ping

vllm/model_executor/layers/quantization/awq_marlin.py

@@ -25,7 +25,7 @@ class AWQMarlinConfig(QuantizationConfig):
     def __init__(self, weight_bits: int, group_size: int, has_zp: bool,
                  lm_head_quantized: bool) -> None:
         self.weight_bits = weight_bits
-        self.pack_factor = 32 // self.weight_bits  # packed into int32
+        self.pack_factor = 32 // self.weight_bits  # packed into 32bits
         self.group_size = group_size
         self.has_zp = has_zp
         self.lm_head_quantized = lm_head_quantized