Ning Xie 3b8f31b362 [benchmark] use model card root instead of id (#31329) ...

Signed-off-by: Andy Xie <andy.xning@gmail.com>

2025-12-26 10:55:56 +08:00

..

lib

[Benchmark] Enable benchmark to run with encoding_format="bytes" (#27467)

2025-10-24 11:16:50 +00:00

sweep

Fix boolean nested params, add dict format support, and enhance plotting for vllm bench sweep (#29025)

2025-12-02 20:40:56 +00:00

__init__.py

Fix Python packaging edge cases (#17159)

2025-04-26 06:15:07 +08:00

datasets.py

Revert "[bench] Support common prefix len config (for decode-only bench)" (#31240)

2025-12-23 21:17:23 -08:00

latency.py

[Misc] support nsys profile for bench latency (#29776)

2025-12-18 14:52:20 +00:00

serve.py

[benchmark] use model card root instead of id (#31329)

2025-12-26 10:55:56 +08:00

startup.py

[Misc] Add a script to benchmark compilation time (#29919)

2025-12-14 13:02:39 +00:00

throughput.py

[Bugfix] Fix prefix_repetition routing in bench throughput (#29663)

2025-12-16 01:37:15 -08:00