onnxruntime
3ef44981
- MLAS: support prepacking APIs for quantized GEMM (#4433)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
5 years ago
MLAS: support prepacking APIs for quantized GEMM (#4433) Add support for prepacking matrix B for use in the quantized GEMMs.
References
#4433 - MLAS: support prepacking APIs for quantized GEMM
Author
tracysh
Parents
dd73e8c0
Loading