Length masking for batch inputs (#1173)

* length masking

* add mask to mlx_lm model interface

* remove lengths

* fix test:

* comment + fix
This commit is contained in:
Alex Barron
2024-12-18 19:43:52 -08:00
committed by GitHub
parent db109184b7
commit d4ef909d4a
34 changed files with 191 additions and 72 deletions

View File

@@ -123,7 +123,8 @@ class QwenModel(nn.Module):
def __call__(self, inputs, mask=None, cache=None):
x = self.wte(inputs)
mask = create_attention_mask(x, cache)
if mask is None:
mask = create_attention_mask(x, cache)
if cache is None:
cache = [None] * len(self.h)