microsoft / microsoft/onnxruntime
[Feature Request] Support AMX BF16
Open
@yufenglee is already working on this.
Since Mar 19, 2024.
feature request
quantization
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
### Describe the feature request
#14042 Adds AMX support for int8 GEMM. It would be good to also have support for BF16.
If there is AMX support for BF16 GEMM, should the BF16 AMX be automatically used when the inputs are FP16 or FP32 or does the user need to explicitly Cast?
### Describe scenario use case
Higher-performance for BF16 GEMM on CPUs with AMX BF16.
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.
Assessment
This issue has not been assessed yet.