From 0297773a2f1233643430f81c47814c1101c3526a Mon Sep 17 00:00:00 2001 From: Gao016 Date: Wed, 29 Oct 2025 11:46:44 +0800 Subject: [PATCH] a tiny fix for support deepseek bf16 weights (#12313) Co-authored-by: gaochang --- python/sglang/srt/models/deepseek_v2.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/sglang/srt/models/deepseek_v2.py b/python/sglang/srt/models/deepseek_v2.py index 827e2e96b..d402578e7 100644 --- a/python/sglang/srt/models/deepseek_v2.py +++ b/python/sglang/srt/models/deepseek_v2.py @@ -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: