NVIDIA / NVIDIA/TensorRT-LLM

[Feature]: Add NVFP4 KV cache support for SM120 in trtllm-gen

Open
#10,241 9 comments 3 reactions 1 assignee View on GitHub

@laikhtewari is already working on this.

Since Dec 23, 2025.

feature request KV-Cache Management
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

🚀 The feature, motivation and pitch

Currently NVFP4 is only available for SM10X in trtllm-gen. It would be useful to have this feature available for consumer Blackwell chips that are SM120 based. The primary use is to allow more VRAM to be used for context.

Alternatives

There are no alternative solutions. I tried loading the cubins for SM100 on the SM120 but it did not work.

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.