TensorRT-LLMs/tensorrt_llm/bench/benchmark/utils
Fanrong Li 1fe64b90be
fix: fix the acceptance rate of pytorch workflow in trtllm-bench (#3240)
* fix acceptance rate of pytorch workflow.
* revert the RequestOutput API change.

---------

Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
2025-04-03 15:12:24 +08:00
..
__init__.py Update TensorRT-LLM (#2460) 2024-11-19 18:30:34 +08:00
asynchronous.py fix: fix the acceptance rate of pytorch workflow in trtllm-bench (#3240) 2025-04-03 15:12:24 +08:00
general.py fix gpus_per_node in trtllm-bench when world_size < device_count (#3007) 2025-03-27 09:31:40 +08:00
processes.py perf: Readd iteration logging for trtllm-bench. (#3039) 2025-04-01 08:13:09 +08:00