NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy][Feature]: Spec Dec + Guided Decoding Support

Open
#10,134 2 comments 1 reaction 1 assignee View on GitHub

Nobody has claimed this yet.

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

Description

🚀 The feature, motivation and pitch

Spec dec + guided decoding together cause some complications - roughly speaking, the sampling needs to do guided decoding, but then the draft tokens also need to be guided otherwise they will never be accepted.

Currently we just check that we don't have both enabled at the same time for AutoDeploy.

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.