zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-12-16 01:49:05 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

mxfp4 works

Browse Source
This commit is contained in:
Awni Hannun
2025-08-19 07:49:56 -07:00
committed by Awni Hannun
parent 88c71d2b13
commit 9807ba0267
12 changed files with 2420 additions and 257 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
python/tests/test_nn.py
View File

@@ -198,6 +198,12 @@ class TestBase(mlx_tests.MLXTestCase):
self.assertTrue(isinstance(m.layers[1], nn.ReLU))
self.assertTrue(isinstance(m.layers[2], nn.QuantizedLinear))
nn.quantize(m, group_size=32, mode="mxfp4")
self.assertTrue(isinstance(m.layers[0], nn.QuantizedEmbedding))
self.assertTrue(isinstance(m.layers[1], nn.ReLU))
self.assertTrue(isinstance(m.layers[2], nn.QuantizedLinear))
self.assertTrue(isinstance(m.layers[2].scales, mx.array))
def test_quantize_freeze(self):
lin = nn.Linear(512, 512)
qlin = lin.to_quantized()