kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
c289880afb
TensorRT-LLMs/tensorrt_llm/bench/dataclasses
History
kris1025 6a3a921284
[TRTLLM-6685][feat] Add speculative metrics for trt llm bench (#6476) 
Signed-off-by: linquanh <linquanh@nvidia.com>
2025-08-04 15:22:57 -07:00
..
__init__.py Update TensorRT-LLM (#2502) 2024-11-26 16:51:34 +08:00
configuration.py [fix] Fixes KV Cache overrides in trtllm-bench (#6103) 2025-07-18 03:44:44 +08:00
engine.py Update TensorRT-LLM (#2502) 2024-11-26 16:51:34 +08:00
enums.py Update TensorRT-LLM (#2502) 2024-11-26 16:51:34 +08:00
general.py Enable trtllm-bench to run LoRA and add basic e2e perf testing capability for LoRA in PyT flow (#5130) 2025-06-15 18:54:04 +03:00
reporting.py [TRTLLM-6685][feat] Add speculative metrics for trt llm bench (#6476) 2025-08-04 15:22:57 -07:00
statistics.py [TRTLLM-6685][feat] Add speculative metrics for trt llm bench (#6476) 2025-08-04 15:22:57 -07:00