vLLM
vLLM is a high-throughput and memory-efficient inference and serving engine for large language models (LLMs).

Contribute
Become a financial contributor.
Financial Contributions
Top financial contributors
Individuals
$100,000 USD since Jun 2024
$100,000 USD since Aug 2024
$10,000 USD since May 2024
$7,500 USD since Dec 2024
$100 USD since May 2024
$100 USD since Jun 2024
$100 USD since Jun 2024
$25 USD since Jul 2024
$20 USD since May 2024
$20 USD since Jul 2024
$20 USD since Sep 2024
$20 USD since Nov 2024
$20 USD since Jan 2025
$20 USD since Jan 2025
$10 USD since Feb 2025
Organizations
$100,000 USD since Jun 2024
$1,084.9 USD since Jul 2024
$200 USD since Aug 2024
vLLM is all of us
Our contributors 22
Thank you for supporting vLLM.
Simon Mo
Woosuk Kwon
Zhuohan Li
Sequoia
$100,000 USD
Guest
$100,000 USD
SKYWORK AI
$100,000 USD
Dropbox Inc.
$10,000 USD
Kindroid
$7,500 USD
GitHub Sponsors
$1,085 USD
Yotta Labs
$200 USD
Tianle Cai
$100 USD
Rymon Yu
$100 USD

Budget
Transparent and open finances.
$284,695.53 USD
$286,998.53 USD
$2,303.00 USD
$319,354.90 USD
