LTSLegendary
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
- Owner
- vllm-project (organization)
- Stars
- Stars: 96,179
- Forks
- Forks: 24,329
- Language
- Python
- License
- Apache-2.0
- Created
- 2023
- Topics
- gptllmpytorchmodel-servingtransformerllm-servinginferencellamaamdcuda
- Tier
- LTS (20,000 ★ and up) What this tier means
More repos by vllm-project
All 20 repos by vllm-project- vllm-project/vllm-omniStars: 7,503PythonStable
- vllm-project/semantic-routerStars: 6,385GoStable
- vllm-project/aibrixStars: 5,177GoStable
- vllm-project/llm-compressorStars: 3,941PythonRC
- vllm-project/vllm-ascendStars: 3,040PythonRC
- vllm-project/production-stackStars: 2,705PythonRC
Nearby in Python
All Python repos- karpathy/autoresearchStars: 99,125PythonLTS
- nvbn/thefuckStars: 97,938PythonLTS
- hacksider/Deep-Live-CamStars: 97,552PythonLTS
- 3b1b/manimStars: 96,027PythonLTS
- sherlock-project/sherlockStars: 95,454PythonLTS
- odysseus-dev/odysseusStars: 94,966PythonLTS