SGLang is a high-performance serving framework for large language models and multimodal models.
[Intel GPU] Enable sgl-kernel-xpu fused_experts MoE kernel path for GPT-OSS bf16 models. (#22417)
C
Chandrakant Khandelwal committed
1e9eecfa36ce899d27cb2d794a083049ba82d937
Parent: d524f11
Committed by GitHub <noreply@github.com>
on 4/13/2026, 5:45:48 AM