vllm-project/vllm

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

59.4

Score

84,776

Stars

18,644

Forks

0.0

Trend

Details

Language
Python
License
Apache-2.0
Category
AI/ML
Open Issues
5484
Contributors
0
Archived
No

Security

OpenSSF Score
N/A
Dependency Risk
Unknown
Activity Health
Unknown

Topics

amdblackwellcudadeepseekdeepseek-v3gptgpt-ossinferencekimillamallmllm-servingmodel-servingmoeopenaipytorchqwenqwen3tputransformer