xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 21:55:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

improve the robustness of parsing vlms config in AutoRound (#18894)

Browse Source 
Signed-off-by: wenhuach21 <wenhua.cheng@intel.com>
This commit is contained in:
Wenhua Cheng 2025-05-30 10:24:47 +08:00 committed by GitHub
parent 3132290a14
commit 3de3eadf5b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -116,8 +116,9 @@ class AutoRoundConfig(QuantizationConfig):
quantized = True
if self.block_name_to_quantize:
quantized = any(name in layer_name
for name in self.block_name_to_quantize)
quantized = any(
layer_name.startswith(name)
for name in self.block_name_to_quantize)
elif isinstance(layer, ParallelLMHead):
quantized = False