- Repository
- https://github.com/vllm-project/vllm
- Homepage
- https://vllm.ai
- Owner
- vllm-project (Organization)
- Stars
- 94,068
- Forks
- 23,543
- Open issues
- 9,034
- Language
- Python
- License
- Apache-2.0
- Created
- 2023-02-09
- Last push
- 2026-10-18
- Topics
- amd, blackwell, cuda, deepseek, deepseek-v3, gpt, gpt-oss, inference, kimi, llama, llm, llm-serving
- Snapshot
- 2026-10-18
GitHub · #43
vllm-project/vllm
vllm-project/vllm is #43 in this GitHub directory, with 94,068 stars. A high-throughput and memory-efficient inference and serving engine for LLMs