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

111
benchmarks/inference/coding-results/20260831T121823Z-vllm-metal-qwen3.8-27b-nvfp4/results.json Normal file
View File

File diff suppressed because one or more lines are too long

53
benchmarks/inference/coding-results/20260831T121823Z-vllm-metal-qwen3.8-27b-nvfp4/summary.json Normal file
View File

@@ -0,0 +1,53 @@
[
{
"task": "python_async_cache",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-nvfp4",
"started_at": "2026-08-31T12:10:51.466896+00:00",
"prompt_chars": 857,
"max_tokens": 3072,
"ttft_s": 1.0361592500121333,
"total_s": 133.43742824997753,
"prompt_tokens": 211,
"output_tokens": 3072,
"decode_tps": 23.20219453486358,
"finish_reason": "length",
"output_chars": 14058,
"output_sha256": "a18e80f1852ecc0c70b987f244870b8a2dc20db8ad42505280162a4b17dbd057",
"error": null
},
{
"task": "php_idempotent_transfer",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-nvfp4",
"started_at": "2026-08-31T12:13:04.907109+00:00",
"prompt_chars": 756,
"max_tokens": 3072,
"ttft_s": 15.930970875022467,
"total_s": 166.00547937501688,
"prompt_tokens": 182,
"output_tokens": 2840,
"decode_tps": 18.923933374068692,
"finish_reason": "stop",
"output_chars": 11403,
"output_sha256": "bb758808663b88bb3fbacc52df49598eb21aa8bc7fa0ee8466410f0ae13e8b0d",
"error": null
},
{
"task": "typescript_dag_scheduler",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-nvfp4",
"started_at": "2026-08-31T12:15:50.913910+00:00",
"prompt_chars": 773,
"max_tokens": 3072,
"ttft_s": 1.4814700839924626,
"total_s": 152.22010587499244,
"prompt_tokens": 183,
"output_tokens": 3072,
"decode_tps": 20.379645761550783,
"finish_reason": "length",
"output_chars": 10869,
"output_sha256": "f700d51c471a59acfcf85016d416f0c5354662552fea44b48f56d80c3afdcb59",
"error": null
}
]