[Auto Sync] Update deepseek_v2.py (20250922) (#10717)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Michael Granado <mgranado@together.ai>
This commit is contained in:
@@ -451,7 +451,7 @@ class MoEGate(nn.Module):
|
||||
_is_cuda
|
||||
and hidden_states.shape[0] <= 16
|
||||
and hidden_states.shape[1] == 7168
|
||||
and self.weight.shape[0] == 256
|
||||
and (self.weight.shape[0] == 256 or self.weight.shape[0] == 384)
|
||||
and _device_sm >= 90
|
||||
):
|
||||
# router gemm output float32
|
||||
|
||||
Reference in New Issue
Block a user