NVIDIA / NVIDIA/TensorRT-LLM

[Feature Request] Better support for w4a8 quantization

Open
#2,605 4 comments 0 reactions 1 assignee View on GitHub

@Barry-Delaney is already working on this.

Since Dec 23, 2024.

Investigating Low Precision triaged
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

Based on this doc, we have to use deepcompressor to build prepare fake-quantized checkpoint. However, it's a lot more trouble to set up that repo and it seems to me that tool is not being maintained well, especially for new llama models like 3.1/3.2. At least I was not able to do it successfully for llama 3.1 8b.

It would be great if we can add more native support for w4a8 quantization in the trtllm.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.