EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Reorder loop in shared expert weight loading (#5719)

Browse Source
This commit is contained in:
Ke Bao
2025-04-26 08:27:42 +08:00
committed by GitHub
parent 269c457e05
commit c3948ba67e
2 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
python/sglang/srt/models/deepseek_nextn.py
View File

@@ -215,11 +215,11 @@ class DeepseekV3ForCausalLMNextN(DeepseekV3ForCausalLM):
"up_proj.weight_scale_inv",
]
names_to_remove = []
for num_repeat in range(self.n_share_experts_fusion):
for suffix in suffix_list:
shared_expert_weight_name = (
f"model.layers.0.mlp.shared_experts.{suffix}"
)
for suffix in suffix_list:
shared_expert_weight_name = (
f"model.layers.0.mlp.shared_experts.{suffix}"
)
for num_repeat in range(self.n_share_experts_fusion):
weights_list.append(
(
f"model.layers.0."
@@ -229,7 +229,7 @@ class DeepseekV3ForCausalLMNextN(DeepseekV3ForCausalLM):
weights_dict[shared_expert_weight_name],
)
)
names_to_remove += [shared_expert_weight_name]
names_to_remove += [shared_expert_weight_name]
weights = [w for w in weights_list if w[0] not in names_to_remove]
# Params for weights, fp8 weight scales, fp8 activation scales

12
python/sglang/srt/models/deepseek_v2.py
View File

@@ -1650,11 +1650,11 @@ class DeepseekV2ForCausalLM(nn.Module):
desc=f"Cloning {self.n_share_experts_fusion} "
"replicas of the shared expert into MoE",
):
for num_repeat in range(self.n_share_experts_fusion):
for suffix in suffix_list:
shared_expert_weight_name = (
f"model.layers.{moe_layer}.mlp.shared_experts.{suffix}"
)
for suffix in suffix_list:
shared_expert_weight_name = (
f"model.layers.{moe_layer}.mlp.shared_experts.{suffix}"
)
for num_repeat in range(self.n_share_experts_fusion):
weights_list.append(
(
f"model.layers.{moe_layer}."
@@ -1664,7 +1664,7 @@ class DeepseekV2ForCausalLM(nn.Module):
weights_dict[shared_expert_weight_name],
)
)
names_to_remove += [shared_expert_weight_name]
names_to_remove += [shared_expert_weight_name]
weights = [w for w in weights_list if w[0] not in names_to_remove]
# Params for weights, fp8 weight scales, fp8 activation scales