vLLM

vLLM is a high-throughput and memory-efficient inference and serving engine for large language models (LLMs).
Collective - Host: opensource - https://opencollective.com/vllm - Code: https://github.com/vllm-project/vllm

Financials

Donations: 4 ($204.30)
Expenses: 5 (-$438.80)
Donors: 4
Spenders: 2

New Projects: 0
New Releases: 4

New Issues: 234
New Pull Requests: 367

Closed Issues: 57
Merged Pull Requests: 106
Closed Pull Requests: 30

Issue Authors: 209
Pull Request Authors: 186
Active Maintainers: 31

Time to close issues: 31.9 days
Time to merge pull requests: 4.4 days
Time to close pull requests: 10.5 days

Commits: 0
Commit Authors: 0
Commit Committers: 0
Additions: 0
Deletions: 0