L-electron-Rare/mlx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adds C++ and nn quantization utilities (#230)

Browse Source 
* Add C++ de-/quantize ops
* Add quantize functions to the docs and tests
* Add a QuantizedLinear module
This commit is contained in:
Angelos Katharopoulos
2023-12-20 14:17:38 -08:00
committed by GitHub
parent 4912ff3ec2
commit 57fe918cf8
12 changed files with 451 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/python/nn/layers.rst
+1
View File
@@ -26,3 +26,4 @@ Layers
RoPE
MultiHeadAttention
Sequential
QuantizedLinear