[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
@@ -63,6 +63,7 @@ class BitBLASConfig(QuantizationConfig):
# (since we have only one group per output channel)
desc_act = False
super().__init__()
self.weight_bits = weight_bits
self.group_size = group_size
self.desc_act = desc_act