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:
David Holtz 2024-10-31 22:39:07 +00:00
parent bfa16a5857
commit 17de5998e5
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
server/text_generation_server/models/custom_modeling/qwen2_vl.py
View File

@ -516,7 +516,7 @@ class Qwen2VLForConditionalGeneration(nn.Module):
prefill_cache_indices=prefill_cache_indices,
)
hidden_states, _ = self.norm(hidden_states)
print("lm_head_indices", lm_head_indices)
logits, speculative_logits = self.lm_head(hidden_states)
# import ipdb; ipdb.set_trace()
return logits, speculative_logits
if lm_head_indices is not None:
hidden_states = hidden_states[lm_head_indices]
logits = self.lm_head(hidden_states)
return logits, None