microsoft / microsoft/onnxruntime
Support output QK symbolic shape inference
Open
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
Update GQA symbolic shape inference (https://github.com/microsoft/onnxruntime/blob/9de58ac7a3d18d6ae7f7ae502b3f91361067f1b5/onnxruntime/python/tools/symbolic_shape_infer.py#L2548) to account for newly added output QK optional output.
Contributor guide
Assessment
This issue has not been assessed yet.