chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

doc: improve modelopt error description (#12269)

Browse Source
This commit is contained in:
Liana Koleva
2025-10-28 20:57:55 -07:00
committed by GitHub
parent 5e36a0b455
commit e03b6beeb1
1 changed files with 8 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
python/sglang/srt/configs/model_config.py
View File

@@ -590,14 +590,20 @@ class ModelConfig:
return
# Check if ModelOpt quantization is specified
modelopt_quantization_specified = self.quantization in [
_MODELOPT_QUANTIZATION_METHODS = [
"modelopt",
"modelopt_fp8",
"modelopt_fp4",
]
modelopt_quantization_specified = (
self.quantization in _MODELOPT_QUANTIZATION_METHODS
)
if not modelopt_quantization_specified:
raise ValueError("quantize_and_serve requires ModelOpt quantization")
raise ValueError(
"quantize_and_serve requires ModelOpt quantization (set with --quantization "
f"{{{', '.join(sorted(_MODELOPT_QUANTIZATION_METHODS))}}})"
)
# quantize_and_serve is disabled due to compatibility issues
raise NotImplementedError(