[Feat][CPU] Enable Gated DeltaNet Attention (Qwen 3.5 / 3.6) (#41025)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com> Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
This commit is contained in:
co-authored by
Vadim Gimpelson
parent
20cac26b19
commit
51f22dcfd0
@@ -213,6 +213,9 @@ class UnquantizedLinearMethod(LinearMethodBase):
|
||||
|
||||
def process_weights_after_loading(self, layer: torch.nn.Module) -> None:
|
||||
if current_platform.is_cpu():
|
||||
if layer.weight.ndim != 2:
|
||||
# this is not a linear layer
|
||||
return
|
||||
from vllm.model_executor.layers.utils import dispatch_cpu_unquantized_gemm
|
||||
|
||||
dispatch_cpu_unquantized_gemm(layer, remove_weight=True)
|
||||
|
||||
Reference in New Issue
Block a user