[FEA] Has CUTLASS considered supporting Zero-points and block-wise scaling in Hoppr Mixed Grouped Gemm recently?
Open
Nobody has claimed this yet.
? - Needs Triage
feature request
inactive-90d
- Dominant language
- C++
- Stars
- 10.5k
- Forks
- 2.1k
- Avg merge
- 3d 11h
- Merged PRs (30d)
- 7
Description
For the Hopper architecture, the mixed_dtype_grouped_gemm currently only supports row-wise scaling. However, for the AWQ quantization, the precision loss is still quite significant.
Will CUTLASS support the Zero-points and block-wise scaling of AWQ (W4A16 / W4A8) for MoE models?
Thanks~
Contributor guide
No contributing guide indexed for this repository
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 by reviewing the mixed_dtype_grouped_gemm support described in the issue and the AWQ requirements for W4A16 and W4A8 MoE models. Determine the scope for zero-points and block-wise scaling, then confirm what CUTLASS behavior and validation would be needed for support.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100