Fix GLM-5 fused shared expert (#18804)

Co-authored-by: FrankMinions <liuchen@shinemo.com>
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
This commit is contained in:
Frank Minors
2026-02-17 03:50:39 +08:00
committed by GitHub
parent 0ff24159a5
commit 1b659bcb08

View File

@@ -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]