zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-09-26 15:58:14 +08:00
Code Issues 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

1
docs/src/python/nn/layers.rst
View File

@@ -26,3 +26,4 @@ Layers
RoPE
MultiHeadAttention
Sequential
QuantizedLinear

3
docs/src/python/ops.rst
View File

@@ -34,6 +34,7 @@ Operations
conv2d
cos
cosh
dequantize
divide
equal
erf
@@ -73,6 +74,8 @@ Operations
partition
pad
prod
quantize
quantized_matmul
reciprocal
reshape
round