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
|
||||
}
|
||||
]
|
||||
Reference in New Issue
Block a user