Skip to content

[AutoDeploy][Feature]: Add pattern matcher to support the NemotronHTopkRouter #9164

@nvchenghaoz

Description

@nvchenghaoz

🚀 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.

Metadata

Metadata

Assignees

Labels

AutoDeploy<NV> AutoDeploy Backendfeature requestNew feature or request. This includes new model, dtype, functionality support

Projects

Status

Backlog

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions