deepspeedai / deepspeedai/DeepSpeed
Compression training: when quantizer_kernel is enabled, the check target of "rounding" param should be "nearest" instead of "nearest_neighbor"
Open
Beginner friendly
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
https://github.com/microsoft/DeepSpeed/blob/11f8e4a5c81ed0553ec1b371fd9d5eee229bdcf0/deepspeed/runtime/quantize.py#L155C73-L155C73
According to https://www.deepspeed.ai/docs/config-json/#weight-quantization, we should check whether self.q_rounding is "nearest", not "nearest_neighbor".
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 at deepspeed/runtime/quantize.py around line 155 and compare the check for q_rounding with the weight-quantization documentation. Confirm that the validation matches the documented "nearest" value rather than "nearest_neighbor"; done means the configuration check accepts the documented setting.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Active
- Clarity
- Clearly specified
- Newbie friendliness
- 88/100