huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 19:34:53 +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 2025-07-01 00:56:50 -07:00
parent 7c8694545f
commit 6382b4261c
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server/text_generation_server/layers/lora.py
View File

@ -51,9 +51,8 @@ class LoraLinear(nn.Module):
return result return result
data: Optional["BatchLoraWeights"] = adapter_data.data.get(layer_type) data: Optional["BatchLoraWeights"] = adapter_data.data.get(layer_type)
if ( if data is not None and (
data is not None SYSTEM == "ipex"
and SYSTEM == "ipex"
or (punica_sgmv is not None and data.can_vectorize(self.process_group)) or (punica_sgmv is not None and data.can_vectorize(self.process_group))
): ):
# In tensor-parallel configurations, each GPU processes a specific segment of the output. # In tensor-parallel configurations, each GPU processes a specific segment of the output.