Consolidate Intel Quantization Toolkit Integration in vLLM (#31716)

Signed-off-by: yiliu30 <yi4.liu@intel.com>
This commit is contained in:
Yi Liu
2026-01-14 07:11:30 +00:00
committed by GitHub
parent 6fa6e7ef0c
commit 50632adc58
10 changed files with 531 additions and 660 deletions
@@ -233,7 +233,7 @@ def get_quant_config(
quant_cls = get_quantization_config(model_config.quantization)
# GGUF doesn't have config file
if model_config.quantization in ("gguf", "inc"):
if model_config.quantization == "gguf":
return quant_cls()
# Read the quantization config from the HF model config, if available.