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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Scheduler] Fix CUDA crash caused by stale async placeholder tokens in speculative decoding
- nixl refactor: new transfer design
- [MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK
- [Examples] Resettle Disaggregated examples.
- [GDN] Enable FI Blackwell GDN prefill kernel
- [Bugfix] Don't reserve `max_tokens` strictly for chat completions
- [Bugfix] Fix Qwen3 reasoning parser: raw text tags, transition loss, end detection, token counting, withhold recovery
- [TurboQuant] Share decode scratch workspace across layers
- [Perf][Kernel] BF16 input support for persistent topK - DeepSeekV4
- [torch.compile] Add hierarchical module trace dump for FX graphs
- Docs
- Python not yet supported