vLLM

A high-throughput and memory-efficient inference and serving engine for LLMs

Growing steadily this week

7d +0.51% +472 stars in 7d

30d +2.2% +2,011 stars in 30d

90d Not tracked yet — first tracked 2026-08-14

89,026 → 93,918 stars since Aug 14

90,095 Stars 23,438 Forks 8,902 Open issues

Timeline

💬 1 Hacker News discussion

HN vLLM v0.28.0 Aug 29, 2026 108 pts

View on GitHub ↗ Visit site ↗

amd blackwell cuda deepseek deepseek-v3 gpt gpt-oss inference kimi llama llm llm-serving model-serving moe openai pytorch qwen qwen3 tpu transformer