christian.meyer/lai_automatisierung
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: record Qwen MLX benchmark results
Some checks failed
CI / test (push) Has been cancelled
Details
CI / test (pull_request) Has been cancelled
Details

Browse Source
This commit is contained in:
Christian Meyer
2026-08-31 16:39:37 +02:00
parent 75b2c8958c
commit 407af8099b
40 changed files with 6091 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

136
benchmarks/inference/results/20260831T132015Z/metadata.json Normal file
View 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
View 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,
1 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
2 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
3 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
4 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
5 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
6 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
7 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
8 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
9 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
10 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
11 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
12 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
13 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
14 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
15 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
16 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
17 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
18 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
19 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
20 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
21 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
22 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
23 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
24 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
25 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
26 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
27 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
28 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
29 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
30 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
31 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
32 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
33 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
34 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
35 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
36 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
View 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
View 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
}
]