search

NVIDIA / 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.
https://nvidia.github.io/TensorRT-LLM
Apache License 2.0
7.37k stars 796 forks source link

Decoding Logic #791

Open riyaj8888 opened 6 months ago

riyaj8888 commented 6 months ago

Hi , Is there any way we can change the decoding logic? example : like support for speculative sampling or other

jdemouth-nvidia commented 6 months ago

We are working on adding support for speculative decoding. There's already support for it in the main branch as a preview (more work is needed to make it more performant).

riyaj8888 commented 6 months ago

thanks