We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent c4e48ee commit 1b2a672Copy full SHA for 1b2a672
vllm/model_executor/layers/fused_moe/config.py
@@ -341,7 +341,10 @@ def make(
341
342
if quant_config is not None and isinstance(quant_config,
343
QuantizationConfig):
344
- block_shape = quant_config.get("weight_block_size", None)
+ if hasattr(quant_config, 'weight_block_size'):
345
+ block_shape = quant_config.weight_block_size
346
+ else:
347
+ block_shape = None
348
per_act_token_quant = False
349
per_out_ch_quant = False
350
quant_dtype: Optional[torch.dtype] = None
0 commit comments