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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Support sparse in-place weight updates in weight transfer API
- [Doc] Add pip equivalent for CUDA-specific wheel installation
- [torch.compile] E2E correctness testing for fusions
- [ROCm][Bugfix] add swiglustep triton fallback
- Use physical device id for get_device_uuid
- [PD][NIXL] refine wording for #38935
- fix: exclude MTP layers from MoE quantization to fix KeyError with moe_wna16
- [Bugfix] Reserve distributed init socket to avoid port conflicts
- [Bug]: /v1/responses: Protocol drift and malformed tool aggregation breaking official OpenAI SDK compatibility
- [V1][Metrics] Add MLA attention metrics for DeepSeek MFU estimation
- Docs
- Python not yet supported