NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy][Feature]: Add pattern matcher to support the NemotronHTopkRouter

Open
#9,164 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

🚀 The feature, motivation and pitch

Currently the NemotronHTopkRouter is supported with a patch. Please check the #9163.

Going forward, we can do the pattern matcher for the NemotronHTopkRouter and use the pattern matcher to fuse the top_k operators and other operators to torch.ops.trtllm.noaux_tc_op

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.

Research direction

Start by reviewing issue #9163 and the existing NemotronHTopkRouter patch referenced there. Trace the AutoDeploy pattern-matcher path and determine the scope needed to fuse the top_k and related operators into torch.ops.trtllm.noaux_tc_op; done means the router is supported without the patch.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, performance
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.