vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported23 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Vulkan support
- [V0 Deprecation] [P/D] Move `kv_connector/v1` to `kv_connector` (2/2)
- [Feature]: add some pre-built CPU-only wheels for basic testing
- [Feature Request]: Per-rank log files (especially per-actor for Ray)
- Add Vectorguard Tokenizer: Encrypted Token Streams for Secure AI Inference
- [Feature]: FlexAttention + encoder_decoder support
- [Bug]: qwen3 next fp8 failed on 4 * L40s, EOFError
- [Bug]: xgrammar cleanup leakage
- [Frontend][gpt-oss] Support all MCP servers for gpt-oss
- [Usage]: Does vllm support use TokensPrompt for Qwen3VL model
- Docs
- Python not yet supported