541972816,
|
||||
"group_output_tps": 53.37917524685921,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 2,
|
||||
"request_id": "9ccc94c9-d569-4785-9f48-e48e760b0e15",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:47.335447+00:00",
|
||||
"ttft_s": 1.236121624999214,
|
||||
"total_s": 9.591066916007549,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.320267882275031,
|
||||
"request_tps": 13.345751950324445,
|
||||
"group_elapsed_s": 9.591755541972816,
|
||||
"group_output_tps": 53.37917524685921,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 3,
|
||||
"request_id": "e7c5be37-35a8-47a5-869d-a3bee16750d4",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:47.335653+00:00",
|
||||
"ttft_s": 1.2359632499865256,
|
||||
"total_s": 9.590960291970987,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.32017298830757,
|
||||
"request_tps": 13.345900316900948,
|
||||
"group_elapsed_s": 9.591755541972816,
|
||||
"group_output_tps": 53.37917524685921,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "49d569ca-4eef-46fd-88f9-58cf68e01898",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:56.927355+00:00",
|
||||
"ttft_s": 1.067110000003595,
|
||||
"total_s": 9.073982625035569,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 124,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.486695718417879,
|
||||
"request_tps": 13.665443843575128,
|
||||
"group_elapsed_s": 9.254564541974105,
|
||||
"group_output_tps": 54.89183177619698,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 1,
|
||||
"request_id": "a34ede89-ca43-4a1c-a7c8-c916bfec24a5",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:56.927278+00:00",
|
||||
"ttft_s": 1.0672226250171661,
|
||||
"total_s": 9.253953957988415,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.635055652124883,
|
||||
"request_tps": 13.831925313341854,
|
||||
"group_elapsed_s": 9.254564541974105,
|
||||
"group_output_tps": 54.89183177619698,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 2,
|
||||
"request_id": "af0dfbe9-f1a5-434a-a714-98fad2af83a3",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:56.927205+00:00",
|
||||
"ttft_s": 1.067305459000636,
|
||||
"total_s": 9.254084500018507,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.634964539617723,
|
||||
"request_tps": 13.831730194352993,
|
||||
"group_elapsed_s": 9.254564541974105,
|
||||
"group_output_tps": 54.89183177619698,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 3,
|
||||
"request_id": "80dc0643-6f40-4ab5-805d-ace4e9f149bb",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:48:56.927082+00:00",
|
||||
"ttft_s": 1.0054587500053458,
|
||||
"total_s": 9.254091374983545,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.517723460297553,
|
||||
"request_tps": 13.831719918610334,
|
||||
"group_elapsed_s": 9.254564541974105,
|
||||
"group_output_tps": 54.89183177619698,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "12e42bf2-6a75-4f89-a598-ac14d5b67a78",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:06.181834+00:00",
|
||||
"ttft_s": 1.2329518750193529,
|
||||
"total_s": 9.273020750028081,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.920261628338482,
|
||||
"request_tps": 13.803484695061464,
|
||||
"group_elapsed_s": 9.273481999989599,
|
||||
"group_output_tps": 55.21119251652985,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 1,
|
||||
"request_id": "5f2cf183-3654-45be-81ed-4eebfb57bce1",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:06.182126+00:00",
|
||||
"ttft_s": 1.1721314580063336,
|
||||
"total_s": 9.272628374979831,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.801499748959015,
|
||||
"request_tps": 13.804068795141205,
|
||||
"group_elapsed_s": 9.273481999989599,
|
||||
"group_output_tps": 55.21119251652985,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 2,
|
||||
"request_id": "746da721-ed00-4c80-bc92-ed115313463e",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:06.182026+00:00",
|
||||
"ttft_s": 1.2329447079682723,
|
||||
"total_s": 9.272807125002146,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.920670449385964,
|
||||
"request_tps": 13.80380269690667,
|
||||
"group_elapsed_s": 9.273481999989599,
|
||||
"group_output_tps": 55.21119251652985,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114727Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 3,
|
||||
"request_id": "5c45d61d-9d4a-4fc4-931d-5193cdcaa598",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:06.181940+00:00",
|
||||
"ttft_s": 1.2330110420007259,
|
||||
"total_s": 9.272864667000249,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.920687859538933,
|
||||
"request_tps": 13.803717038545729,
|
||||
"group_elapsed_s": 9.273481999989599,
|
||||
"group_output_tps": 55.21119251652985,
|
||||
"error": null
|
||||
}
|
||||
]
|
||||
54
benchmarks/inference/results/20260831T114727Z/summary.json
Normal file
54
benchmarks/inference/results/20260831T114727Z/summary.json
Normal file
@@ -0,0 +1,54 @@
|
||||
[
|
||||
{
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"concurrency": 1,
|
||||
"requests": 5,
|
||||
"successes": 5,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 0.3338013501954265,
|
||||
"ttft_s_p50": 0.37227433401858434,
|
||||
"ttft_s_p95": 0.4201282836031169,
|
||||
"total_s_mean": 5.444907250197138,
|
||||
"total_s_p50": 5.454897999996319,
|
||||
"total_s_p95": 5.562144016823732,
|
||||
"prompt_tps_mean": null,
|
||||
"prompt_tps_p50": null,
|
||||
"prompt_tps_p95": null,
|
||||
"decode_tps_mean": 25.04504255080693,
|
||||
"decode_tps_p50": 24.962500989743333,
|
||||
"decode_tps_p95": 25.32382313060655,
|
||||
"request_tps_mean": 23.517575676354507,
|
||||
"request_tps_p50": 23.465150035818517,
|
||||
"request_tps_p95": 24.196276605031606,
|
||||
"aggregate_output_tps_mean": 23.516827822391825,
|
||||
"aggregate_output_tps_p50": 23.464397444683396,
|
||||
"aggregate_output_tps_p95": 24.195480643338048
|
||||
},
|
||||
{
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-nvfp4",
|
||||
"concurrency": 4,
|
||||
"requests": 20,
|
||||
"successes": 20,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 1.1358489938022103,
|
||||
"ttft_s_p50": 1.1691114795103204,
|
||||
"ttft_s_p95": 1.2360623297834537,
|
||||
"total_s_mean": 9.343862856202758,
|
||||
"total_s_p50": 9.272835896001197,
|
||||
"total_s_p95": 9.591099269420374,
|
||||
"prompt_tps_mean": null,
|
||||
"prompt_tps_p50": null,
|
||||
"prompt_tps_p95": null,
|
||||
"decode_tps_mean": 15.572524640705884,
|
||||
"decode_tps_p50": 15.580143217705817,
|
||||
"decode_tps_p95": 15.920671319893613,
|
||||
"request_tps_mean": 13.679827878866371,
|
||||
"request_tps_p50": 13.803600866803595,
|
||||
"request_tps_p95": 13.831739950302437,
|
||||
"aggregate_output_tps_mean": 54.66256367620249,
|
||||
"aggregate_output_tps_p50": 54.89183177619698,
|
||||
"aggregate_output_tps_p95": 55.24148726503248
|
||||
}
|
||||
]
|
||||
135
benchmarks/inference/results/20260831T114928Z/metadata.json
Normal file
135
benchmarks/inference/results/20260831T114928Z/metadata.json
Normal file
File diff suppressed because one or more lines are too long
36
benchmarks/inference/results/20260831T114928Z/raw.csv
Normal file
36
benchmarks/inference/results/20260831T114928Z/raw.csv
Normal file
@@ -0,0 +1,36 @@
|
||||
run_id,runtime,model,phase,concurrency,round,slot,request_id,prompt_name,prompt_chars,max_tokens,started_at,ttft_s,total_s,prompt_tokens,output_tokens,prompt_tps,decode_tps,request_tps,group_elapsed_s,group_output_tps,error
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,1,0,0,0bd09e14-c217-44ad-b0a1-98600e1bf40e,short,106,128,2026-08-31T11:49:33.251646+00:00,3.627692041976843,5.577126249962021,20,96,116.69505030650684,46.54721674973356,17.213166010121025,5.578097124991473,17.210170036282175,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,1,1,0,ada11e2f-0b97-42ec-a5be-5175f0bb29b1,medium,252,128,2026-08-31T11:49:38.829357+00:00,0.3621791250188835,2.7543381249997765,43,128,157.23847751774449,52.253166030964316,46.472144737135494,2.7547111669555306,46.46585149667936,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,1,0,0,a3bd0047-d992-4553-9b17-4472b6290acc,short,106,128,2026-08-31T11:49:41.584102+00:00,0.11936691601295024,2.1721785410190932,20,96,448.5805263612496,45.72630609321048,44.19526212378514,2.172526082955301,44.18819214792146,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,1,1,0,a8033a77-d60f-42b4-a2a9-8f6a97ef3496,medium,252,128,2026-08-31T11:49:43.757773+00:00,0.14179470797535032,2.78225216595456,43,128,816.5668113066018,47.377908815894095,46.00589463683088,2.7835853330325335,45.98386062788756,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,1,2,0,9cc954fc-95f5-474e-b219-8a89d7091934,code,267,128,2026-08-31T11:49:46.540349+00:00,0.45632574998307973,2.7544727920321748,54,128,146.71421293937848,54.2491762219149,46.46987269951035,2.754789875005372,46.46452390484062,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,1,3,0,e8ee5060-7c14-4c34-bd5b-76d7e51fef07,short,106,128,2026-08-31T11:49:49.295554+00:00,0.0983880830463022,2.5220755000482313,20,96,2758620.689655172,38.503422116977305,38.063888253212134,2.522709292010404,38.054325285929174,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,1,4,0,edd132c8-7aaa-4eb0-98e8-2b2d711f2cf9,medium,252,128,2026-08-31T11:49:51.817976+00:00,0.09851625002920628,3.6179742500535212,43,128,3245283.0188679243,35.649936286183205,35.3789140423281,3.6182677499600686,35.37604424145024,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,4,0,0,f0df217a-d72c-4b5c-b4a7-87c267716da0,short,106,128,2026-08-31T11:49:55.436979+00:00,0.11441224999725819,2.9100067079998553,20,96,4138216.428719222,33.47564745836445,32.989614675487815,12.524156374973245,35.77087243139417,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,4,0,1,9565d3c0-e753-4a7b-be43-115556beec5b,medium,252,128,2026-08-31T11:49:55.437104+00:00,6.277438874996733,9.582254499953706,43,128,3865168.539325843,37.881971614565146,13.358025504396528,12.524156374973245,35.77087243139417,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,4,0,2,42b7e290-9d92-4647-bbdb-3b3ba99f4c3e,code,267,128,2026-08-31T11:49:55.436744+00:00,3.0367828750167973,6.193101375014521,54,128,771.3321549092078,39.94659431201623,20.66815836672783,12.524156374973245,35.77087243139417,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,4,0,3,c22aaea0-7394-47e8-b6ab-25444fc113d1,short,106,128,2026-08-31T11:49:55.437235+00:00,9.661167457990814,12.522873707988765,20,96,3966679.888932963,32.71048444655768,7.665972063485584,12.524156374973245,35.77087243139417,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,4,1,0,84f401af-117d-4956-b939-fdbb1e1ceecf,medium,252,128,2026-08-31T11:50:07.961234+00:00,3.091476584027987,6.373854791978374,43,128,5375000.0,38.1244834091544,20.08203891953902,12.858689875050914,37.32884179214249,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,4,1,1,b3c9f50e-fcf6-4ad6-b00f-9de925c9092a,code,267,128,2026-08-31T11:50:07.961465+00:00,9.849772959016263,12.85736475000158,54,128,11076923.076923078,41.56311628897905,9.955383742223248,12.858689875050914,37.32884179214249,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,4,1,2,5f528a81-943d-445a-a2f2-9b986c01c96e,short,106,128,2026-08-31T11:50:07.961041+00:00,0.11284091597190127,3.010363540961407,20,96,1476995.7905619969,32.336156802028626,31.889836125686298,12.858689875050914,37.32884179214249,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,warmup,4,1,3,45991adb-aae4-4122-bb0d-21d34b549b46,medium,252,128,2026-08-31T11:50:07.960837+00:00,6.452098417037632,9.774627042002976,43,128,7319148.936170213,37.70880560635668,13.095128791100224,12.858689875050914,37.32884179214249,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,0,0,1cd3b269-0ed7-4470-9bf5-9aba6dbdda3b,short,106,128,2026-08-31T11:50:20.819745+00:00,9.799659290991258,12.57556495803874,20,96,2461538.461538462,33.69646737394496,7.633851864335801,12.576361375045963,35.781414558656905,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,0,1,b2258258-f465-4131-bb56-cdead87e67c5,medium,252,128,2026-08-31T11:50:20.820473+00:00,2.9737471669795923,6.33726870897226,43,128,4755585.04755585,37.255703188397476,20.19797579654126,12.576361375045963,35.781414558656905,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,0,2,9bb209a2-19a6-4172-a166-c29a75683a37,code,267,128,2026-08-31T11:50:20.819981+00:00,0.11236062500393018,2.89358854200691,54,128,3661016.9491525427,44.88156766233007,44.23572949014475,12.576361375045963,35.781414558656905,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,0,3,c74fbeef-16a3-40b2-ade6-0b24b3ee0147,short,106,128,2026-08-31T11:50:20.820727+00:00,6.417795290995855,9.71814520796761,20,98,2608582.235554976,29.056692998778793,10.084228821735737,12.576361375045963,35.781414558656905,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,1,0,844d6c49-9989-400d-bb5d-31f8490da904,medium,252,128,2026-08-31T11:50:33.396890+00:00,10.48226895800326,14.052842833043542,43,128,5083944.194845118,35.11947732750843,9.108477303896379,14.054668250028044,34.152353613828076,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,1,1,213efda7-5da6-47a7-9517-f63ad082e62e,code,267,128,2026-08-31T11:50:33.397263+00:00,0.11672520800493658,3.508996458025649,54,128,3630252.100840336,36.93011583511385,36.47766577456727,14.054668250028044,34.152353613828076,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,1,2,d03d55d9-a506-44a9-887e-e0ab77392c8d,short,106,128,2026-08-31T11:50:33.397083+00:00,3.606067124987021,6.893670374993235,20,96,3356267.830172848,28.527554720530254,13.925818145909567,14.054668250028044,34.152353613828076,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,1,3,55be3260-b3a0-422a-b918-a81261da6a84,medium,252,128,2026-08-31T11:50:33.396391+00:00,6.9750645000021905,10.400937125028577,43,128,6745098.039215687,36.57719818551596,12.30658338391295,14.054668250028044,34.152353613828076,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,2,0,930b484d-3177-4ee9-9d72-5442ee8cd7c9,code,267,128,2026-08-31T11:50:47.451672+00:00,0.11444733297685161,3.540263083006721,54,128,4248957.431741286,36.58630699945727,36.15550511327833,14.210740375041496,33.918007597024484,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,2,1,231f3cbb-61f2-4042-8a99-def6a8698a7d,short,106,128,2026-08-31T11:50:47.451387+00:00,10.67886250000447,14.209862457995769,20,98,2840102.243680773,27.132075592063398,6.896618478165229,14.210740375041496,33.918007597024484,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,2,2,32437705-bf67-438f-bad7-0bb10d0e2030,medium,252,128,2026-08-31T11:50:47.451856+00:00,3.622358249966055,7.2201729999505915,43,128,4777777.777777778,34.87549075162609,17.72810706902396,14.210740375041496,33.918007597024484,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,2,3,a16a724c-155d-4e2d-ba28-3a8683af4d40,code,267,128,2026-08-31T11:50:47.451136+00:00,7.304396207968239,10.594903749995865,54,128,17515407.071034707,38.04511611184116,12.081280115456448,14.210740375041496,33.918007597024484,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,3,0,f6ab47e7-5bdf-4b5c-be3f-0e639727a2bb,short,106,128,2026-08-31T11:51:01.661760+00:00,10.42098737496417,14.485269291966688,20,96,2105263.1578947366,23.198198961620538,6.627422525947802,14.485774166998453,30.926893850149572,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,3,1,8e015249-8b0c-4560-b93d-603afb968f5b,medium,252,128,2026-08-31T11:51:01.662046+00:00,0.11227079102536663,3.6567685829941183,43,128,3571131.9657835728,35.39152606628793,35.00358228717748,14.485774166998453,30.926893850149572,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,3,2,d2848890-f070-45de-8a2f-4bb2b8788a87,code,267,128,2026-08-31T11:51:01.661862+00:00,7.207546124991495,10.33818608301226,54,128,9458749.343142407,39.94848206301452,12.381282264819164,14.485774166998453,30.926893850149572,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,3,3,aba512eb-9825-4e49-9ab8-0c75678ff654,short,106,128,2026-08-31T11:51:01.661952+00:00,3.738764916022774,7.12777191598434,20,96,2652168.1474605487,27.731643965337334,13.468444435590849,14.485774166998453,30.926893850149572,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,4,0,4c24ae09-884b-4b94-ae8e-37346f1408f2,medium,252,128,2026-08-31T11:51:16.148220+00:00,10.924698917020578,15.198258958000224,43,128,7068880.486602006,29.434480556585335,8.422017308280036,15.199551291007083,31.579879616840746,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,4,1,c94ceb91-b83d-4d47-a36d-71741993f366,code,267,128,2026-08-31T11:51:16.148464+00:00,0.12565479200566188,3.500943167018704,54,128,4025044.7227191413,37.03108618648992,36.56157609350765,15.199551291007083,31.579879616840746,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,4,2,0672967f-d135-44b0-b89f-7995f59b2d8c,short,106,128,2026-08-31T11:51:16.148378+00:00,7.600669999956153,10.846751042001415,20,96,2666666.6666666665,28.898123213254255,8.850576511645125,15.199551291007083,31.579879616840746,
|
||||
20260831T114928Z,ollama,qwen3.8:27b-mlx,measured,4,4,3,8185344b-c228-457a-8c3d-6a7b5f803594,medium,252,128,2026-08-31T11:51:16.147977+00:00,3.5925854169763625,7.520279875025153,43,128,4229785.559708833,31.98591420303284,17.02064313126004,15.199551291007083,31.579879616840746,
|
||||
|
842
benchmarks/inference/results/20260831T114928Z/raw.json
Normal file
842
benchmarks/inference/results/20260831T114928Z/raw.json
Normal file
@@ -0,0 +1,842 @@
|
||||
[
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "0bd09e14-c217-44ad-b0a1-98600e1bf40e",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:33.251646+00:00",
|
||||
"ttft_s": 3.627692041976843,
|
||||
"total_s": 5.577126249962021,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 116.69505030650684,
|
||||
"decode_tps": 46.54721674973356,
|
||||
"request_tps": 17.213166010121025,
|
||||
"group_elapsed_s": 5.578097124991473,
|
||||
"group_output_tps": 17.210170036282175,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "ada11e2f-0b97-42ec-a5be-5175f0bb29b1",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:38.829357+00:00",
|
||||
"ttft_s": 0.3621791250188835,
|
||||
"total_s": 2.7543381249997765,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 157.23847751774449,
|
||||
"decode_tps": 52.253166030964316,
|
||||
"request_tps": 46.472144737135494,
|
||||
"group_elapsed_s": 2.7547111669555306,
|
||||
"group_output_tps": 46.46585149667936,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "a3bd0047-d992-4553-9b17-4472b6290acc",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:41.584102+00:00",
|
||||
"ttft_s": 0.11936691601295024,
|
||||
"total_s": 2.1721785410190932,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 448.5805263612496,
|
||||
"decode_tps": 45.72630609321048,
|
||||
"request_tps": 44.19526212378514,
|
||||
"group_elapsed_s": 2.172526082955301,
|
||||
"group_output_tps": 44.18819214792146,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "a8033a77-d60f-42b4-a2a9-8f6a97ef3496",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:43.757773+00:00",
|
||||
"ttft_s": 0.14179470797535032,
|
||||
"total_s": 2.78225216595456,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 816.5668113066018,
|
||||
"decode_tps": 47.377908815894095,
|
||||
"request_tps": 46.00589463683088,
|
||||
"group_elapsed_s": 2.7835853330325335,
|
||||
"group_output_tps": 45.98386062788756,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "9cc954fc-95f5-474e-b219-8a89d7091934",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:46.540349+00:00",
|
||||
"ttft_s": 0.45632574998307973,
|
||||
"total_s": 2.7544727920321748,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 146.71421293937848,
|
||||
"decode_tps": 54.2491762219149,
|
||||
"request_tps": 46.46987269951035,
|
||||
"group_elapsed_s": 2.754789875005372,
|
||||
"group_output_tps": 46.46452390484062,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "e8ee5060-7c14-4c34-bd5b-76d7e51fef07",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:49.295554+00:00",
|
||||
"ttft_s": 0.0983880830463022,
|
||||
"total_s": 2.5220755000482313,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 2758620.689655172,
|
||||
"decode_tps": 38.503422116977305,
|
||||
"request_tps": 38.063888253212134,
|
||||
"group_elapsed_s": 2.522709292010404,
|
||||
"group_output_tps": 38.054325285929174,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "edd132c8-7aaa-4eb0-98e8-2b2d711f2cf9",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:51.817976+00:00",
|
||||
"ttft_s": 0.09851625002920628,
|
||||
"total_s": 3.6179742500535212,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 3245283.0188679243,
|
||||
"decode_tps": 35.649936286183205,
|
||||
"request_tps": 35.3789140423281,
|
||||
"group_elapsed_s": 3.6182677499600686,
|
||||
"group_output_tps": 35.37604424145024,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "f0df217a-d72c-4b5c-b4a7-87c267716da0",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:55.436979+00:00",
|
||||
"ttft_s": 0.11441224999725819,
|
||||
"total_s": 2.9100067079998553,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 4138216.428719222,
|
||||
"decode_tps": 33.47564745836445,
|
||||
"request_tps": 32.989614675487815,
|
||||
"group_elapsed_s": 12.524156374973245,
|
||||
"group_output_tps": 35.77087243139417,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 1,
|
||||
"request_id": "9565d3c0-e753-4a7b-be43-115556beec5b",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:55.437104+00:00",
|
||||
"ttft_s": 6.277438874996733,
|
||||
"total_s": 9.582254499953706,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 3865168.539325843,
|
||||
"decode_tps": 37.881971614565146,
|
||||
"request_tps": 13.358025504396528,
|
||||
"group_elapsed_s": 12.524156374973245,
|
||||
"group_output_tps": 35.77087243139417,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 2,
|
||||
"request_id": "42b7e290-9d92-4647-bbdb-3b3ba99f4c3e",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:55.436744+00:00",
|
||||
"ttft_s": 3.0367828750167973,
|
||||
"total_s": 6.193101375014521,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 771.3321549092078,
|
||||
"decode_tps": 39.94659431201623,
|
||||
"request_tps": 20.66815836672783,
|
||||
"group_elapsed_s": 12.524156374973245,
|
||||
"group_output_tps": 35.77087243139417,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 3,
|
||||
"request_id": "c22aaea0-7394-47e8-b6ab-25444fc113d1",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:49:55.437235+00:00",
|
||||
"ttft_s": 9.661167457990814,
|
||||
"total_s": 12.522873707988765,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 3966679.888932963,
|
||||
"decode_tps": 32.71048444655768,
|
||||
"request_tps": 7.665972063485584,
|
||||
"group_elapsed_s": 12.524156374973245,
|
||||
"group_output_tps": 35.77087243139417,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "84f401af-117d-4956-b939-fdbb1e1ceecf",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:07.961234+00:00",
|
||||
"ttft_s": 3.091476584027987,
|
||||
"total_s": 6.373854791978374,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 5375000.0,
|
||||
"decode_tps": 38.1244834091544,
|
||||
"request_tps": 20.08203891953902,
|
||||
"group_elapsed_s": 12.858689875050914,
|
||||
"group_output_tps": 37.32884179214249,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 1,
|
||||
"request_id": "b3c9f50e-fcf6-4ad6-b00f-9de925c9092a",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:07.961465+00:00",
|
||||
"ttft_s": 9.849772959016263,
|
||||
"total_s": 12.85736475000158,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 11076923.076923078,
|
||||
"decode_tps": 41.56311628897905,
|
||||
"request_tps": 9.955383742223248,
|
||||
"group_elapsed_s": 12.858689875050914,
|
||||
"group_output_tps": 37.32884179214249,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 2,
|
||||
"request_id": "5f528a81-943d-445a-a2f2-9b986c01c96e",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:07.961041+00:00",
|
||||
"ttft_s": 0.11284091597190127,
|
||||
"total_s": 3.010363540961407,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 1476995.7905619969,
|
||||
"decode_tps": 32.336156802028626,
|
||||
"request_tps": 31.889836125686298,
|
||||
"group_elapsed_s": 12.858689875050914,
|
||||
"group_output_tps": 37.32884179214249,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 3,
|
||||
"request_id": "45991adb-aae4-4122-bb0d-21d34b549b46",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:07.960837+00:00",
|
||||
"ttft_s": 6.452098417037632,
|
||||
"total_s": 9.774627042002976,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 7319148.936170213,
|
||||
"decode_tps": 37.70880560635668,
|
||||
"request_tps": 13.095128791100224,
|
||||
"group_elapsed_s": 12.858689875050914,
|
||||
"group_output_tps": 37.32884179214249,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "1cd3b269-0ed7-4470-9bf5-9aba6dbdda3b",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:20.819745+00:00",
|
||||
"ttft_s": 9.799659290991258,
|
||||
"total_s": 12.57556495803874,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 2461538.461538462,
|
||||
"decode_tps": 33.69646737394496,
|
||||
"request_tps": 7.633851864335801,
|
||||
"group_elapsed_s": 12.576361375045963,
|
||||
"group_output_tps": 35.781414558656905,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 1,
|
||||
"request_id": "b2258258-f465-4131-bb56-cdead87e67c5",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:20.820473+00:00",
|
||||
"ttft_s": 2.9737471669795923,
|
||||
"total_s": 6.33726870897226,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 4755585.04755585,
|
||||
"decode_tps": 37.255703188397476,
|
||||
"request_tps": 20.19797579654126,
|
||||
"group_elapsed_s": 12.576361375045963,
|
||||
"group_output_tps": 35.781414558656905,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 2,
|
||||
"request_id": "9bb209a2-19a6-4172-a166-c29a75683a37",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:20.819981+00:00",
|
||||
"ttft_s": 0.11236062500393018,
|
||||
"total_s": 2.89358854200691,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 3661016.9491525427,
|
||||
"decode_tps": 44.88156766233007,
|
||||
"request_tps": 44.23572949014475,
|
||||
"group_elapsed_s": 12.576361375045963,
|
||||
"group_output_tps": 35.781414558656905,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 3,
|
||||
"request_id": "c74fbeef-16a3-40b2-ade6-0b24b3ee0147",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:20.820727+00:00",
|
||||
"ttft_s": 6.417795290995855,
|
||||
"total_s": 9.71814520796761,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 98,
|
||||
"prompt_tps": 2608582.235554976,
|
||||
"decode_tps": 29.056692998778793,
|
||||
"request_tps": 10.084228821735737,
|
||||
"group_elapsed_s": 12.576361375045963,
|
||||
"group_output_tps": 35.781414558656905,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "844d6c49-9989-400d-bb5d-31f8490da904",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:33.396890+00:00",
|
||||
"ttft_s": 10.48226895800326,
|
||||
"total_s": 14.052842833043542,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 5083944.194845118,
|
||||
"decode_tps": 35.11947732750843,
|
||||
"request_tps": 9.108477303896379,
|
||||
"group_elapsed_s": 14.054668250028044,
|
||||
"group_output_tps": 34.152353613828076,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 1,
|
||||
"request_id": "213efda7-5da6-47a7-9517-f63ad082e62e",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:33.397263+00:00",
|
||||
"ttft_s": 0.11672520800493658,
|
||||
"total_s": 3.508996458025649,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 3630252.100840336,
|
||||
"decode_tps": 36.93011583511385,
|
||||
"request_tps": 36.47766577456727,
|
||||
"group_elapsed_s": 14.054668250028044,
|
||||
"group_output_tps": 34.152353613828076,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 2,
|
||||
"request_id": "d03d55d9-a506-44a9-887e-e0ab77392c8d",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:33.397083+00:00",
|
||||
"ttft_s": 3.606067124987021,
|
||||
"total_s": 6.893670374993235,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 3356267.830172848,
|
||||
"decode_tps": 28.527554720530254,
|
||||
"request_tps": 13.925818145909567,
|
||||
"group_elapsed_s": 14.054668250028044,
|
||||
"group_output_tps": 34.152353613828076,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 3,
|
||||
"request_id": "55be3260-b3a0-422a-b918-a81261da6a84",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:33.396391+00:00",
|
||||
"ttft_s": 6.9750645000021905,
|
||||
"total_s": 10.400937125028577,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 6745098.039215687,
|
||||
"decode_tps": 36.57719818551596,
|
||||
"request_tps": 12.30658338391295,
|
||||
"group_elapsed_s": 14.054668250028044,
|
||||
"group_output_tps": 34.152353613828076,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "930b484d-3177-4ee9-9d72-5442ee8cd7c9",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:47.451672+00:00",
|
||||
"ttft_s": 0.11444733297685161,
|
||||
"total_s": 3.540263083006721,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 4248957.431741286,
|
||||
"decode_tps": 36.58630699945727,
|
||||
"request_tps": 36.15550511327833,
|
||||
"group_elapsed_s": 14.210740375041496,
|
||||
"group_output_tps": 33.918007597024484,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 1,
|
||||
"request_id": "231f3cbb-61f2-4042-8a99-def6a8698a7d",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:47.451387+00:00",
|
||||
"ttft_s": 10.67886250000447,
|
||||
"total_s": 14.209862457995769,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 98,
|
||||
"prompt_tps": 2840102.243680773,
|
||||
"decode_tps": 27.132075592063398,
|
||||
"request_tps": 6.896618478165229,
|
||||
"group_elapsed_s": 14.210740375041496,
|
||||
"group_output_tps": 33.918007597024484,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 2,
|
||||
"request_id": "32437705-bf67-438f-bad7-0bb10d0e2030",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:47.451856+00:00",
|
||||
"ttft_s": 3.622358249966055,
|
||||
"total_s": 7.2201729999505915,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 4777777.777777778,
|
||||
"decode_tps": 34.87549075162609,
|
||||
"request_tps": 17.72810706902396,
|
||||
"group_elapsed_s": 14.210740375041496,
|
||||
"group_output_tps": 33.918007597024484,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 3,
|
||||
"request_id": "a16a724c-155d-4e2d-ba28-3a8683af4d40",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:50:47.451136+00:00",
|
||||
"ttft_s": 7.304396207968239,
|
||||
"total_s": 10.594903749995865,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 17515407.071034707,
|
||||
"decode_tps": 38.04511611184116,
|
||||
"request_tps": 12.081280115456448,
|
||||
"group_elapsed_s": 14.210740375041496,
|
||||
"group_output_tps": 33.918007597024484,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "f6ab47e7-5bdf-4b5c-be3f-0e639727a2bb",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:51:01.661760+00:00",
|
||||
"ttft_s": 10.42098737496417,
|
||||
"total_s": 14.485269291966688,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 2105263.1578947366,
|
||||
"decode_tps": 23.198198961620538,
|
||||
"request_tps": 6.627422525947802,
|
||||
"group_elapsed_s": 14.485774166998453,
|
||||
"group_output_tps": 30.926893850149572,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 1,
|
||||
"request_id": "8e015249-8b0c-4560-b93d-603afb968f5b",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:51:01.662046+00:00",
|
||||
"ttft_s": 0.11227079102536663,
|
||||
"total_s": 3.6567685829941183,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 3571131.9657835728,
|
||||
"decode_tps": 35.39152606628793,
|
||||
"request_tps": 35.00358228717748,
|
||||
"group_elapsed_s": 14.485774166998453,
|
||||
"group_output_tps": 30.926893850149572,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 2,
|
||||
"request_id": "d2848890-f070-45de-8a2f-4bb2b8788a87",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:51:01.661862+00:00",
|
||||
"ttft_s": 7.207546124991495,
|
||||
"total_s": 10.33818608301226,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 9458749.343142407,
|
||||
"decode_tps": 39.94848206301452,
|
||||
"request_tps": 12.381282264819164,
|
||||
"group_elapsed_s": 14.485774166998453,
|
||||
"group_output_tps": 30.926893850149572,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 3,
|
||||
"request_id": "aba512eb-9825-4e49-9ab8-0c75678ff654",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:51:01.661952+00:00",
|
||||
"ttft_s": 3.738764916022774,
|
||||
"total_s": 7.12777191598434,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 2652168.1474605487,
|
||||
"decode_tps": 27.731643965337334,
|
||||
"request_tps": 13.468444435590849,
|
||||
"group_elapsed_s": 14.485774166998453,
|
||||
"group_output_tps": 30.926893850149572,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "4c24ae09-884b-4b94-ae8e-37346f1408f2",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:51:16.148220+00:00",
|
||||
"ttft_s": 10.924698917020578,
|
||||
"total_s": 15.198258958000224,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 7068880.486602006,
|
||||
"decode_tps": 29.434480556585335,
|
||||
"request_tps": 8.422017308280036,
|
||||
"group_elapsed_s": 15.199551291007083,
|
||||
"group_output_tps": 31.579879616840746,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 1,
|
||||
"request_id": "c94ceb91-b83d-4d47-a36d-71741993f366",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:51:16.148464+00:00",
|
||||
"ttft_s": 0.12565479200566188,
|
||||
"total_s": 3.500943167018704,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 4025044.7227191413,
|
||||
"decode_tps": 37.03108618648992,
|
||||
"request_tps": 36.56157609350765,
|
||||
"group_elapsed_s": 15.199551291007083,
|
||||
"group_output_tps": 31.579879616840746,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 2,
|
||||
"request_id": "0672967f-d135-44b0-b89f-7995f59b2d8c",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:51:16.148378+00:00",
|
||||
"ttft_s": 7.600669999956153,
|
||||
"total_s": 10.846751042001415,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 2666666.6666666665,
|
||||
"decode_tps": 28.898123213254255,
|
||||
"request_tps": 8.850576511645125,
|
||||
"group_elapsed_s": 15.199551291007083,
|
||||
"group_output_tps": 31.579879616840746,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T114928Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 3,
|
||||
"request_id": "8185344b-c228-457a-8c3d-6a7b5f803594",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T11:51:16.147977+00:00",
|
||||
"ttft_s": 3.5925854169763625,
|
||||
"total_s": 7.520279875025153,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 4229785.559708833,
|
||||
"decode_tps": 31.98591420303284,
|
||||
"request_tps": 17.02064313126004,
|
||||
"group_elapsed_s": 15.199551291007083,
|
||||
"group_output_tps": 31.579879616840746,
|
||||
"error": null
|
||||
}
|
||||
]
|
||||
54
benchmarks/inference/results/20260831T114928Z/summary.json
Normal file
54
benchmarks/inference/results/20260831T114928Z/summary.json
Normal file
@@ -0,0 +1,54 @@
|
||||
[
|
||||
{
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"concurrency": 1,
|
||||
"requests": 5,
|
||||
"successes": 5,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 0.18287834140937775,
|
||||
"ttft_s_p50": 0.11936691601295024,
|
||||
"ttft_s_p95": 0.3934195415815338,
|
||||
"total_s_mean": 2.769790649821516,
|
||||
"total_s_p50": 2.7544727920321748,
|
||||
"total_s_p95": 3.450829833233729,
|
||||
"prompt_tps_mean": 1201063.1140147406,
|
||||
"prompt_tps_p50": 816.5668113066018,
|
||||
"prompt_tps_p95": 3147950.5530253737,
|
||||
"decode_tps_mean": 44.301349906835995,
|
||||
"decode_tps_p50": 45.72630609321048,
|
||||
"decode_tps_p95": 52.87492274071074,
|
||||
"request_tps_mean": 42.02276635113332,
|
||||
"request_tps_p50": 44.19526212378514,
|
||||
"request_tps_p95": 46.37707708697445,
|
||||
"aggregate_output_tps_mean": 42.01338924160581,
|
||||
"aggregate_output_tps_p50": 44.18819214792146,
|
||||
"aggregate_output_tps_p95": 46.368391249450006
|
||||
},
|
||||
{
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"concurrency": 4,
|
||||
"requests": 20,
|
||||
"successes": 20,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 5.296346539442311,
|
||||
"ttft_s_p50": 5.078280103509314,
|
||||
"ttft_s_p95": 10.691154320855276,
|
||||
"total_s_mean": 8.731022270751419,
|
||||
"total_s_p50": 8.619212541496381,
|
||||
"total_s_p95": 14.520918775268365,
|
||||
"prompt_tps_mean": 4873110.971654413,
|
||||
"prompt_tps_p50": 3843030.8359358422,
|
||||
"prompt_tps_p95": 9861582.229537027,
|
||||
"decode_tps_mean": 33.61516109813652,
|
||||
"decode_tps_p50": 34.997484039567254,
|
||||
"decode_tps_p95": 40.1951363429803,
|
||||
"request_tps_mean": 18.258369295759792,
|
||||
"request_tps_p50": 12.924863350205007,
|
||||
"request_tps_p95": 36.94528376333951,
|
||||
"aggregate_output_tps_mean": 33.27170984729996,
|
||||
"aggregate_output_tps_p50": 33.918007597024484,
|
||||
"aggregate_output_tps_p95": 35.45560236969114
|
||||
}
|
||||
]
|
||||
135
benchmarks/inference/results/20260831T121855Z/metadata.json
Normal file
135
benchmarks/inference/results/20260831T121855Z/metadata.json
Normal file
File diff suppressed because one or more lines are too long
36
benchmarks/inference/results/20260831T121855Z/raw.csv
Normal file
36
benchmarks/inference/results/20260831T121855Z/raw.csv
Normal file
@@ -0,0 +1,36 @@
|
||||
run_id,runtime,model,phase,concurrency,round,slot,request_id,prompt_name,prompt_chars,max_tokens,started_at,ttft_s,total_s,prompt_tokens,output_tokens,prompt_tps,decode_tps,request_tps,group_elapsed_s,group_output_tps,error
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,1,0,0,556d36df-74f6-4dba-866f-134c99f385ac,short,106,128,2026-08-31T12:19:01.706610+00:00,8.133006000018213,13.098198042018339,20,95,80.39981477169073,18.60021913626931,7.252906063509266,13.099143458006438,7.252382593148428,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,1,1,0,456b9efb-0afa-48e4-8093-041758c70c7d,medium,252,128,2026-08-31T12:19:14.805394+00:00,0.6389443330117501,6.043248832982499,43,128,91.99219534791703,23.084069916067204,21.180660194134138,6.043762709014118,21.178859290602404,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,1,0,0,78330ae3-a01a-4bf4-b1b6-e4ae861145a8,short,106,128,2026-08-31T12:19:20.848831+00:00,0.25939199997810647,5.077765540976543,20,95,194.8949698826367,19.20226982827757,18.709016639970706,5.077990833029617,18.708186588694836,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,1,1,0,f8373947-d690-42a4-b613-33f71746b2f9,medium,252,128,2026-08-31T12:19:25.927037+00:00,0.25913220801157877,5.760092166019604,43,128,423.79232394227944,22.737809958094928,22.22186664913243,5.761121416988317,22.217896609947385,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,1,2,0,9e12f0f4-50d6-444c-8752-4565aa55084b,code,267,128,2026-08-31T12:19:31.688098+00:00,0.6637360000167973,5.271547083975747,54,128,115.32507388679936,26.793290081008884,24.281296924974765,5.271936749981251,24.27950221528269,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,1,3,0,583bec1f-0983-4208-8635-439a9a0c5424,short,106,128,2026-08-31T12:19:36.960047+00:00,0.15107908402569592,5.119054667011369,20,95,4102564.1025641025,18.66803886577614,18.558113983858536,5.11973733396735,18.555639440663118,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,1,4,0,641937dd-533c-493e-b7b3-3fa2cc6e8879,medium,252,128,2026-08-31T12:19:42.079662+00:00,0.1495445409673266,5.59909695800161,43,128,3794229.2420365307,22.9734392268289,22.86082933732315,5.599817292008083,22.85788862838049,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,4,0,0,3dbdfe4c-7d43-4575-a1e6-6b74bd5a10a7,short,106,128,2026-08-31T12:19:47.680109+00:00,0.16311579098692164,4.8760897910106,20,95,1791151.7105498835,19.64848684540538,19.482824162741817,22.031325709016528,20.24390206429885,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,4,0,1,1ea04fa9-7f60-4936-ba53-6829df8e5714,medium,252,128,2026-08-31T12:19:47.680573+00:00,10.314829125010874,16.516400250024162,43,128,6370370.37037037,20.216323480613685,7.749872736331438,22.031325709016528,20.24390206429885,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,4,0,2,046681e1-e7be-4c58-8284-88f821e4a8a0,code,267,128,2026-08-31T12:19:47.680452+00:00,5.110771542007569,10.15410141699249,54,128,514.3377603686088,24.759396813702583,12.605743703307615,22.031325709016528,20.24390206429885,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,4,0,3,f496e50f-a2db-4fad-a2e1-2a7965fd862d,short,106,128,2026-08-31T12:19:47.680317+00:00,16.645131999976,22.03015966597013,20,95,6666666.666666666,17.25091779989875,4.312270153300159,22.031325709016528,20.24390206429885,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,4,1,0,cb3d0e9e-0a6f-4f36-aec9-4b20cbc8f87d,medium,252,128,2026-08-31T12:20:09.710819+00:00,17.595250790996943,23.510470708017237,43,128,19843101.06137517,21.163606353137514,5.444382700357892,23.51121658302145,20.37325454038428,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,4,1,1,fa3bb29e-7370-4255-877e-376076d7aa76,code,267,128,2026-08-31T12:20:09.711021+00:00,5.7327396660111845,11.353798499971163,54,128,9000000.0,22.18879858004337,11.273760054868431,23.51121658302145,20.37325454038428,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,4,1,2,93ec5b28-1a29-426a-96ff-b3b525fb3c71,short,106,128,2026-08-31T12:20:09.710927+00:00,0.1655573329771869,5.57563720800681,20,95,1563477.1732332706,17.170644798585553,17.038411298277563,23.51121658302145,20.37325454038428,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,warmup,4,1,3,dcac6e9a-3580-4bb1-8787-9cef1c64bfd5,medium,252,128,2026-08-31T12:20:09.711149+00:00,11.527663582994137,17.459117082995363,43,128,6331909.880724489,21.03978753266432,7.331413117371669,23.51121658302145,20.37325454038428,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,0,0,d42caf5b-fb6a-4e96-8e42-fd0b8fc1945b,short,106,128,2026-08-31T12:20:33.222727+00:00,6.285906166012865,10.864910541044082,20,95,8421052.631578946,20.156958877874334,8.743744335594945,21.625605207984336,20.623700271534293,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,0,1,87483860-d4c6-4f13-928c-48de78b6ef70,medium,252,128,2026-08-31T12:20:33.222336+00:00,0.17068937502335757,6.147177167003974,43,128,4669345.205776958,20.965937740191077,20.822565630133763,21.625605207984336,20.623700271534293,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,0,2,ee57b9cf-06bc-468b-bd1e-f936abf292df,code,267,128,2026-08-31T12:20:33.222603+00:00,16.19913299998734,21.62435016600648,54,128,11675675.675675677,22.963769927247082,5.919253018812849,21.625605207984336,20.623700271534293,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,0,3,13164aa4-836c-4761-8f99-95bfe18d33a1,short,106,128,2026-08-31T12:20:33.222066+00:00,11.00553745898651,16.043328458967153,20,95,10214504.596527068,18.355407643172423,5.9214645042626,21.625605207984336,20.623700271534293,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,1,0,51389c06-2a1c-4dcb-a847-5f0c914e298c,medium,252,128,2026-08-31T12:20:54.847154+00:00,0.16574266698444262,6.310333041998092,43,128,5402688.779997488,20.423563700405246,20.284190889466956,23.574590582982637,20.318486478648204,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,1,1,1952ea53-9c68-4536-8e9d-089790a8bdee,code,267,128,2026-08-31T12:20:54.847267+00:00,18.0774574590032,23.57407404197147,54,128,6513086.47931492,22.77481444475703,5.4296936444717945,23.574590582982637,20.318486478648204,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,1,2,d71abf03-e17c-42b0-b6bb-c57bf6961bc2,short,106,128,2026-08-31T12:20:54.847373+00:00,12.635340875014663,17.94654095900478,20,95,9229349.330872172,17.481471270830138,5.293499188339869,23.574590582982637,20.318486478648204,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,1,3,4e10d58d-5d6d-46e7-8254-46dd35cfeb9f,medium,252,128,2026-08-31T12:20:54.847461+00:00,6.461538125004154,12.505505541979801,43,128,3739130.434782609,20.730070992395465,10.235491845596812,23.574590582982637,20.318486478648204,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,2,0,63b32437-7995-44f4-b5ca-f0f52da2bda7,code,267,128,2026-08-31T12:21:18.421714+00:00,17.908610125014093,23.736398082983214,54,128,15071169.411108011,21.428265908373906,5.392562070812423,23.736987709009554,20.179477104341757,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,2,1,3b8fa85d-5574-4ac2-b33c-7208ef99a34f,short,106,128,2026-08-31T12:21:18.421631+00:00,6.036650207999628,11.081229583011009,20,95,4571428.571428572,18.37088402458498,8.573055840810985,23.736987709009554,20.179477104341757,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,2,2,76178335-d531-49f7-83d5-84a414d73ce5,medium,252,128,2026-08-31T12:21:18.421520+00:00,11.268355667009018,17.757357084017713,43,128,7533286.615276804,19.182821184166418,7.208279891786645,23.736987709009554,20.179477104341757,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,2,3,728d2a73-194b-41bb-9dda-216960415fcf,code,267,128,2026-08-31T12:21:18.421818+00:00,0.17636983300326392,5.888466249976773,54,128,7200000.0,21.89716979543998,21.737409125934093,23.736987709009554,20.179477104341757,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,3,0,dfcbb66f-3170-41e1-a4e1-a9b7449517ce,short,106,128,2026-08-31T12:21:42.158434+00:00,6.034018917009234,11.539304499980062,20,95,3200000.0,16.88203353475361,8.232731877399036,23.861715458042454,18.69102834556173,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,3,1,04f9942b-bc73-4665-9830-40b7a50beb96,medium,252,128,2026-08-31T12:21:42.158640+00:00,11.68165541702183,18.32316145801451,43,128,9921550.530687585,18.896968681699633,6.985694051394885,23.861715458042454,18.69102834556173,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,3,2,e2e252a5-26bf-4277-a744-cf7456cdfac7,code,267,128,2026-08-31T12:21:42.158549+00:00,0.17531787499319762,5.8762462079757825,54,128,5355548.943766736,21.95473700787165,21.782613503543573,23.861715458042454,18.69102834556173,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,3,3,61a1f98f-fb9a-49a8-8f00-04bb52b494cc,short,106,128,2026-08-31T12:21:42.158328+00:00,18.46465341700241,23.86128708301112,20,95,5782017.924255566,17.187946685051212,3.981344328556299,23.861715458042454,18.69102834556173,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,4,0,ae555d62-2572-4a62-8cd6-7ae714aace26,medium,252,128,2026-08-31T12:22:06.019994+00:00,20.83534020796651,28.275580540997908,43,128,7937973.047812442,16.887931275751107,4.526874340012493,28.276262458995916,16.940004029691313,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,4,1,c0147505-dd4a-4ad8-bb9d-0955114a8ee0,code,267,128,2026-08-31T12:22:06.020061+00:00,13.962619374971837,20.66803166596219,54,128,10125632.852053255,18.57306514141657,6.193139340443381,28.276262458995916,16.940004029691313,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,4,2,3a3d625f-5d64-42d0-9145-3056ea9864db,short,106,128,2026-08-31T12:22:06.019916+00:00,7.783273542008828,13.761600458994508,20,95,1927710.843373494,15.539155324201145,6.903266831722942,28.276262458995916,16.940004029691313,
|
||||
20260831T121855Z,ollama,qwen3.8:27b-mxfp8,measured,4,4,3,8ea78898-3c59-49f2-9734-f01bb668d810,medium,252,128,2026-08-31T12:22:06.019812+00:00,0.17432458401890472,7.616022333968431,43,128,2866666.6666666665,16.90294641795698,16.806673403399,28.276262458995916,16.940004029691313,
|
||||
|
842
benchmarks/inference/results/20260831T121855Z/raw.json
Normal file
842
benchmarks/inference/results/20260831T121855Z/raw.json
Normal file
@@ -0,0 +1,842 @@
|
||||
[
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "556d36df-74f6-4dba-866f-134c99f385ac",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:01.706610+00:00",
|
||||
"ttft_s": 8.133006000018213,
|
||||
"total_s": 13.098198042018339,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 80.39981477169073,
|
||||
"decode_tps": 18.60021913626931,
|
||||
"request_tps": 7.252906063509266,
|
||||
"group_elapsed_s": 13.099143458006438,
|
||||
"group_output_tps": 7.252382593148428,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "456b9efb-0afa-48e4-8093-041758c70c7d",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:14.805394+00:00",
|
||||
"ttft_s": 0.6389443330117501,
|
||||
"total_s": 6.043248832982499,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 91.99219534791703,
|
||||
"decode_tps": 23.084069916067204,
|
||||
"request_tps": 21.180660194134138,
|
||||
"group_elapsed_s": 6.043762709014118,
|
||||
"group_output_tps": 21.178859290602404,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "78330ae3-a01a-4bf4-b1b6-e4ae861145a8",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:20.848831+00:00",
|
||||
"ttft_s": 0.25939199997810647,
|
||||
"total_s": 5.077765540976543,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 194.8949698826367,
|
||||
"decode_tps": 19.20226982827757,
|
||||
"request_tps": 18.709016639970706,
|
||||
"group_elapsed_s": 5.077990833029617,
|
||||
"group_output_tps": 18.708186588694836,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "f8373947-d690-42a4-b613-33f71746b2f9",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:25.927037+00:00",
|
||||
"ttft_s": 0.25913220801157877,
|
||||
"total_s": 5.760092166019604,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 423.79232394227944,
|
||||
"decode_tps": 22.737809958094928,
|
||||
"request_tps": 22.22186664913243,
|
||||
"group_elapsed_s": 5.761121416988317,
|
||||
"group_output_tps": 22.217896609947385,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "9e12f0f4-50d6-444c-8752-4565aa55084b",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:31.688098+00:00",
|
||||
"ttft_s": 0.6637360000167973,
|
||||
"total_s": 5.271547083975747,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 115.32507388679936,
|
||||
"decode_tps": 26.793290081008884,
|
||||
"request_tps": 24.281296924974765,
|
||||
"group_elapsed_s": 5.271936749981251,
|
||||
"group_output_tps": 24.27950221528269,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "583bec1f-0983-4208-8635-439a9a0c5424",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:36.960047+00:00",
|
||||
"ttft_s": 0.15107908402569592,
|
||||
"total_s": 5.119054667011369,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 4102564.1025641025,
|
||||
"decode_tps": 18.66803886577614,
|
||||
"request_tps": 18.558113983858536,
|
||||
"group_elapsed_s": 5.11973733396735,
|
||||
"group_output_tps": 18.555639440663118,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "641937dd-533c-493e-b7b3-3fa2cc6e8879",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:42.079662+00:00",
|
||||
"ttft_s": 0.1495445409673266,
|
||||
"total_s": 5.59909695800161,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 3794229.2420365307,
|
||||
"decode_tps": 22.9734392268289,
|
||||
"request_tps": 22.86082933732315,
|
||||
"group_elapsed_s": 5.599817292008083,
|
||||
"group_output_tps": 22.85788862838049,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "3dbdfe4c-7d43-4575-a1e6-6b74bd5a10a7",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:47.680109+00:00",
|
||||
"ttft_s": 0.16311579098692164,
|
||||
"total_s": 4.8760897910106,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 1791151.7105498835,
|
||||
"decode_tps": 19.64848684540538,
|
||||
"request_tps": 19.482824162741817,
|
||||
"group_elapsed_s": 22.031325709016528,
|
||||
"group_output_tps": 20.24390206429885,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 1,
|
||||
"request_id": "1ea04fa9-7f60-4936-ba53-6829df8e5714",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:47.680573+00:00",
|
||||
"ttft_s": 10.314829125010874,
|
||||
"total_s": 16.516400250024162,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 6370370.37037037,
|
||||
"decode_tps": 20.216323480613685,
|
||||
"request_tps": 7.749872736331438,
|
||||
"group_elapsed_s": 22.031325709016528,
|
||||
"group_output_tps": 20.24390206429885,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 2,
|
||||
"request_id": "046681e1-e7be-4c58-8284-88f821e4a8a0",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:47.680452+00:00",
|
||||
"ttft_s": 5.110771542007569,
|
||||
"total_s": 10.15410141699249,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 514.3377603686088,
|
||||
"decode_tps": 24.759396813702583,
|
||||
"request_tps": 12.605743703307615,
|
||||
"group_elapsed_s": 22.031325709016528,
|
||||
"group_output_tps": 20.24390206429885,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 3,
|
||||
"request_id": "f496e50f-a2db-4fad-a2e1-2a7965fd862d",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:19:47.680317+00:00",
|
||||
"ttft_s": 16.645131999976,
|
||||
"total_s": 22.03015966597013,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 6666666.666666666,
|
||||
"decode_tps": 17.25091779989875,
|
||||
"request_tps": 4.312270153300159,
|
||||
"group_elapsed_s": 22.031325709016528,
|
||||
"group_output_tps": 20.24390206429885,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "cb3d0e9e-0a6f-4f36-aec9-4b20cbc8f87d",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:09.710819+00:00",
|
||||
"ttft_s": 17.595250790996943,
|
||||
"total_s": 23.510470708017237,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 19843101.06137517,
|
||||
"decode_tps": 21.163606353137514,
|
||||
"request_tps": 5.444382700357892,
|
||||
"group_elapsed_s": 23.51121658302145,
|
||||
"group_output_tps": 20.37325454038428,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 1,
|
||||
"request_id": "fa3bb29e-7370-4255-877e-376076d7aa76",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:09.711021+00:00",
|
||||
"ttft_s": 5.7327396660111845,
|
||||
"total_s": 11.353798499971163,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 9000000.0,
|
||||
"decode_tps": 22.18879858004337,
|
||||
"request_tps": 11.273760054868431,
|
||||
"group_elapsed_s": 23.51121658302145,
|
||||
"group_output_tps": 20.37325454038428,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 2,
|
||||
"request_id": "93ec5b28-1a29-426a-96ff-b3b525fb3c71",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:09.710927+00:00",
|
||||
"ttft_s": 0.1655573329771869,
|
||||
"total_s": 5.57563720800681,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 1563477.1732332706,
|
||||
"decode_tps": 17.170644798585553,
|
||||
"request_tps": 17.038411298277563,
|
||||
"group_elapsed_s": 23.51121658302145,
|
||||
"group_output_tps": 20.37325454038428,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 3,
|
||||
"request_id": "dcac6e9a-3580-4bb1-8787-9cef1c64bfd5",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:09.711149+00:00",
|
||||
"ttft_s": 11.527663582994137,
|
||||
"total_s": 17.459117082995363,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 6331909.880724489,
|
||||
"decode_tps": 21.03978753266432,
|
||||
"request_tps": 7.331413117371669,
|
||||
"group_elapsed_s": 23.51121658302145,
|
||||
"group_output_tps": 20.37325454038428,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "d42caf5b-fb6a-4e96-8e42-fd0b8fc1945b",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:33.222727+00:00",
|
||||
"ttft_s": 6.285906166012865,
|
||||
"total_s": 10.864910541044082,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 8421052.631578946,
|
||||
"decode_tps": 20.156958877874334,
|
||||
"request_tps": 8.743744335594945,
|
||||
"group_elapsed_s": 21.625605207984336,
|
||||
"group_output_tps": 20.623700271534293,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 1,
|
||||
"request_id": "87483860-d4c6-4f13-928c-48de78b6ef70",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:33.222336+00:00",
|
||||
"ttft_s": 0.17068937502335757,
|
||||
"total_s": 6.147177167003974,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 4669345.205776958,
|
||||
"decode_tps": 20.965937740191077,
|
||||
"request_tps": 20.822565630133763,
|
||||
"group_elapsed_s": 21.625605207984336,
|
||||
"group_output_tps": 20.623700271534293,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 2,
|
||||
"request_id": "ee57b9cf-06bc-468b-bd1e-f936abf292df",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:33.222603+00:00",
|
||||
"ttft_s": 16.19913299998734,
|
||||
"total_s": 21.62435016600648,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 11675675.675675677,
|
||||
"decode_tps": 22.963769927247082,
|
||||
"request_tps": 5.919253018812849,
|
||||
"group_elapsed_s": 21.625605207984336,
|
||||
"group_output_tps": 20.623700271534293,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 3,
|
||||
"request_id": "13164aa4-836c-4761-8f99-95bfe18d33a1",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:33.222066+00:00",
|
||||
"ttft_s": 11.00553745898651,
|
||||
"total_s": 16.043328458967153,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 10214504.596527068,
|
||||
"decode_tps": 18.355407643172423,
|
||||
"request_tps": 5.9214645042626,
|
||||
"group_elapsed_s": 21.625605207984336,
|
||||
"group_output_tps": 20.623700271534293,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "51389c06-2a1c-4dcb-a847-5f0c914e298c",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:54.847154+00:00",
|
||||
"ttft_s": 0.16574266698444262,
|
||||
"total_s": 6.310333041998092,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 5402688.779997488,
|
||||
"decode_tps": 20.423563700405246,
|
||||
"request_tps": 20.284190889466956,
|
||||
"group_elapsed_s": 23.574590582982637,
|
||||
"group_output_tps": 20.318486478648204,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 1,
|
||||
"request_id": "1952ea53-9c68-4536-8e9d-089790a8bdee",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:54.847267+00:00",
|
||||
"ttft_s": 18.0774574590032,
|
||||
"total_s": 23.57407404197147,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 6513086.47931492,
|
||||
"decode_tps": 22.77481444475703,
|
||||
"request_tps": 5.4296936444717945,
|
||||
"group_elapsed_s": 23.574590582982637,
|
||||
"group_output_tps": 20.318486478648204,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 2,
|
||||
"request_id": "d71abf03-e17c-42b0-b6bb-c57bf6961bc2",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:54.847373+00:00",
|
||||
"ttft_s": 12.635340875014663,
|
||||
"total_s": 17.94654095900478,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 9229349.330872172,
|
||||
"decode_tps": 17.481471270830138,
|
||||
"request_tps": 5.293499188339869,
|
||||
"group_elapsed_s": 23.574590582982637,
|
||||
"group_output_tps": 20.318486478648204,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 3,
|
||||
"request_id": "4e10d58d-5d6d-46e7-8254-46dd35cfeb9f",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:20:54.847461+00:00",
|
||||
"ttft_s": 6.461538125004154,
|
||||
"total_s": 12.505505541979801,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 3739130.434782609,
|
||||
"decode_tps": 20.730070992395465,
|
||||
"request_tps": 10.235491845596812,
|
||||
"group_elapsed_s": 23.574590582982637,
|
||||
"group_output_tps": 20.318486478648204,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "63b32437-7995-44f4-b5ca-f0f52da2bda7",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:21:18.421714+00:00",
|
||||
"ttft_s": 17.908610125014093,
|
||||
"total_s": 23.736398082983214,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 15071169.411108011,
|
||||
"decode_tps": 21.428265908373906,
|
||||
"request_tps": 5.392562070812423,
|
||||
"group_elapsed_s": 23.736987709009554,
|
||||
"group_output_tps": 20.179477104341757,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 1,
|
||||
"request_id": "3b8fa85d-5574-4ac2-b33c-7208ef99a34f",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:21:18.421631+00:00",
|
||||
"ttft_s": 6.036650207999628,
|
||||
"total_s": 11.081229583011009,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 4571428.571428572,
|
||||
"decode_tps": 18.37088402458498,
|
||||
"request_tps": 8.573055840810985,
|
||||
"group_elapsed_s": 23.736987709009554,
|
||||
"group_output_tps": 20.179477104341757,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 2,
|
||||
"request_id": "76178335-d531-49f7-83d5-84a414d73ce5",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:21:18.421520+00:00",
|
||||
"ttft_s": 11.268355667009018,
|
||||
"total_s": 17.757357084017713,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 7533286.615276804,
|
||||
"decode_tps": 19.182821184166418,
|
||||
"request_tps": 7.208279891786645,
|
||||
"group_elapsed_s": 23.736987709009554,
|
||||
"group_output_tps": 20.179477104341757,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 3,
|
||||
"request_id": "728d2a73-194b-41bb-9dda-216960415fcf",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:21:18.421818+00:00",
|
||||
"ttft_s": 0.17636983300326392,
|
||||
"total_s": 5.888466249976773,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 7200000.0,
|
||||
"decode_tps": 21.89716979543998,
|
||||
"request_tps": 21.737409125934093,
|
||||
"group_elapsed_s": 23.736987709009554,
|
||||
"group_output_tps": 20.179477104341757,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "dfcbb66f-3170-41e1-a4e1-a9b7449517ce",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:21:42.158434+00:00",
|
||||
"ttft_s": 6.034018917009234,
|
||||
"total_s": 11.539304499980062,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 3200000.0,
|
||||
"decode_tps": 16.88203353475361,
|
||||
"request_tps": 8.232731877399036,
|
||||
"group_elapsed_s": 23.861715458042454,
|
||||
"group_output_tps": 18.69102834556173,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 1,
|
||||
"request_id": "04f9942b-bc73-4665-9830-40b7a50beb96",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:21:42.158640+00:00",
|
||||
"ttft_s": 11.68165541702183,
|
||||
"total_s": 18.32316145801451,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 9921550.530687585,
|
||||
"decode_tps": 18.896968681699633,
|
||||
"request_tps": 6.985694051394885,
|
||||
"group_elapsed_s": 23.861715458042454,
|
||||
"group_output_tps": 18.69102834556173,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 2,
|
||||
"request_id": "e2e252a5-26bf-4277-a744-cf7456cdfac7",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:21:42.158549+00:00",
|
||||
"ttft_s": 0.17531787499319762,
|
||||
"total_s": 5.8762462079757825,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 5355548.943766736,
|
||||
"decode_tps": 21.95473700787165,
|
||||
"request_tps": 21.782613503543573,
|
||||
"group_elapsed_s": 23.861715458042454,
|
||||
"group_output_tps": 18.69102834556173,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 3,
|
||||
"request_id": "61a1f98f-fb9a-49a8-8f00-04bb52b494cc",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:21:42.158328+00:00",
|
||||
"ttft_s": 18.46465341700241,
|
||||
"total_s": 23.86128708301112,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 5782017.924255566,
|
||||
"decode_tps": 17.187946685051212,
|
||||
"request_tps": 3.981344328556299,
|
||||
"group_elapsed_s": 23.861715458042454,
|
||||
"group_output_tps": 18.69102834556173,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "ae555d62-2572-4a62-8cd6-7ae714aace26",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:22:06.019994+00:00",
|
||||
"ttft_s": 20.83534020796651,
|
||||
"total_s": 28.275580540997908,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 7937973.047812442,
|
||||
"decode_tps": 16.887931275751107,
|
||||
"request_tps": 4.526874340012493,
|
||||
"group_elapsed_s": 28.276262458995916,
|
||||
"group_output_tps": 16.940004029691313,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 1,
|
||||
"request_id": "c0147505-dd4a-4ad8-bb9d-0955114a8ee0",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:22:06.020061+00:00",
|
||||
"ttft_s": 13.962619374971837,
|
||||
"total_s": 20.66803166596219,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 10125632.852053255,
|
||||
"decode_tps": 18.57306514141657,
|
||||
"request_tps": 6.193139340443381,
|
||||
"group_elapsed_s": 28.276262458995916,
|
||||
"group_output_tps": 16.940004029691313,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 2,
|
||||
"request_id": "3a3d625f-5d64-42d0-9145-3056ea9864db",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:22:06.019916+00:00",
|
||||
"ttft_s": 7.783273542008828,
|
||||
"total_s": 13.761600458994508,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 95,
|
||||
"prompt_tps": 1927710.843373494,
|
||||
"decode_tps": 15.539155324201145,
|
||||
"request_tps": 6.903266831722942,
|
||||
"group_elapsed_s": 28.276262458995916,
|
||||
"group_output_tps": 16.940004029691313,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T121855Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 3,
|
||||
"request_id": "8ea78898-3c59-49f2-9734-f01bb668d810",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T12:22:06.019812+00:00",
|
||||
"ttft_s": 0.17432458401890472,
|
||||
"total_s": 7.616022333968431,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 2866666.6666666665,
|
||||
"decode_tps": 16.90294641795698,
|
||||
"request_tps": 16.806673403399,
|
||||
"group_elapsed_s": 28.276262458995916,
|
||||
"group_output_tps": 16.940004029691313,
|
||||
"error": null
|
||||
}
|
||||
]
|
||||
54
benchmarks/inference/results/20260831T121855Z/summary.json
Normal file
54
benchmarks/inference/results/20260831T121855Z/summary.json
Normal file
@@ -0,0 +1,54 @@
|
||||
[
|
||||
{
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"concurrency": 1,
|
||||
"requests": 5,
|
||||
"successes": 5,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 0.296576766599901,
|
||||
"ttft_s_p50": 0.25913220801157877,
|
||||
"ttft_s_p95": 0.5828672000090591,
|
||||
"total_s_mean": 5.365511283196975,
|
||||
"total_s_p50": 5.271547083975747,
|
||||
"total_s_p95": 5.7278931244160045,
|
||||
"prompt_tps_mean": 1579505.471393669,
|
||||
"prompt_tps_p50": 423.79232394227944,
|
||||
"prompt_tps_p95": 4040897.1304585882,
|
||||
"decode_tps_mean": 22.074969591997284,
|
||||
"decode_tps_p50": 22.737809958094928,
|
||||
"decode_tps_p95": 26.029319910172887,
|
||||
"request_tps_mean": 21.326224707051917,
|
||||
"request_tps_p50": 22.22186664913243,
|
||||
"request_tps_p95": 23.99720340744444,
|
||||
"aggregate_output_tps_mean": 21.3238226965937,
|
||||
"aggregate_output_tps_p50": 22.217896609947385,
|
||||
"aggregate_output_tps_p95": 23.99517949790225
|
||||
},
|
||||
{
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mxfp8",
|
||||
"concurrency": 4,
|
||||
"requests": 20,
|
||||
"successes": 20,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 9.275126714701765,
|
||||
"ttft_s_p50": 9.394405500497669,
|
||||
"ttft_s_p95": 18.583187756550615,
|
||||
"total_s_mean": 15.170045258343453,
|
||||
"total_s_p50": 14.90246445898083,
|
||||
"total_s_p95": 24.08200175591046,
|
||||
"prompt_tps_mean": 7067890.927047749,
|
||||
"prompt_tps_p50": 6856543.23965746,
|
||||
"prompt_tps_p95": 11845450.362447295,
|
||||
"decode_tps_mean": 19.377795978907,
|
||||
"decode_tps_p50": 19.039894932933024,
|
||||
"decode_tps_p95": 22.784262218881533,
|
||||
"request_tps_mean": 10.048677383124767,
|
||||
"request_tps_p50": 7.0969869715907645,
|
||||
"request_tps_p95": 21.739669344814565,
|
||||
"aggregate_output_tps_mean": 19.35053924595546,
|
||||
"aggregate_output_tps_p50": 20.179477104341757,
|
||||
"aggregate_output_tps_p95": 20.562657512957074
|
||||
}
|
||||
]
|
||||
136
benchmarks/inference/results/20260831T132015Z/metadata.json
Normal file
136
benchmarks/inference/results/20260831T132015Z/metadata.json
Normal file
@@ -0,0 +1,136 @@
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"created_at": "2026-08-31T13:20:15.702115+00:00",
|
||||
"host": {
|
||||
"platform": "macOS-15.6-arm64-arm-64bit",
|
||||
"machine": "arm64",
|
||||
"python": "3.12.8"
|
||||
},
|
||||
"arguments": {
|
||||
"output_dir": "/Users/christianmeyer/Documents/git/lai_automatisierung/benchmarks/inference/results",
|
||||
"runtime": "vllm",
|
||||
"ollama_url": "http://127.0.0.1:11434",
|
||||
"ollama_model": "qwen3.8:27b-mlx",
|
||||
"vllm_url": "http://127.0.0.1:8001",
|
||||
"vllm_model": "qwen3.8-27b-mxfp8",
|
||||
"warmups": 2,
|
||||
"rounds": 5,
|
||||
"concurrency": [
|
||||
1,
|
||||
4
|
||||
],
|
||||
"max_tokens": 128,
|
||||
"seed": 42,
|
||||
"timeout": 600
|
||||
},
|
||||
"runtimes": [
|
||||
{
|
||||
"name": "vllm-metal",
|
||||
"kind": "openai",
|
||||
"base_url": "http://127.0.0.1:8001",
|
||||
"model": "qwen3.8-27b-mxfp8"
|
||||
}
|
||||
],
|
||||
"versions": {
|
||||
"ollama": "ollama version is 0.32.14",
|
||||
"vllm": "INFO 08-31 15:20:16 [__init__.py:52] Available plugins for group vllm.platform_plugins:\nINFO 08-31 15:20:16 [__init__.py:54] - metal -> vllm_metal:register\nINFO 08-31 15:20:16 [__init__.py:57] All plugins in this group will be loaded. Set `VLLM_PLUGINS` to control which plugins to load.\nINFO 08-31 15:20:18 [__init__.py:254] Platform plugin metal is activated\nINFO 08-31 15:20:19 [importing.py:88] Triton not installed or not compatible; certain GPU-related functions will not be available.\n0.28.0+cpu"
|
||||
},
|
||||
"model_metadata": {
|
||||
"vllm-metal": {
|
||||
"object": "list",
|
||||
"data": [
|
||||
{
|
||||
"id": "qwen3.8-27b-mxfp8",
|
||||
"object": "model",
|
||||
"created": 1788182421,
|
||||
"owned_by": "vllm",
|
||||
"root": "mlx-community/Qwen3.8-27B-mxfp8",
|
||||
"parent": null,
|
||||
"max_model_len": 8192,
|
||||
"permission": [
|
||||
{
|
||||
"id": "modelperm-a3c90f9b6d588379",
|
||||
"object": "model_permission",
|
||||
"created": 1788182421,
|
||||
"allow_create_engine": false,
|
||||
"allow_sampling": true,
|
||||
"allow_logprobs": true,
|
||||
"allow_search_indices": false,
|
||||
"allow_view": true,
|
||||
"allow_fine_tuning": false,
|
||||
"organization": "*",
|
||||
"group": null,
|
||||
"is_blocking": false
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"prompts": {
|
||||
"short": "In exactly four concise bullet points, explain why database transactions are useful. Do not use a heading.",
|
||||
"medium": "You are reviewing a Laravel service that transfers money between two accounts. Explain the failure modes involving concurrency, partial writes, retries, and audit logs. Then provide a robust implementation plan. Keep the response technical and concise.",
|
||||
"code": "Write a Python 3.12 function named merge_intervals that accepts a list of integer pairs, validates each pair, merges overlapping or adjacent intervals, and returns sorted tuples. Include type hints, a short docstring, and five assert-based examples. Output only code."
|
||||
},
|
||||
"measurement_notes": {
|
||||
"ttft": "Client wall time from request start until first non-empty generated text chunk.",
|
||||
"total": "Client wall time from request start until stream completion.",
|
||||
"decode_tps": "Ollama server eval metric; otherwise output tokens / (total - TTFT).",
|
||||
"aggregate_output_tps": "Sum of successful output tokens / concurrent group wall time."
|
||||
},
|
||||
"completed_at": "2026-08-31T13:22:48.218681+00:00",
|
||||
"summary": [
|
||||
{
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"concurrency": 1,
|
||||
"requests": 5,
|
||||
"successes": 5,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 0.37155269999057056,
|
||||
"ttft_s_p50": 0.4171057919738814,
|
||||
"ttft_s_p95": 0.4531440335791558,
|
||||
"total_s_mean": 7.930883799993898,
|
||||
"total_s_p50": 8.838838333962485,
|
||||
"total_s_p95": 8.998963149765041,
|
||||
"prompt_tps_mean": null,
|
||||
"prompt_tps_p50": null,
|
||||
"prompt_tps_p95": null,
|
||||
"decode_tps_mean": 15.079897408512505,
|
||||
"decode_tps_p50": 15.126147490283795,
|
||||
"decode_tps_p95": 15.196162811046243,
|
||||
"request_tps_mean": 14.380896425252896,
|
||||
"request_tps_p50": 14.386982882152838,
|
||||
"request_tps_p95": 14.53502856074605,
|
||||
"aggregate_output_tps_mean": 14.380548747737752,
|
||||
"aggregate_output_tps_p50": 14.386712701914696,
|
||||
"aggregate_output_tps_p95": 14.534638049200744
|
||||
},
|
||||
{
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"concurrency": 4,
|
||||
"requests": 20,
|
||||
"successes": 20,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 1.255672066603438,
|
||||
"ttft_s_p50": 1.3144360205042176,
|
||||
"ttft_s_p95": 1.419064954231726,
|
||||
"total_s_mean": 12.251293779097614,
|
||||
"total_s_p50": 12.702340687508695,
|
||||
"total_s_p95": 13.641910566360457,
|
||||
"prompt_tps_mean": null,
|
||||
"prompt_tps_p50": null,
|
||||
"prompt_tps_p95": null,
|
||||
"decode_tps_mean": 10.500220268362742,
|
||||
"decode_tps_p50": 10.485677148644122,
|
||||
"decode_tps_p95": 11.071162546140778,
|
||||
"request_tps_mean": 9.417789343799708,
|
||||
"request_tps_p50": 9.430282582501674,
|
||||
"request_tps_p95": 10.077752113288362,
|
||||
"aggregate_output_tps_mean": 35.09087333775396,
|
||||
"aggregate_output_tps_p50": 34.96408475660248,
|
||||
"aggregate_output_tps_p95": 35.52678209465127
|
||||
}
|
||||
]
|
||||
}
|
||||
36
benchmarks/inference/results/20260831T132015Z/raw.csv
Normal file
36
benchmarks/inference/results/20260831T132015Z/raw.csv
Normal file
@@ -0,0 +1,36 @@
|
||||
run_id,runtime,model,phase,concurrency,round,slot,request_id,prompt_name,prompt_chars,max_tokens,started_at,ttft_s,total_s,prompt_tokens,output_tokens,prompt_tps,decode_tps,request_tps,group_elapsed_s,group_output_tps,error
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,1,0,0,4c059f2d-caa2-44ae-ab1d-539d608c86d8,short,106,128,2026-08-31T13:20:21.117908+00:00,0.3135264579905197,6.390581874991767,20,93,,15.303464197450301,14.552665440988472,6.39150691695977,14.550559235604652,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,1,1,0,1bf28507-8f2f-4127-ba2f-2f5637e722bf,medium,252,128,2026-08-31T13:20:27.508796+00:00,0.3822946660220623,8.7317384579801,43,128,,15.330362499509992,14.659165596401756,8.731932666967623,14.658839558419446,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,1,0,0,81b82bc5-db99-4c10-9ec1-1f684485db59,short,106,128,2026-08-31T13:20:36.240817+00:00,0.2682818329776637,6.39245533302892,20,93,,15.185722612075187,14.548400443172758,6.392639332974795,14.547981695179217,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,1,1,0,1de32693-20bd-450c-8341-17773d6c57b2,medium,252,128,2026-08-31T13:20:42.633525+00:00,0.4171057919738814,8.838838333962485,43,128,,15.198772860789006,14.481541031039212,8.839007750037126,14.481263465286855,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,1,2,0,e821a6d4-8b00-477b-a66f-3579d33c583b,code,267,128,2026-08-31T13:20:51.472629+00:00,0.4347635000012815,8.896931416995358,54,128,,15.126147490283795,14.386982882152838,8.897098499990534,14.386712701914696,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,1,3,0,6415410d-9d1c-4521-b2e2-04c40ce2fd72,short,106,128,2026-08-31T13:21:00.369851+00:00,0.2798732080264017,6.501722833025269,20,93,,14.947323642528074,14.303901041060966,6.501933082996402,14.303438502498576,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,1,4,0,44eda129-4834-4a55-a14a-33a4a510922d,medium,252,128,2026-08-31T13:21:06.871859+00:00,0.4577391669736244,9.024471082957461,43,128,,14.94152043688646,14.183656728838715,9.024667916994076,14.183347373809413,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,4,0,0,a696baea-c3a4-422a-9d29-c4fff0e6d70e,short,106,128,2026-08-31T13:21:15.897040+00:00,1.1126187500194646,9.980102250003256,20,93,,10.48775562989996,9.318541801510065,12.400747582956683,35.64301241059653,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,4,0,1,2a75391e-8c1c-4244-8cea-f8f97ce3c40d,medium,252,128,2026-08-31T13:21:15.896746+00:00,1.1128792079980485,12.400287791970186,43,128,,11.340069693388886,10.322341073639151,12.400747582956683,35.64301241059653,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,4,0,2,21360267-b5fe-4bd2-8b87-d5bbdf4a9c49,code,267,128,2026-08-31T13:21:15.896944+00:00,1.1127408749889582,12.400139749981463,54,128,,11.340079447673899,10.322464309339042,12.400747582956683,35.64301241059653,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,4,0,3,106f9109-b093-475b-85c2-dc0847a3f3e3,short,106,128,2026-08-31T13:21:15.896863+00:00,1.0121074999915436,9.893255082948599,20,93,,10.471619701317342,9.400343892910335,12.400747582956683,35.64301241059653,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,4,1,0,fd6e44d9-a975-4760-853a-c85d6547b8f2,medium,252,128,2026-08-31T13:21:28.297798+00:00,1.4682920000050217,13.96469266602071,43,128,,10.242949423676817,9.165973291446168,13.965293916000519,36.232678169433896,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,4,1,1,a5541448-562a-4c84-aeff-3e2e5b8aba34,code,267,128,2026-08-31T13:21:28.297877+00:00,1.4681764579727314,13.9645455830032,54,128,,10.242975277003744,9.166069833005798,13.965293916000519,36.232678169433896,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,4,1,2,bb897f87-b4a0-4483-9946-4f6483212386,short,106,128,2026-08-31T13:21:28.297713+00:00,1.3568928329623304,13.431885249970946,20,122,,10.103526013660515,9.082864968658356,13.965293916000519,36.232678169433896,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,warmup,4,1,3,576c3ce6-5566-4a17-b311-3c2f8f3a5a17,medium,252,128,2026-08-31T13:21:28.297622+00:00,1.4684889169875532,13.964902083971538,43,128,,10.242939176993687,9.16583583832745,13.965293916000519,36.232678169433896,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,0,0,75886439-869f-49d6-881d-4bc7cf650b04,short,106,128,2026-08-31T13:21:42.263079+00:00,1.1142227500095032,10.27476887498051,20,93,,10.152233145411333,9.051298489687577,12.701848333003,34.79808516147676,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,0,1,2ecba00e-62dd-4ea7-a1e1-c7b0c12aae0e,medium,252,128,2026-08-31T13:21:42.263219+00:00,1.1140572919975966,12.70125433296198,43,128,,11.046675011003936,10.077744815157159,12.701848333003,34.79808516147676,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,0,2,c1df76bd-2c64-4e34-a5be-10d74b64ce17,code,267,128,2026-08-31T13:21:42.263452+00:00,1.1138802919886075,12.701070374983829,54,128,,11.046681644400257,10.077890777781237,12.701848333003,34.79808516147676,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,0,3,1bf72731-e2e3-4f8d-bf42-627b9fce292a,short,106,128,2026-08-31T13:21:42.263323+00:00,1.0123424580087885,10.185485332971439,20,93,,10.138291888359873,9.130640019572722,12.701848333003,34.79808516147676,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,1,0,a04682c5-d585-4466-8fad-17ed2b9ba80b,medium,252,128,2026-08-31T13:21:54.962444+00:00,1.4147373330197297,13.505381957977079,43,128,,10.586697729563905,9.477703066694506,13.505815375014208,35.31811939932565,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,1,1,bf6552cc-7c18-4617-8260-b6a63ff65b3c,code,267,128,2026-08-31T13:21:54.962650+00:00,1.4145112080150284,13.505133582977578,54,128,,10.586717211933143,9.477877372596776,13.505815375014208,35.31811939932565,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,1,2,36abe2cb-3ddf-4311-853a-4151aef2b328,short,106,128,2026-08-31T13:21:54.962724+00:00,1.4144840000080876,10.538147750019561,20,93,,10.193273508121454,8.825080289828673,13.505815375014208,35.31811939932565,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,1,3,110efa2a-5fb4-48e9-835b-3092cd0df4fb,medium,252,128,2026-08-31T13:21:54.962552+00:00,1.3138721249997616,13.505327666993253,43,128,,10.49915652475652,9.477741166756687,13.505815375014208,35.31811939932565,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,2,0,4d78c4f5-e05f-4ffe-afb6-748b8db712f6,code,267,128,2026-08-31T13:22:08.467061+00:00,1.2189033330068924,13.40631824999582,54,128,,10.502637423262865,9.547736941127733,13.406804582977202,35.57894776848267,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,2,1,9beb5379-ecf9-45d3-8725-13dd100b245d,short,106,128,2026-08-31T13:22:08.467363+00:00,1.3166250829817727,10.428931292030029,20,93,,10.205978362278222,8.917500498931489,13.406804582977202,35.57894776848267,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,2,2,e863870c-69a1-44bd-9d57-7d28f9a30c17,medium,252,128,2026-08-31T13:22:08.467157+00:00,1.3168415420223027,13.406341000052635,43,128,,10.58770054495327,9.547720738976986,13.406804582977202,35.57894776848267,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,2,3,21ffaa25-b50a-4b5f-b562-4a7810b56506,code,267,128,2026-08-31T13:22:08.467234+00:00,1.316743416013196,13.406194041017443,54,128,,10.587743311946818,9.547825401331103,13.406804582977202,35.57894776848267,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,3,0,00728b55-60a4-46d3-8000-146e38d0b3a6,short,106,128,2026-08-31T13:22:21.873446+00:00,1.0375588749884628,10.190524249977898,20,93,,10.160641517788692,9.126125184403708,12.702927250007633,34.795129602882234,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,3,1,531d5ceb-d88b-49ab-ad8d-7bea678c3bb8,medium,252,128,2026-08-31T13:22:21.873549+00:00,1.140847125032451,12.702382000046782,43,128,,11.07119438584415,10.076850152949941,12.702927250007633,34.795129602882234,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,3,2,a4b2f7bb-ab5c-405b-9514-d64bf34153ea,code,267,128,2026-08-31T13:22:21.873705+00:00,1.1407294999808073,12.702299374970607,54,128,,11.071160870366917,10.076915700177802,12.702927250007633,34.795129602882234,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,3,3,1b77ace8-b3ef-47f2-a2cd-06b6f9400a6e,short,106,128,2026-08-31T13:22:21.873633+00:00,1.1407265829620883,10.277835665969178,20,93,,10.178274020276117,9.048597683647658,12.702927250007633,34.795129602882234,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,4,0,1143b997-b26b-4ca6-a4ad-dd1014020849,medium,252,128,2026-08-31T13:22:34.576247+00:00,1.3149999160086736,13.642209500016179,43,128,,10.383534012925246,9.382644358294614,13.642570749972947,34.96408475660248,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,4,1,907e97b8-fec4-47ff-b971-45716a15b6fb,code,267,128,2026-08-31T13:22:34.576465+00:00,1.419054625032004,13.641894833010156,54,128,,10.472197772531725,9.38286078047386,13.642570749972947,34.96408475660248,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,4,2,d5875acf-e267-4393-84c1-a01dac48c4a5,short,106,128,2026-08-31T13:22:34.576349+00:00,1.4192612090264447,10.662482584011741,20,93,,10.061427312742246,8.722171339295066,13.642570749972947,34.96408475660248,
|
||||
20260831T132015Z,vllm-metal,qwen3.8-27b-mxfp8,measured,4,4,3,d2828df9-67d3-44b0-9809-bdb8c75f5282,medium,252,128,2026-08-31T13:22:34.576542+00:00,1.4190426669665612,13.641892916988581,43,128,,10.47218916878814,9.382862098308841,13.642570749972947,34.96408475660248,
|
||||
|
842
benchmarks/inference/results/20260831T132015Z/raw.json
Normal file
842
benchmarks/inference/results/20260831T132015Z/raw.json
Normal file
@@ -0,0 +1,842 @@
|
||||
[
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "4c059f2d-caa2-44ae-ab1d-539d608c86d8",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:20:21.117908+00:00",
|
||||
"ttft_s": 0.3135264579905197,
|
||||
"total_s": 6.390581874991767,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.303464197450301,
|
||||
"request_tps": 14.552665440988472,
|
||||
"group_elapsed_s": 6.39150691695977,
|
||||
"group_output_tps": 14.550559235604652,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "1bf28507-8f2f-4127-ba2f-2f5637e722bf",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:20:27.508796+00:00",
|
||||
"ttft_s": 0.3822946660220623,
|
||||
"total_s": 8.7317384579801,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.330362499509992,
|
||||
"request_tps": 14.659165596401756,
|
||||
"group_elapsed_s": 8.731932666967623,
|
||||
"group_output_tps": 14.658839558419446,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "81b82bc5-db99-4c10-9ec1-1f684485db59",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:20:36.240817+00:00",
|
||||
"ttft_s": 0.2682818329776637,
|
||||
"total_s": 6.39245533302892,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.185722612075187,
|
||||
"request_tps": 14.548400443172758,
|
||||
"group_elapsed_s": 6.392639332974795,
|
||||
"group_output_tps": 14.547981695179217,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "1de32693-20bd-450c-8341-17773d6c57b2",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:20:42.633525+00:00",
|
||||
"ttft_s": 0.4171057919738814,
|
||||
"total_s": 8.838838333962485,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.198772860789006,
|
||||
"request_tps": 14.481541031039212,
|
||||
"group_elapsed_s": 8.839007750037126,
|
||||
"group_output_tps": 14.481263465286855,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "e821a6d4-8b00-477b-a66f-3579d33c583b",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:20:51.472629+00:00",
|
||||
"ttft_s": 0.4347635000012815,
|
||||
"total_s": 8.896931416995358,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 15.126147490283795,
|
||||
"request_tps": 14.386982882152838,
|
||||
"group_elapsed_s": 8.897098499990534,
|
||||
"group_output_tps": 14.386712701914696,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "6415410d-9d1c-4521-b2e2-04c40ce2fd72",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:00.369851+00:00",
|
||||
"ttft_s": 0.2798732080264017,
|
||||
"total_s": 6.501722833025269,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 14.947323642528074,
|
||||
"request_tps": 14.303901041060966,
|
||||
"group_elapsed_s": 6.501933082996402,
|
||||
"group_output_tps": 14.303438502498576,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "44eda129-4834-4a55-a14a-33a4a510922d",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:06.871859+00:00",
|
||||
"ttft_s": 0.4577391669736244,
|
||||
"total_s": 9.024471082957461,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 14.94152043688646,
|
||||
"request_tps": 14.183656728838715,
|
||||
"group_elapsed_s": 9.024667916994076,
|
||||
"group_output_tps": 14.183347373809413,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "a696baea-c3a4-422a-9d29-c4fff0e6d70e",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:15.897040+00:00",
|
||||
"ttft_s": 1.1126187500194646,
|
||||
"total_s": 9.980102250003256,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.48775562989996,
|
||||
"request_tps": 9.318541801510065,
|
||||
"group_elapsed_s": 12.400747582956683,
|
||||
"group_output_tps": 35.64301241059653,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 1,
|
||||
"request_id": "2a75391e-8c1c-4244-8cea-f8f97ce3c40d",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:15.896746+00:00",
|
||||
"ttft_s": 1.1128792079980485,
|
||||
"total_s": 12.400287791970186,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 11.340069693388886,
|
||||
"request_tps": 10.322341073639151,
|
||||
"group_elapsed_s": 12.400747582956683,
|
||||
"group_output_tps": 35.64301241059653,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 2,
|
||||
"request_id": "21360267-b5fe-4bd2-8b87-d5bbdf4a9c49",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:15.896944+00:00",
|
||||
"ttft_s": 1.1127408749889582,
|
||||
"total_s": 12.400139749981463,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 11.340079447673899,
|
||||
"request_tps": 10.322464309339042,
|
||||
"group_elapsed_s": 12.400747582956683,
|
||||
"group_output_tps": 35.64301241059653,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 3,
|
||||
"request_id": "106f9109-b093-475b-85c2-dc0847a3f3e3",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:15.896863+00:00",
|
||||
"ttft_s": 1.0121074999915436,
|
||||
"total_s": 9.893255082948599,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.471619701317342,
|
||||
"request_tps": 9.400343892910335,
|
||||
"group_elapsed_s": 12.400747582956683,
|
||||
"group_output_tps": 35.64301241059653,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "fd6e44d9-a975-4760-853a-c85d6547b8f2",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:28.297798+00:00",
|
||||
"ttft_s": 1.4682920000050217,
|
||||
"total_s": 13.96469266602071,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.242949423676817,
|
||||
"request_tps": 9.165973291446168,
|
||||
"group_elapsed_s": 13.965293916000519,
|
||||
"group_output_tps": 36.232678169433896,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 1,
|
||||
"request_id": "a5541448-562a-4c84-aeff-3e2e5b8aba34",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:28.297877+00:00",
|
||||
"ttft_s": 1.4681764579727314,
|
||||
"total_s": 13.9645455830032,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.242975277003744,
|
||||
"request_tps": 9.166069833005798,
|
||||
"group_elapsed_s": 13.965293916000519,
|
||||
"group_output_tps": 36.232678169433896,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 2,
|
||||
"request_id": "bb897f87-b4a0-4483-9946-4f6483212386",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:28.297713+00:00",
|
||||
"ttft_s": 1.3568928329623304,
|
||||
"total_s": 13.431885249970946,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 122,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.103526013660515,
|
||||
"request_tps": 9.082864968658356,
|
||||
"group_elapsed_s": 13.965293916000519,
|
||||
"group_output_tps": 36.232678169433896,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "warmup",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 3,
|
||||
"request_id": "576c3ce6-5566-4a17-b311-3c2f8f3a5a17",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:28.297622+00:00",
|
||||
"ttft_s": 1.4684889169875532,
|
||||
"total_s": 13.964902083971538,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.242939176993687,
|
||||
"request_tps": 9.16583583832745,
|
||||
"group_elapsed_s": 13.965293916000519,
|
||||
"group_output_tps": 36.232678169433896,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "75886439-869f-49d6-881d-4bc7cf650b04",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:42.263079+00:00",
|
||||
"ttft_s": 1.1142227500095032,
|
||||
"total_s": 10.27476887498051,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.152233145411333,
|
||||
"request_tps": 9.051298489687577,
|
||||
"group_elapsed_s": 12.701848333003,
|
||||
"group_output_tps": 34.79808516147676,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 1,
|
||||
"request_id": "2ecba00e-62dd-4ea7-a1e1-c7b0c12aae0e",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:42.263219+00:00",
|
||||
"ttft_s": 1.1140572919975966,
|
||||
"total_s": 12.70125433296198,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 11.046675011003936,
|
||||
"request_tps": 10.077744815157159,
|
||||
"group_elapsed_s": 12.701848333003,
|
||||
"group_output_tps": 34.79808516147676,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 2,
|
||||
"request_id": "c1df76bd-2c64-4e34-a5be-10d74b64ce17",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:42.263452+00:00",
|
||||
"ttft_s": 1.1138802919886075,
|
||||
"total_s": 12.701070374983829,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 11.046681644400257,
|
||||
"request_tps": 10.077890777781237,
|
||||
"group_elapsed_s": 12.701848333003,
|
||||
"group_output_tps": 34.79808516147676,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 0,
|
||||
"slot": 3,
|
||||
"request_id": "1bf72731-e2e3-4f8d-bf42-627b9fce292a",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:42.263323+00:00",
|
||||
"ttft_s": 1.0123424580087885,
|
||||
"total_s": 10.185485332971439,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.138291888359873,
|
||||
"request_tps": 9.130640019572722,
|
||||
"group_elapsed_s": 12.701848333003,
|
||||
"group_output_tps": 34.79808516147676,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "a04682c5-d585-4466-8fad-17ed2b9ba80b",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:54.962444+00:00",
|
||||
"ttft_s": 1.4147373330197297,
|
||||
"total_s": 13.505381957977079,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.586697729563905,
|
||||
"request_tps": 9.477703066694506,
|
||||
"group_elapsed_s": 13.505815375014208,
|
||||
"group_output_tps": 35.31811939932565,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 1,
|
||||
"request_id": "bf6552cc-7c18-4617-8260-b6a63ff65b3c",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:54.962650+00:00",
|
||||
"ttft_s": 1.4145112080150284,
|
||||
"total_s": 13.505133582977578,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.586717211933143,
|
||||
"request_tps": 9.477877372596776,
|
||||
"group_elapsed_s": 13.505815375014208,
|
||||
"group_output_tps": 35.31811939932565,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 2,
|
||||
"request_id": "36abe2cb-3ddf-4311-853a-4151aef2b328",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:54.962724+00:00",
|
||||
"ttft_s": 1.4144840000080876,
|
||||
"total_s": 10.538147750019561,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.193273508121454,
|
||||
"request_tps": 8.825080289828673,
|
||||
"group_elapsed_s": 13.505815375014208,
|
||||
"group_output_tps": 35.31811939932565,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 1,
|
||||
"slot": 3,
|
||||
"request_id": "110efa2a-5fb4-48e9-835b-3092cd0df4fb",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:21:54.962552+00:00",
|
||||
"ttft_s": 1.3138721249997616,
|
||||
"total_s": 13.505327666993253,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.49915652475652,
|
||||
"request_tps": 9.477741166756687,
|
||||
"group_elapsed_s": 13.505815375014208,
|
||||
"group_output_tps": 35.31811939932565,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "4d78c4f5-e05f-4ffe-afb6-748b8db712f6",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:08.467061+00:00",
|
||||
"ttft_s": 1.2189033330068924,
|
||||
"total_s": 13.40631824999582,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.502637423262865,
|
||||
"request_tps": 9.547736941127733,
|
||||
"group_elapsed_s": 13.406804582977202,
|
||||
"group_output_tps": 35.57894776848267,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 1,
|
||||
"request_id": "9beb5379-ecf9-45d3-8725-13dd100b245d",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:08.467363+00:00",
|
||||
"ttft_s": 1.3166250829817727,
|
||||
"total_s": 10.428931292030029,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.205978362278222,
|
||||
"request_tps": 8.917500498931489,
|
||||
"group_elapsed_s": 13.406804582977202,
|
||||
"group_output_tps": 35.57894776848267,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 2,
|
||||
"request_id": "e863870c-69a1-44bd-9d57-7d28f9a30c17",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:08.467157+00:00",
|
||||
"ttft_s": 1.3168415420223027,
|
||||
"total_s": 13.406341000052635,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.58770054495327,
|
||||
"request_tps": 9.547720738976986,
|
||||
"group_elapsed_s": 13.406804582977202,
|
||||
"group_output_tps": 35.57894776848267,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 2,
|
||||
"slot": 3,
|
||||
"request_id": "21ffaa25-b50a-4b5f-b562-4a7810b56506",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:08.467234+00:00",
|
||||
"ttft_s": 1.316743416013196,
|
||||
"total_s": 13.406194041017443,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.587743311946818,
|
||||
"request_tps": 9.547825401331103,
|
||||
"group_elapsed_s": 13.406804582977202,
|
||||
"group_output_tps": 35.57894776848267,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "00728b55-60a4-46d3-8000-146e38d0b3a6",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:21.873446+00:00",
|
||||
"ttft_s": 1.0375588749884628,
|
||||
"total_s": 10.190524249977898,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.160641517788692,
|
||||
"request_tps": 9.126125184403708,
|
||||
"group_elapsed_s": 12.702927250007633,
|
||||
"group_output_tps": 34.795129602882234,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 1,
|
||||
"request_id": "531d5ceb-d88b-49ab-ad8d-7bea678c3bb8",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:21.873549+00:00",
|
||||
"ttft_s": 1.140847125032451,
|
||||
"total_s": 12.702382000046782,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 11.07119438584415,
|
||||
"request_tps": 10.076850152949941,
|
||||
"group_elapsed_s": 12.702927250007633,
|
||||
"group_output_tps": 34.795129602882234,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 2,
|
||||
"request_id": "a4b2f7bb-ab5c-405b-9514-d64bf34153ea",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:21.873705+00:00",
|
||||
"ttft_s": 1.1407294999808073,
|
||||
"total_s": 12.702299374970607,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 11.071160870366917,
|
||||
"request_tps": 10.076915700177802,
|
||||
"group_elapsed_s": 12.702927250007633,
|
||||
"group_output_tps": 34.795129602882234,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 3,
|
||||
"slot": 3,
|
||||
"request_id": "1b77ace8-b3ef-47f2-a2cd-06b6f9400a6e",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:21.873633+00:00",
|
||||
"ttft_s": 1.1407265829620883,
|
||||
"total_s": 10.277835665969178,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.178274020276117,
|
||||
"request_tps": 9.048597683647658,
|
||||
"group_elapsed_s": 12.702927250007633,
|
||||
"group_output_tps": 34.795129602882234,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "1143b997-b26b-4ca6-a4ad-dd1014020849",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:34.576247+00:00",
|
||||
"ttft_s": 1.3149999160086736,
|
||||
"total_s": 13.642209500016179,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.383534012925246,
|
||||
"request_tps": 9.382644358294614,
|
||||
"group_elapsed_s": 13.642570749972947,
|
||||
"group_output_tps": 34.96408475660248,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 1,
|
||||
"request_id": "907e97b8-fec4-47ff-b971-45716a15b6fb",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:34.576465+00:00",
|
||||
"ttft_s": 1.419054625032004,
|
||||
"total_s": 13.641894833010156,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.472197772531725,
|
||||
"request_tps": 9.38286078047386,
|
||||
"group_elapsed_s": 13.642570749972947,
|
||||
"group_output_tps": 34.96408475660248,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 2,
|
||||
"request_id": "d5875acf-e267-4393-84c1-a01dac48c4a5",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:34.576349+00:00",
|
||||
"ttft_s": 1.4192612090264447,
|
||||
"total_s": 10.662482584011741,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 93,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.061427312742246,
|
||||
"request_tps": 8.722171339295066,
|
||||
"group_elapsed_s": 13.642570749972947,
|
||||
"group_output_tps": 34.96408475660248,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T132015Z",
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"phase": "measured",
|
||||
"concurrency": 4,
|
||||
"round": 4,
|
||||
"slot": 3,
|
||||
"request_id": "d2828df9-67d3-44b0-9809-bdb8c75f5282",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:22:34.576542+00:00",
|
||||
"ttft_s": 1.4190426669665612,
|
||||
"total_s": 13.641892916988581,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": null,
|
||||
"decode_tps": 10.47218916878814,
|
||||
"request_tps": 9.382862098308841,
|
||||
"group_elapsed_s": 13.642570749972947,
|
||||
"group_output_tps": 34.96408475660248,
|
||||
"error": null
|
||||
}
|
||||
]
|
||||
54
benchmarks/inference/results/20260831T132015Z/summary.json
Normal file
54
benchmarks/inference/results/20260831T132015Z/summary.json
Normal file
@@ -0,0 +1,54 @@
|
||||
[
|
||||
{
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"concurrency": 1,
|
||||
"requests": 5,
|
||||
"successes": 5,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 0.37155269999057056,
|
||||
"ttft_s_p50": 0.4171057919738814,
|
||||
"ttft_s_p95": 0.4531440335791558,
|
||||
"total_s_mean": 7.930883799993898,
|
||||
"total_s_p50": 8.838838333962485,
|
||||
"total_s_p95": 8.998963149765041,
|
||||
"prompt_tps_mean": null,
|
||||
"prompt_tps_p50": null,
|
||||
"prompt_tps_p95": null,
|
||||
"decode_tps_mean": 15.079897408512505,
|
||||
"decode_tps_p50": 15.126147490283795,
|
||||
"decode_tps_p95": 15.196162811046243,
|
||||
"request_tps_mean": 14.380896425252896,
|
||||
"request_tps_p50": 14.386982882152838,
|
||||
"request_tps_p95": 14.53502856074605,
|
||||
"aggregate_output_tps_mean": 14.380548747737752,
|
||||
"aggregate_output_tps_p50": 14.386712701914696,
|
||||
"aggregate_output_tps_p95": 14.534638049200744
|
||||
},
|
||||
{
|
||||
"runtime": "vllm-metal",
|
||||
"model": "qwen3.8-27b-mxfp8",
|
||||
"concurrency": 4,
|
||||
"requests": 20,
|
||||
"successes": 20,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 1.255672066603438,
|
||||
"ttft_s_p50": 1.3144360205042176,
|
||||
"ttft_s_p95": 1.419064954231726,
|
||||
"total_s_mean": 12.251293779097614,
|
||||
"total_s_p50": 12.702340687508695,
|
||||
"total_s_p95": 13.641910566360457,
|
||||
"prompt_tps_mean": null,
|
||||
"prompt_tps_p50": null,
|
||||
"prompt_tps_p95": null,
|
||||
"decode_tps_mean": 10.500220268362742,
|
||||
"decode_tps_p50": 10.485677148644122,
|
||||
"decode_tps_p95": 11.071162546140778,
|
||||
"request_tps_mean": 9.417789343799708,
|
||||
"request_tps_p50": 9.430282582501674,
|
||||
"request_tps_p95": 10.077752113288362,
|
||||
"aggregate_output_tps_mean": 35.09087333775396,
|
||||
"aggregate_output_tps_p50": 34.96408475660248,
|
||||
"aggregate_output_tps_p95": 35.52678209465127
|
||||
}
|
||||
]
|
||||
108
benchmarks/inference/results/20260831T134334Z/metadata.json
Normal file
108
benchmarks/inference/results/20260831T134334Z/metadata.json
Normal file
File diff suppressed because one or more lines are too long
8
benchmarks/inference/results/20260831T134334Z/raw.csv
Normal file
8
benchmarks/inference/results/20260831T134334Z/raw.csv
Normal file
@@ -0,0 +1,8 @@
|
||||
run_id,runtime,model,phase,concurrency,round,slot,request_id,prompt_name,prompt_chars,max_tokens,started_at,ttft_s,total_s,prompt_tokens,output_tokens,prompt_tps,decode_tps,request_tps,group_elapsed_s,group_output_tps,error
|
||||
20260831T134334Z,ollama,qwen3.8:27b-mlx,warmup,1,0,0,c3b04207-976b-4a0d-9d3c-80ef8dc4225f,short,106,128,2026-08-31T13:43:39.472249+00:00,3.4916902080294676,5.4140321660088375,20,96,114.72541286980045,48.19996255746575,17.731701079044402,5.4149448340176605,17.728712469407014,
|
||||
20260831T134334Z,ollama,qwen3.8:27b-mlx,warmup,1,1,0,47d529a2-f167-46a0-af05-a6ca0e1929a4,medium,252,128,2026-08-31T13:43:44.886979+00:00,0.35504300001775846,2.7301927499938756,43,128,157.93211765391837,52.61516193511847,46.88313673101913,2.730699084000662,46.87444352618714,
|
||||
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,0,0,5b638c8b-a185-48d7-8625-f6ebacc06853,short,106,128,2026-08-31T13:43:47.617556+00:00,0.11980204097926617,2.1940376659622416,20,96,441.616869764425,45.28260592046214,43.7549461840698,2.1943347500055097,43.749022340260055,
|
||||
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,1,0,fd1c62de-2412-4243-85a0-0851e2364f7c,medium,252,128,2026-08-31T13:43:49.811979+00:00,0.12685995898209512,2.771603333996609,43,128,831.312776076798,47.52723693214773,46.18265479404875,2.771931625029538,46.17718519613052,
|
||||
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,2,0,50050b20-0fd0-4e15-a4bb-ddfc74ada7e1,code,267,128,2026-08-31T13:43:52.584034+00:00,0.42160862497985363,2.646599249972496,54,128,159.3484419263456,56.09763282504741,48.363952344250905,2.6469858330092393,48.35688895791427,
|
||||
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,3,0,22721212-cd1e-460f-9aa3-f2a1bb6f2f96,short,106,128,2026-08-31T13:43:55.231045+00:00,0.09599920798791572,2.2750009580049664,20,96,2500000.0,42.69653289142422,42.19778442826943,2.2753357499605045,42.19157546382611,
|
||||
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,4,0,d95f9110-8465-4bf1-8b6d-511699a58906,medium,252,128,2026-08-31T13:43:57.506343+00:00,0.09756654204102233,2.8720681670238264,43,128,3766313.3923097136,45.01625903574264,44.56718732154595,2.8723847499932162,44.56227530114212,
|
||||
|
170
benchmarks/inference/results/20260831T134334Z/raw.json
Normal file
170
benchmarks/inference/results/20260831T134334Z/raw.json
Normal file
@@ -0,0 +1,170 @@
|
||||
[
|
||||
{
|
||||
"run_id": "20260831T134334Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "c3b04207-976b-4a0d-9d3c-80ef8dc4225f",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:43:39.472249+00:00",
|
||||
"ttft_s": 3.4916902080294676,
|
||||
"total_s": 5.4140321660088375,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 114.72541286980045,
|
||||
"decode_tps": 48.19996255746575,
|
||||
"request_tps": 17.731701079044402,
|
||||
"group_elapsed_s": 5.4149448340176605,
|
||||
"group_output_tps": 17.728712469407014,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T134334Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "warmup",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "47d529a2-f167-46a0-af05-a6ca0e1929a4",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:43:44.886979+00:00",
|
||||
"ttft_s": 0.35504300001775846,
|
||||
"total_s": 2.7301927499938756,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 157.93211765391837,
|
||||
"decode_tps": 52.61516193511847,
|
||||
"request_tps": 46.88313673101913,
|
||||
"group_elapsed_s": 2.730699084000662,
|
||||
"group_output_tps": 46.87444352618714,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T134334Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 0,
|
||||
"slot": 0,
|
||||
"request_id": "5b638c8b-a185-48d7-8625-f6ebacc06853",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:43:47.617556+00:00",
|
||||
"ttft_s": 0.11980204097926617,
|
||||
"total_s": 2.1940376659622416,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 441.616869764425,
|
||||
"decode_tps": 45.28260592046214,
|
||||
"request_tps": 43.7549461840698,
|
||||
"group_elapsed_s": 2.1943347500055097,
|
||||
"group_output_tps": 43.749022340260055,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T134334Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 1,
|
||||
"slot": 0,
|
||||
"request_id": "fd1c62de-2412-4243-85a0-0851e2364f7c",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:43:49.811979+00:00",
|
||||
"ttft_s": 0.12685995898209512,
|
||||
"total_s": 2.771603333996609,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 831.312776076798,
|
||||
"decode_tps": 47.52723693214773,
|
||||
"request_tps": 46.18265479404875,
|
||||
"group_elapsed_s": 2.771931625029538,
|
||||
"group_output_tps": 46.17718519613052,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T134334Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 2,
|
||||
"slot": 0,
|
||||
"request_id": "50050b20-0fd0-4e15-a4bb-ddfc74ada7e1",
|
||||
"prompt_name": "code",
|
||||
"prompt_chars": 267,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:43:52.584034+00:00",
|
||||
"ttft_s": 0.42160862497985363,
|
||||
"total_s": 2.646599249972496,
|
||||
"prompt_tokens": 54,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 159.3484419263456,
|
||||
"decode_tps": 56.09763282504741,
|
||||
"request_tps": 48.363952344250905,
|
||||
"group_elapsed_s": 2.6469858330092393,
|
||||
"group_output_tps": 48.35688895791427,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T134334Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 3,
|
||||
"slot": 0,
|
||||
"request_id": "22721212-cd1e-460f-9aa3-f2a1bb6f2f96",
|
||||
"prompt_name": "short",
|
||||
"prompt_chars": 106,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:43:55.231045+00:00",
|
||||
"ttft_s": 0.09599920798791572,
|
||||
"total_s": 2.2750009580049664,
|
||||
"prompt_tokens": 20,
|
||||
"output_tokens": 96,
|
||||
"prompt_tps": 2500000.0,
|
||||
"decode_tps": 42.69653289142422,
|
||||
"request_tps": 42.19778442826943,
|
||||
"group_elapsed_s": 2.2753357499605045,
|
||||
"group_output_tps": 42.19157546382611,
|
||||
"error": null
|
||||
},
|
||||
{
|
||||
"run_id": "20260831T134334Z",
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"phase": "measured",
|
||||
"concurrency": 1,
|
||||
"round": 4,
|
||||
"slot": 0,
|
||||
"request_id": "d95f9110-8465-4bf1-8b6d-511699a58906",
|
||||
"prompt_name": "medium",
|
||||
"prompt_chars": 252,
|
||||
"max_tokens": 128,
|
||||
"started_at": "2026-08-31T13:43:57.506343+00:00",
|
||||
"ttft_s": 0.09756654204102233,
|
||||
"total_s": 2.8720681670238264,
|
||||
"prompt_tokens": 43,
|
||||
"output_tokens": 128,
|
||||
"prompt_tps": 3766313.3923097136,
|
||||
"decode_tps": 45.01625903574264,
|
||||
"request_tps": 44.56718732154595,
|
||||
"group_elapsed_s": 2.8723847499932162,
|
||||
"group_output_tps": 44.56227530114212,
|
||||
"error": null
|
||||
}
|
||||
]
|
||||
28
benchmarks/inference/results/20260831T134334Z/summary.json
Normal file
28
benchmarks/inference/results/20260831T134334Z/summary.json
Normal file
@@ -0,0 +1,28 @@
|
||||
[
|
||||
{
|
||||
"runtime": "ollama",
|
||||
"model": "qwen3.8:27b-mlx",
|
||||
"concurrency": 1,
|
||||
"requests": 5,
|
||||
"successes": 5,
|
||||
"failures": 0,
|
||||
"ttft_s_mean": 0.1723672749940306,
|
||||
"ttft_s_p50": 0.11980204097926617,
|
||||
"ttft_s_p95": 0.36265889178030186,
|
||||
"total_s_mean": 2.551861874992028,
|
||||
"total_s_p50": 2.646599249972496,
|
||||
"total_s_p95": 2.8519752004183827,
|
||||
"prompt_tps_mean": 1253549.1340794961,
|
||||
"prompt_tps_p50": 831.312776076798,
|
||||
"prompt_tps_p95": 3513050.713847771,
|
||||
"decode_tps_mean": 47.324053520964824,
|
||||
"decode_tps_p50": 45.28260592046214,
|
||||
"decode_tps_p95": 54.383553646467476,
|
||||
"request_tps_mean": 45.013305014436966,
|
||||
"request_tps_p50": 44.56718732154595,
|
||||
"request_tps_p95": 47.927692834210475,
|
||||
"aggregate_output_tps_mean": 45.00738945185462,
|
||||
"aggregate_output_tps_p50": 44.56227530114212,
|
||||
"aggregate_output_tps_p95": 47.92094820555752
|
||||
}
|
||||
]
|
||||
37
benchmarks/inference/results/backend_verification.json
Normal file
37
benchmarks/inference/results/backend_verification.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"verified_at": "2026-08-31",
|
||||
"host": "Apple M4 Max, arm64, macOS 15.6",
|
||||
"ollama": {
|
||||
"version": "0.32.14",
|
||||
"mlx_version": "0.32.0-213-gadf21de",
|
||||
"device": "gpu",
|
||||
"metal_library": true,
|
||||
"nvfp4_model": {
|
||||
"name": "qwen3.8:27b-mlx",
|
||||
"id": "5642e97495e1",
|
||||
"format": "safetensors",
|
||||
"quantization": "nvfp4",
|
||||
"parameter_size": "27.8B",
|
||||
"runner_log": "starting mlx runner subprocess"
|
||||
},
|
||||
"mxfp8_model": {
|
||||
"name": "qwen3.8:27b-mxfp8",
|
||||
"id": "464021588235",
|
||||
"format": "safetensors",
|
||||
"quantization": "mxfp8",
|
||||
"parameter_size": "27.8B",
|
||||
"runner_log": "starting mlx runner subprocess"
|
||||
}
|
||||
},
|
||||
"vllm_metal": {
|
||||
"vllm_version": "0.28.0+cpu",
|
||||
"plugin_version": "0.4.0.dev20260831112704",
|
||||
"mlx_version": "0.32.0",
|
||||
"mlx_lm_version": "0.31.3",
|
||||
"mlx_vlm_version": "0.6.4",
|
||||
"platform_plugin": "metal",
|
||||
"compute_log": "MLX device set to: Device(gpu, 0)",
|
||||
"pytorch_device_log": "PyTorch device set to: mps",
|
||||
"note": "The +cpu suffix identifies the portable vLLM core wheel; the Metal plugin supplies MLX GPU execution."
|
||||
}
|
||||
}
|
||||
27
benchmarks/inference/results/cold_start.json
Normal file
27
benchmarks/inference/results/cold_start.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"measured_at": "2026-08-31",
|
||||
"notes": [
|
||||
"Cold starts were measured separately from warm inference.",
|
||||
"The vLLM model was already present in the Hugging Face cache; zero bytes were downloaded.",
|
||||
"vLLM launch-to-ready is derived from the recorded epoch and second-resolution API startup log.",
|
||||
"Ollama's daemon was already running, but the model was fully unloaded before the request.",
|
||||
"The Ollama request used one output token and keep_alive=0 so generation time was negligible and the model was unloaded afterward."
|
||||
],
|
||||
"vllm_metal": {
|
||||
"process_start_epoch": 1788177244.465068,
|
||||
"api_ready_local_time": "2026-08-31T13:54:33+02:00",
|
||||
"approx_launch_to_api_ready_s": 28.535,
|
||||
"model_load_s": 3.25,
|
||||
"engine_profile_cache_warmup_s": 9.71,
|
||||
"download_bytes": 0
|
||||
},
|
||||
"ollama": {
|
||||
"client_total_s": 3.455159667,
|
||||
"server_total_s": 3.448873125,
|
||||
"model_load_s": 3.244982292,
|
||||
"prompt_eval_s": 0.13364925,
|
||||
"decode_s": 0.069530292,
|
||||
"prompt_tokens": 7,
|
||||
"output_tokens": 1
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user