remove unecessary dual stream token threshold from the rest of models (qwen moe, kimi linear, etc.) (#14337)

2025-12-06 19:57:26 -08:00
parent 91c9c14c28
commit 6d5d76ad97
4 changed files with 0 additions and 8 deletions
@@ -125,13 +125,11 @@ class KimiMoE(nn.Module):
        hidden_states = hidden_states.view(-1, hidden_size)

        shared_output = None
-        DUAL_STREAM_TOKEN_THRESHOLD = 1024

        if (
            self.alt_stream is not None
            and self.num_shared_experts is not None
            and hidden_states.shape[0] > 0
-            and hidden_states.shape[0] <= DUAL_STREAM_TOKEN_THRESHOLD
            and get_is_capture_mode()
        ):
            current_stream = torch.cuda.current_stream()