vLLM × HPC-Ops: High-Performance Attention and MoE Backends from Tencent Hunyuan
Tencent Hunyuan contributed production-grade high-performance Attention and MoE kernels to vLLM, achieving up to 2.95x attention speedup for mixed-length decode and 1.59x MoE speedup on H20 GPUs, reducing end-to-end latency by up to 24%.
vLLM Blog · Jul 6, 2026