mlx/python/mlx/nn/layers
Lucas Newman 4a64d4bff1
Add support for grouped 1D convolutions to the nn API (#1444)
* Fix the weight shape for grouped convolutions from the nn API.

* Add tests.

* Pre-commit formatting.

* Add input validation.

* Use integer division instead of casting.

* docs

* nit

---------

Co-authored-by: Awni Hannun <awni@apple.com>
2024-09-28 06:41:07 -07:00
..
__init__.py Transposed Convolution (#1245) 2024-09-06 19:52:38 -07:00
activations.py feat: Added "tanh" option to GELU approximation (#1268) 2024-07-28 09:07:56 +02:00
base.py fix module attribute set, reset, set (#1403) 2024-09-11 16:30:42 -07:00
containers.py copyright + ack 2023-11-30 11:12:53 -08:00
convolution_transpose.py Transposed Convolution (#1245) 2024-09-06 19:52:38 -07:00
convolution.py Add support for grouped 1D convolutions to the nn API (#1444) 2024-09-28 06:41:07 -07:00
dropout.py Fix: Preserve input dtype in Dropout layer output (#1323) 2024-08-13 11:54:21 -07:00
embedding.py Block sparse qmm (#1124) 2024-05-16 15:24:14 -07:00
linear.py Block sparse qmm (#1124) 2024-05-16 15:24:14 -07:00
normalization.py faster group norm (#1304) 2024-08-01 12:49:23 -07:00
pooling.py Some fixes to typing (#1371) 2024-08-28 11:16:19 -07:00
positional_encoding.py Doc error for default for scale in SinusoidalPositionalEncoding (#1174) 2024-06-02 13:42:45 -07:00
quantized.py Some fixes to typing (#1371) 2024-08-28 11:16:19 -07:00
recurrent.py Faster RNN layers (#1419) 2024-09-17 06:04:19 -07:00
transformer.py Fix typo in transformer docs (#1414) 2024-09-14 06:05:15 -07:00
upsample.py Upsample with bicubic interpolation (#967) 2024-04-10 15:47:22 -07:00