LMSYS:Blog(Chatbot Arena 团队)·· 13 小时前AI 评分55
腾讯混元 HPC-Ops 的 Attention、Router GEMM 与 MoE 算子合入 SGLang 主分支
Blog HPC-Ops × SGLang: High-Performance Attention, Router GEMM, and MoE Kernels from Tencent Hunyuan HPC-Ops is an open-source operator library for LLM inference, deployed in Tencent's large-scale production serving. Its core operators, including Dynamic Attention and Fused MoE, play a critical role ... Tencent Hunyuan AI Infra and the SGLang Team August 7, 2026
AI 导读
腾讯混元 AI Infra 与 SGLang 团队宣布,HPC-Ops 的 Attention、Router GEMM 和 MoE 算子已合入 SGLang 主分支。
来源:LMSYS:Blog(Chatbot Arena 团队) · lmsys.org