NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy][Bug]: Fix the Torch kernel for SSM layers

Open
#8,170 1 comment 0 reactions 1 assignee View on GitHub

@nvchenghaoz is already working on this.

Since Oct 7, 2025.

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

Description

System Info

The Torch kernel does not handle the mixed batch (one batch with both prefill and decode) for TRT LLM.

Requirement:

  1. Fix the torch backend kernels
  2. Update the unit test.
Who can help?

No response

Information
  • The official example scripts
  • My own modified scripts
Tasks
  • An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
  • My own task or dataset (give details below)
Reproduction

N/A

Expected behavior

The expected output from torch backend should be the same / or approximately same as the triton fast kernels.

actual behavior

The torch backend could only have the prefill-only and decode-only batch.

additional notes

N/A

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.