onnxruntime
c5aa86e1
- [WebNN EP] Support 8-bit MatMulNBits (#29025)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
44 days ago
[WebNN EP] Support 8-bit MatMulNBits (#29025) Add support for 8-bit quantized weights (bits=8) in the MatMulNBits op builder. Previously only 4-bit was supported. The 8-bit path uses uint8 block size and scales the dequantized values appropriately.
References
#29025 - [WebNN EP] Support 8-bit MatMulNBits
Author
Honry
Parents
bc226539
Loading