vLLM Blog

blog.vllm.ai

Technical articles, release announcements, model guides, and community updates from the vLLM project.

Popular posts: 1
Total points: 147
HN comments: 54
Rank: #7,667 company

Visit blog.vllm.ai → RSS feedOn Hacker News Jan 2026 – Jan 2026

Systems & Performance 1 AI & Machine Learning 1

Most points Most discussed Most cited Newest

vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep

2026147 points54 comments AI & Machine Learning details

How vLLM reaches 2.2k tokens per second per H200 for DeepSeek-style MoE serving with Wide-EP, async scheduling, dual-batch overlap, disaggregated serving, CUDA