vllm-project/vllm - 75.2k Stars · Global Rank #181

Nearby Ranks

#171d2l-zh
#172LeetCodeAnimation
#173PayloadsAllTheThings
#174Font-Awesome
#175elasticsearch
#176Stirling-PDF
#177Best-websites-a-programmer-should-visit
#178json-server
#179lazygit
#180Ventoy
#181vllm
#182nest
#183PaddleOCR
#184lobehub
#185union
#186awesome-public-datasets
#187redis
#188awesome-vue
#189tesseract
#190codex

Global Rank#181Apr 4, 2026

Global Rank#181Apr 4, 2026

since Feb 2023

vllm-project/vllm

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

PythonApache-2.0

75.2k

15.1k

2.5k

Weekly

115stars

·

121pushes

Stars

Contributors

New Stars

New Pushes

Forks

star-history.com

vllm-project/vllm

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

75.2k

Stars

#181

Global Rank

15.1k

Forks

2.5k

Contributors

Python

Language

Apache-2.0

License

Feb 9, 2023

Created

This Week

New stars+115

Pushes121

Issues closed24

Topics

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