THUDM / THUDM/slime

Speculative Decoding Standalone mode load draft model

Open
#1,548 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
8.5k
Forks
1.3k
Avg merge
5h 36m
Merged PRs (30d)
22

Description

用standalone speculative decoding貌似draft model加载失败 draft token输出全是0 logits也都是0

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

The issue reports a failure when loading the draft model in standalone speculative decoding, with draft tokens and logits output as zero. No file, test, or entry point is named; begin by locating the standalone speculative-decoding and draft-model loading paths, then reproduce the issue and verify that draft tokens and logits are no longer all zero.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.