onnxruntime
b7bb4d22
- move to tiling approach for sqnbitgemm compint8 impl
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
move to tiling approach for sqnbitgemm compint8 impl
References
#21193 - [MLAS] AArch64 SQNBitGemm CompInt8 initial multi-row implementation
Author
edgchen1
Parents
10505a6f
Loading