onnxruntime
35b42a80
- Refactor Intel SubgroupMatrix MatMulNBits (#27911)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
3 days ago
Refactor Intel SubgroupMatrix MatMulNBits (#27911) - Migrate inline C++ shader to WGSL templates - Add bias and weight index support for gpt_oss_20b - Enable xe-3lpg config for PTL
References
#27911 - Refactor Intel SubgroupMatrix MatMulNBits
Author
jchen10
Parents
4e1c42e2
Loading