deepspeedai / deepspeedai/DeepSpeed
Does deepspeed support qdq model used pytorch-quantization for training？
Open
Nobody has claimed this yet.
bug
compression
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
I used the qdq model for llama sft, but the parameters related to quantization cannot be loaded correctly. Could anyone please tell me how to solve this problem?
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
No files, tests, or entry points are named. Start by reproducing the qdq model with llama SFT and inspect where the quantization-related parameters fail to load; done means establishing whether this configuration is supported and documenting or addressing the loading failure.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100