huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 11:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

minor fix

Browse Source 
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi A 2025-06-29 23:02:10 -07:00
parent 9f6d1704fe
commit db11fe1f95
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/custom_modeling/qwen2_5_vl.py
View File

@ -460,7 +460,7 @@ class Qwen2_5VLAttention(nn.Module):
# execute flash attention # execute flash attention
if SYSTEM == "ipex": if SYSTEM == "ipex":
attn_output = torch.empty_like(query) attn_output = torch.empty_like(query)
if query.device.dtype == "xpu": if query.device.type == "xpu":
ipex.llm.functional.varlen_attention( ipex.llm.functional.varlen_attention(
query.contiguous(), query.contiguous(),
key.contiguous(), key.contiguous(),