xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 18:06:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BUG FIX] minicpm (#18739)

Browse Source 
Signed-off-by: huangyuxiang03 <huangyx0321@gmail.com>
Co-authored-by: huangyuxiang03 <huangyx0321@gmail.com>
This commit is contained in:
Shawn Huang 2025-05-27 16:04:49 +08:00 committed by GitHub
parent e0f0ff87b8
commit 6881107948
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/models/minicpm.py
View File

@ -242,9 +242,6 @@ class MiniCPMAttention(nn.Module):
base=rope_theta, base=rope_theta,
rope_scaling=rope_scaling, rope_scaling=rope_scaling,
) )
# set rope as fp32 instead of bf16
self.rotary_emb.cos_sin_cache = self.rotary_emb._compute_cos_sin_cache(
)
self.attn = Attention(self.num_heads, self.attn = Attention(self.num_heads,
self.head_dim, self.head_dim,
self.scaling, self.scaling,