AI圈报产品发布 / 更新精选
HPC-Ops × SGLang：腾讯混元开源高性能 Attention、Router GEMM 与 MoE 算子
原始标题：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
内容摘要
腾讯混元开源算子库 HPC-Ops 已集成至 SGLang 主分支，其 Dynamic Attention 与 Fused MoE 在 Hy3 模型上最高降低 TPOT 48.8%。