vLLM:
github.com/vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
https://github.com/vllm-project/vllm
Project activity
New Projects: 0
New Releases: 0
New Issues: 0
New Pull Requests: 0
Closed Issues: 0
Merged Pull Requests: 0
Closed Pull Requests: 0
Issue Authors: 0
Pull Request Authors: 0
Active Maintainers: 0
Time to close issues:
N/A
Time to merge pull requests:
N/A
Time to close pull requests:
N/A
Commit Stats
Commits: 0
Commit Authors: 0
Commit Committers: 0
Additions: 0
Deletions: 0
amd blackwell cuda deepseek deepseek-v3 gpt gpt-oss inference kimi llama llm llm-serving model-serving moe openai pytorch qwen qwen3 tpu transformer
Last synced: 7 days ago
JSON representation
A high-throughput and memory-efficient inference and serving engine for LLMs
- Host: GitHub
- URL: https://github.com/vllm-project/vllm
- Owner: vllm-project
- License: apache-2.0
- Created: 2023-02-09T11:23:20.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2025-10-07T20:59:42.000Z (3 months ago)
- Last Synced: 2025-10-07T21:29:27.601Z (3 months ago)
- 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
- Language: Python
- Homepage: https://docs.vllm.ai
- Size: 94.5 MB
- Stars: 59,586
- Watchers: 440
- Forks: 10,552
- Open Issues: 2,988
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- Funding: .github/FUNDING.yml
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Codeowners: .github/CODEOWNERS
- Security: SECURITY.md
- Dco: DCO
-
Funding:
- Github: vllm-project
- Open collective: vllm