diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu index 303d67e4c..c72419613 100644 --- a/ggml/src/ggml-cuda/ggml-cuda.cu +++ b/ggml/src/ggml-cuda/ggml-cuda.cu @@ -3164,7 +3164,7 @@ static bool ggml_cuda_match_moe_weighted_reduction( const int n_expert_used = (int) weighted->ne[1]; const int64_t n_tokens = weighted->ne[2] * weighted->ne[3]; - if (n_expert_used < 2 || n_expert_used > MOE_WEIGHTED_REDUCTION_MAX_EXPERTS || n_tokens <= 0) { + if (n_expert_used < 2 || n_expert_used > MOE_WEIGHTED_REDUCTION_MAX_EXPERTS) { return false; }