vLLM

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

1.9× faster than LLM Infrastructure this week

7d +0.83% +741 stars in 7d

30d Not tracked yet — first tracked 2026-08-14

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

89,026 → 90,230 stars since Aug 14

★ 90,095 stars 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