NVIDIA / NVIDIA/TensorRT-LLM

MLIR-fusion seems to corrupt CUDA graph replay in Gemma4 e2b

Open
#14,272 1 comment 0 reactions 1 assignee View on GitHub

@nvchenghaoz is already working on this.

Since May 18, 2026.

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

Description

MLIR elementwise kernels currently corrupt piecewise CUDA graph replay for Gemma4 E2B.

Steps to reproduce:
examples/auto_deploy/model_registry/configs/gemma4_e2b.yaml
enable mlir_elementwise_fusion
and run the model e2e.

  mlir_elementwise_fusion:
    enabled: true

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.