xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-23 12:04:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[XPU] Fix AWQ skipped layer detection in IPEX quantization (#29774)

Browse Source 
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
This commit is contained in:
Fanli Lin 2025-12-01 20:00:52 +08:00 committed by GitHub
parent f0a28bf661
commit f37e8938d2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/layers/quantization/ipex_quant.py
View File

@ -150,7 +150,10 @@ class IPEXConfig(QuantizationConfig):
if isinstance(layer, LinearBase):
if self.method == "awq":
if is_layer_skipped(
prefix, self.modules_to_not_convert, self.packed_modules_mapping
prefix,
self.modules_to_not_convert,
self.packed_modules_mapping,
skip_with_substr=True,
):
return UnquantizedLinearMethod()
return IPEXAWQLinearMethod(self)