deepspeedai / deepspeedai/DeepSpeed
[BUG] fp6 can‘t load qwen1.5-34b-chat
Nobody has claimed this yet.
- 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
thanks for your help!
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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