Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Address ZeroK case for Gemm for CPU and CUDA #22111

Merged
merged 12 commits into from
Sep 21, 2024
Merged

Conversation

yuslepukhin
Copy link
Member

@yuslepukhin yuslepukhin commented Sep 17, 2024

Description

When K == 0 output a MxN matrix filled with bias if present or filled with zeros.
This brings it inline with MatMul behavior especially when Gemm is used to fuse MatMul with Add.

Motivation and Context

  • Comply with numpy spec of MatMul
  • Address a case when empty initializers are used for computation.

pranavsharma
pranavsharma previously approved these changes Sep 17, 2024
snnn
snnn previously approved these changes Sep 19, 2024
snnn
snnn previously approved these changes Sep 19, 2024
cmake/onnxruntime_python.cmake Outdated Show resolved Hide resolved
onnxruntime/core/providers/cpu/math/gemm.cc Outdated Show resolved Hide resolved
@yuslepukhin yuslepukhin merged commit fe8a10c into main Sep 21, 2024
87 checks passed
@yuslepukhin yuslepukhin deleted the yuslepukhin/zeroK_Gemm branch September 21, 2024 00:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants