a tiny fix for support deepseek bf16 weights (#12313)

Co-authored-by: gaochang <gaochang@U-19PX2WQ1-0350.local>
2025-10-28 20:46:44 -07:00
parent 587deb15a7
commit 0297773a2f
1 changed files with 1 additions and 1 deletions
@@ -2998,7 +2998,7 @@ class DeepseekV2ForCausalLM(nn.Module):
            disable_reason = "Only Deepseek V3/R1 on NV-platform with capability >= 80 can use shared experts fusion optimization."
        elif get_moe_expert_parallel_world_size() > 1:
            disable_reason = "Deepseek V3/R1 can not use shared experts fusion optimization under expert parallelism."
-        elif self.quant_config.get_name() == "w4afp8":
+        elif self.quant_config and self.quant_config.get_name() == "w4afp8":
            disable_reason = "Deepseek V3/R1 W4AFP8 model uses different quant method for routed experts and shared experts."

        if disable_reason is not None: