zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-28 07:54:24 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix deepseek sharding (#1242)

Browse Source
This commit is contained in:
Awni Hannun 2025-02-03 16:59:50 -08:00
parent e2e5478da5
commit 6e6ba07b54
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llms/mlx_lm/models/deepseek_v2.py
View File

@ -282,12 +282,12 @@ class MoEGate(nn.Module):
if self.topk_method == "group_limited_greedy": if self.topk_method == "group_limited_greedy":
bsz, seq_len = x.shape[:2] bsz, seq_len = x.shape[:2]
scores = scores.reshape(bsz, seq_len, self.n_group, -1) scores = scores.reshape(bsz, seq_len, self.n_group, -1)
group_scores = scores.max(axis=-1) group_scores = scores.max(axis=-1, keepdims=True)
k = self.n_group - self.topk_group k = self.n_group - self.topk_group
group_idx = mx.argpartition(group_scores, kth=k - 1, axis=-1)[..., :k] group_idx = mx.argpartition(group_scores, kth=k - 1, axis=-2)[..., :k, :]
batch_idx = mx.expand_dims(mx.arange(bsz), (1, 2)) scores = mx.put_along_axis(
seq_idx = mx.expand_dims(mx.arange(seq_len), (0, 2)) scores, group_idx, mx.array(0.0, scores.dtype), axis=-2
scores[batch_idx, seq_idx, group_idx] = 0.0 )
scores = scores.reshape(bsz, seq_len, -1) scores = scores.reshape(bsz, seq_len, -1)
k = self.top_k k = self.top_k