[Quant] [Bugfix] Fix quantization config matching with hf_to_vllm_mapper (#20046)
This commit is contained in:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user