Skip to content

GitLab

Unverified Commit 760286e3 authored by Yuxuan Zhang's avatar Yuxuan Zhang Committed by GitHub
Browse files

use fp32 for e_score_correction_bias in GLM-4.5 (#8729)

parent 3435a24e
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
python/sglang/srt/models/glm4_moe.py
View file @ 760286e3
...@@ -343,7 +343,7 @@ class Glm4MoeGate(nn.Module): ...@@ -343,7 +343,7 @@ class Glm4MoeGate(nn.Module):
torch.empty((config.n_routed_experts, config.hidden_size)) torch.empty((config.n_routed_experts, config.hidden_size))
) )
self.e_score_correction_bias = nn.Parameter( self.e_score_correction_bias = nn.Parameter(
torch.empty((config.n_routed_experts)) torch.empty((config.n_routed_experts), dtype=torch.float32)
) )
if _is_cpu and _is_cpu_amx_available: if _is_cpu and _is_cpu_amx_available:
self.quant_method = PackWeightMethod(weight_names=["weight"]) self.quant_method = PackWeightMethod(weight_names=["weight"])
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment