biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix: Apply embedding_multiplier to inputs_embeds (#34813)

Browse Source 
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Gabe Goodhart
2026-02-23 01:42:46 -07:00
committed by GitHub
parent e97c46a92d
commit e631f8e78e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -378,7 +378,7 @@ class GraniteMoeHybridModel(nn.Module):
hidden_states = inputs_embeds hidden_states = inputs_embeds
else: else:
hidden_states = self.embed_input_ids(input_ids) hidden_states = self.embed_input_ids(input_ids)
hidden_states = hidden_states * self.embedding_multiplier hidden_states *= self.embedding_multiplier
residual = None residual = None
else: else:
if intermediate_tensors is None: if intermediate_tensors is None: