TensorRT-LLMs/tensorrt_llm/bench/benchmark
Xianjie Qiao 325ccaae3d
Fix trtllm-bench iter_stats and cuda_graph_batch_sizes error errors. (#4827)
Signed-off-by: Xianjie <5410381+qiaoxj07@users.noreply.github.com>
Co-authored-by: bhsueh_NV <11360707+byshiue@users.noreply.github.com>
2025-06-04 16:36:07 +08:00
..
utils Fix trtllm-bench iter_stats and cuda_graph_batch_sizes error errors. (#4827) 2025-06-04 16:36:07 +08:00
__init__.py Update TensorRT-LLM (#2389) 2024-10-29 22:24:38 +08:00
low_latency.py [enhanchment] Add beam width to low latency. (#4812) 2025-06-03 17:24:55 +08:00
throughput.py Fix trtllm-bench iter_stats and cuda_graph_batch_sizes error errors. (#4827) 2025-06-04 16:36:07 +08:00