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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- feat: add requires_token_ids interface for sampling params
- Optimize fused MoE LoRA intermediate buffers and Triton indexing
- Initial structural_tag support for tool calling
- [Feature]: NVFP4 KV Cache Support
- [Frontend] Add encrypted_content to reasoning items for round-tripping
- fix(tool_parser): filter whitespace-only content before tool_call
- [Bugfix] Pass in missing tp_size to get_port_offset() for MORI IO Connector
- [misc] remove the magic number in _set_cudagraph_sizes function
- [Bug][XPU]: Failed to serve w4a16 Qwen3 VL MoE on Intel Arc Pro B60
- [Roadmap] vLLM Roadmap Q1 2026
- Docs
- Python not yet supported