deepspeedai / deepspeedai/DeepSpeed

[BUG] fp6 can‘t load qwen1.5-34b-chat

Open
#5,579 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug inference
Dominant language
Python
Stars
43.1k
Forks
5k
Avg merge
4d 15h
Merged PRs (30d)
112

Description

Describe the bug
NotImplementedError: Cannot copy out of meta tensor; no data!
import mii model_path = 'Qwen1.5-32B-Chat-hf' pipe = mii.pipeline(model_path, quantization_mode='wf6af16') response = pipe(["DeepSpeed is", "Seattle is"], max_new_tokens=128) print(response)

System info (please complete the following information):

  • OS: Ubuntu 2004]
  • GPU A100
  • Python 3.11

stark
image
image

thanks for your help!

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 with the provided Python reproduction and the mii.pipeline entry point using quantization_mode='wf6af16'. Investigate why loading Qwen1.5-32B-Chat-hf attempts to copy from a meta tensor; done means the pipeline loads successfully and returns responses for the sample prompts.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.