[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:
Yineng Zhang
2025-09-21 17:43:50 -07:00
committed by GitHub
parent 0f04a5f428
commit f67d1f45bc

View File

@@ -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