diff --git a/qwen3_6_scripts/qwen3_5.py b/qwen3_6_scripts/qwen3_5.py index eeda4793..aee361aa 100644 --- a/qwen3_6_scripts/qwen3_5.py +++ b/qwen3_6_scripts/qwen3_5.py @@ -1611,7 +1611,7 @@ class Qwen3_5MoeSparseBlock(nn.Module): # Source: xllm/core/kernels/cuda/moe/moe_topk_softmax_kernels.cuh if _USE_COREX_MOE_TOPK_SOFTMAX: topk_weights, topk_ids = _corex_moe_topk_softmax.moe_topk_softmax( - router_logits, self.top_k, True) + router_logits.float(), self.top_k, True) topk_ids = topk_ids.to(torch.int64) topk_weights = topk_weights.to(hidden_states.dtype) else: