Michael Goin 519ef9a911 [UX] Make vllm bench serve discover model by default and use --input-len (#30816) ...

Signed-off-by: mgoin <mgoin64@gmail.com>

2025-12-17 01:55:30 -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

[Bugfix]: Fix TokenizerLike interface (#30009)

2025-12-05 20:56:40 -08:00

latency.py

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

serve.py

[UX] Make vllm bench serve discover model by default and use --input-len (#30816)

2025-12-17 01:55:30 -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