#attention

2 posts

vLLM × HPC-Ops: High-Performance Attention and MoE Backends from Tencent Hunyuan

Jul 6, 2026·12 min read

How HPC-Ops integrates Hopper-optimized attention and FP8 MoE backends into vLLM for Tencent Hunyuan Hy3, improving mixed-length decode, MoE latency, TTFT, and TPOT on NVIDIA H20.

vLLM Triton Attention Backend Deep Dive

Mar 4, 2026·10 min read

A technical walkthrough of the vLLM Triton attention backend, covering performance-portable paged attention kernels, backend selection, autotuning, CUDA graph behavior, benchmarks, and NVIDIA, AMD, and Intel support.