NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy]: Debug host sync in Eagle

Open
#12,480 1 comment 0 reactions 1 assignee View on GitHub

@govind-ramnarayan is already working on this.

Since Mar 24, 2026.

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

Description

We needed to add a host sync between target and draft model forwards to ensure good acceptance rate. We need to figure out why in order to remove it.

https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/_torch/auto_deploy/models/custom/modeling_eagle.py#L751

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.