kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
rel
TensorRT-LLMs/benchmarks
History
Sharan Chetlur 258c7540c0 open source 09df54c0cc99354a60bbc0303e3e8ea33a96bef0 (#2725) 
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>

open source f8c0381a2bc50ee2739c3d8c2be481b31e5f00bd (#2736)

Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>

Add note for blackwell (#2742)

Update the docs to workaround the extra-index-url issue (#2744)

update README.md (#2751)

Fix github io pages (#2761)

Update
2025-02-11 02:21:51 +00:00
..
cpp open source 09df54c0cc99354a60bbc0303e3e8ea33a96bef0 (#2725) 2025-02-11 02:21:51 +00:00
python open source 09df54c0cc99354a60bbc0303e3e8ea33a96bef0 (#2725) 2025-02-11 02:21:51 +00:00
README.md Update TensorRT-LLM v0.14.0 (#2401) 2024-11-01 19:48:44 +08:00

README.md

TensorRT-LLM Benchmarks

Overview

There are currently three workflows to benchmark TensorRT-LLM:

  • C++ benchmarks
    • The recommended workflow that uses TensorRT-LLM C++ API and can take advantage of the latest features of TensorRT-LLM.
  • Python benchmarks
    • The Python benchmarking scripts can only benchmark the Python runtime, which do not support the latest features, such as in-flight batching.
  • The Python benchmarking suite
    • This benchmarker is native to TensorRT-LLM and is a Python benchmarker for reproducing and testing the performance of TensorRT-LLM.
    • NOTE: This benchmarking suite is a current work in progress and is prone to large changes.