biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[UX] Remove noisy CT UnquantizedLinearMethod warn (#33273)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2026-01-28 19:09:30 -05:00
committed by GitHub
parent 6bf3b46d78
commit 141cd43967
1 changed files with 1 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
View File

@@ -751,11 +751,7 @@ class CompressedTensorsConfig(QuantizationConfig):
model_compression_config=model_compression_config, model_compression_config=model_compression_config,
) )
elif weight_quant is None: elif weight_quant is None:
logger.warning_once( # Falling back to UnquantizedLinearMethod
"Acceleration for non-quantized schemes is "
"not supported by Compressed Tensors. "
"Falling back to UnquantizedLinearMethod"
)
return None return None
else: else: