[Quant] [Bugfix] Fix quantization config matching with hf_to_vllm_mapper (#20046)

This commit is contained in:
Kyle Sayers
2025-07-01 19:20:34 +09:00
committed by GitHub
parent c05596f1a3
commit 9025a9a705
17 changed files with 107 additions and 29 deletions
@@ -32,6 +32,8 @@ class MarlinConfig(QuantizationConfig):
group_size: int,
lm_head_quantized: bool,
) -> None:
super().__init__()
# Group size for the quantization.
self.group_size = group_size
self.lm_head_quantized = lm_head_quantized