NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy]: Support nvfp4 quantization fusion

Open
#11,424 3 comments 0 reactions 1 assignee View on GitHub

@tcherckez-nvidia is already working on this.

Since Mar 9, 2026.

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

Description

🚀 The feature, motivation and pitch

We currently invoke dynamic quantization in a separate quantize_with_block_size kernel before every nvfp4 gemm.

Add a transformation to fuse quantization with the following gemm (preferred) or with the previous kernel (as epilogue - if fusing with gemm is not feasible).

See also: https://github.com/NVIDIA/TensorRT-LLM/pull/11273

Alternatives

No response

Additional context

No response

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

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.