Tencent Hunyuan open-sources production inference kernels and integrates them into SGLang
HPC-Ops × SGLang:腾讯混元开源高性能 Attention、Router GEMM 与 MoE 算子
Tencent Hunyuan open-sourced its production-proven Attention, Router GEMM, and MoE kernels as HPC-Ops and merged them into SGLang's main branch. On H20, Hy3-FP8 TPOT dropped by up to 48.8%; the Attention kernel averaged 2.25× faster than FlashInfer/FlashAttention, and Router GEMM ran 1.30–3.22× faster than FP32 cuBLAS with lower error. H200 validation passed, with the MoE kernel hitting 4.21× over Triton on Qwen3.
Why it matters: Tencent Hunyuan open-sourced Attention, Router GEMM and MoE operators honed in production and merged them into the SGLang main branch, offering concrete fixes for GPU idle time caused by varying request lengths in MoE inference.