NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy] Expose logit_softcap in torch attention reference ops

Open
#4,881 0 comments 0 reactions 1 assignee View on GitHub

@nvchenghaoz is already working on this.

Since Jun 3, 2025.

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

Description

During pattern matching we insert torch reference ops into the graph. When we adapt the pattern matcher to detect logit softcap we need to also have a corresponding torch reference op ready that can take the logit softcap parameter

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.