diff --git a/python/sglang/srt/models/glm4_moe.py b/python/sglang/srt/models/glm4_moe.py index e3eeb7d10..db8c1c7ce 100644 --- a/python/sglang/srt/models/glm4_moe.py +++ b/python/sglang/srt/models/glm4_moe.py @@ -1281,7 +1281,8 @@ class Glm4MoeForCausalLM(nn.Module): class GlmMoeDsaForCausalLM(DeepseekV2ForCausalLM): - pass + def determine_num_fused_shared_experts(self): + super().determine_num_fused_shared_experts("GlmMoeDsaForCausalLM") EntryClass = [Glm4MoeForCausalLM, GlmMoeDsaForCausalLM]