/TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Primary LanguageC++Apache License 2.0Apache-2.0

Pinned issues

TensorRT-LLM Requests

#632 opened by ncomly-nvidia

Open15

[Issue Template]Short one-line summary of the issue #270

#783 opened by juney-nvidia

Open0

Issues