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 supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Sequence Parallelism and Async TP disabled by default
- [Bug]: vLLM does not support DeepSeek series on RTX PRO 6000/SM120
- [Model] Add ApertusToolParser
- Add FULL CUDA-Graph support for KV Connector path
- [bugfix]:Cannot connect to host when using disagg epd proxy
- [Feature][Bugfix] Support draft model tp any of speculative decode
- Segmented prefill for gapped external KV cache hits
- [MoE][Fix] Fix PPLX CUTLASS FP8 incorrect output with apply_router_weight_on_input
- [V1][Feat] Fail request if FSM fails to advance
- log process name and id
- Docs
- Python not yet supported