huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix qwen2 failure in intel cpu

Browse Source 
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi A 2024-10-30 22:29:05 -07:00
parent befd9f6735
commit 3836c3fe72
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/custom_modeling/qwen2_vl.py
View File

@ -505,5 +505,7 @@ class Qwen2VLForConditionalGeneration(nn.Module):
prefill_cache_indices=prefill_cache_indices,
)
hidden_states, _ = self.norm(hidden_states)
if lm_head_indices is not None:
hidden_states = hidden_states[lm_head_indices]
logits = self.lm_head(hidden_states)
return logits, None