huggingface / huggingface/pytorch_block_sparse
Only blockshape=(32, 32) is supported
Open
- Dominant language
- C++
- Stars
- 551
- Forks
- 34
- PR merge metrics
- No merged PRs in 30d
Description
When I set the blockshape to (64, 64) or (128, 128), the result is quite wrong
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.