[Kernel] Extend Marlin thread-tile padding to MoE (WNA16 + FP8/MXFP8) (#45703)
Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -243,7 +243,9 @@ class AutoGPTQConfig(QuantizationConfig):
|
||||
if isinstance(layer, RoutedExperts):
|
||||
from vllm.model_executor.layers.quantization.moe_wna16 import MoeWNA16Config
|
||||
|
||||
if not check_moe_marlin_supports_layer(layer, self.group_size):
|
||||
if not check_moe_marlin_supports_layer(
|
||||
layer, self.group_size, allow_tile_padding=not self.desc_act
|
||||
):
|
||||
logger.warning_once(
|
||||
f"Layer '{prefix}' is not supported by GPTQMoeMarlin. "
|
||||
"Falling back to Moe WNA16 kernels."
|
||||
|
||||
Reference in New Issue
Block a user