xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-20 20:25:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bug] Fix usage of .transpose() and .view() consecutively. (#11979)

Browse Source
This commit is contained in:
Siyuan Li 2025-01-13 14:24:10 +08:00 committed by GitHub
parent f7b3ba82c3
commit 9dd02d85ca
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/attention/layer.py
View File

@ -230,7 +230,7 @@ class MultiHeadAttention(nn.Module):
value, value,
scale=self.scale) scale=self.scale)
out = out.transpose(1, 2) out = out.transpose(1, 2)
return out.view(bsz, q_len, -1) return out.reshape(bsz, q_len, -1)
def unified_attention( def unified_attention(

2
vllm/model_executor/models/intern_vit.py
View File

@ -271,7 +271,7 @@ class InternSdpaAttention(nn.Module):
v = v.transpose(1, 2) v = v.transpose(1, 2)
x = F.scaled_dot_product_attention(q, k, v, scale=self.scale) x = F.scaled_dot_product_attention(q, k, v, scale=self.scale)
x = x.transpose(1, 2).view(B, N, -1) x = x.transpose(1, 2).reshape(B, N, -1)
x = self.proj(x) x = self.proj(x)
return x return x