[Kernel] Consolidate Marlin thread-tile padding across all dense Marlin paths (#45295)
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -468,6 +468,7 @@ class ModelOptFp8LinearMethod(LinearMethodBase):
|
||||
layer.logical_widths = output_partition_sizes
|
||||
layer.input_size_per_partition = input_size_per_partition
|
||||
layer.output_size_per_partition = output_size_per_partition
|
||||
layer.orig_dtype = params_dtype
|
||||
weight_dtype = (
|
||||
torch.float8_e4m3fn
|
||||
if self.quant_config.is_checkpoint_fp8_serialized
|
||||
|
||||
Reference in New Issue
Block a user