onnxruntime
150c4cb8
- [MLAS AArch64] SQNBitGemm CompInt8 kernel (#18953)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
[MLAS AArch64] SQNBitGemm CompInt8 kernel (#18953) Implement ARM NEON SQNBitGemm kernel that first block quantizes A to int8 and then does int8 multiplication.
References
#18953 - [MLAS AArch64] SQNBitGemm CompInt8 kernel
Author
edgchen1
Parents
a756017e
Loading