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 supported10 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Hardware][TPU][V1] Multi-LoRA implementation for the V1 TPU backend
- VLLM for Qwen 2.5 72B produces all !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! outputs, regardless of prompt given GPTQ 4 bits quantization
- [V1][PP] Continue scheduling prefill chunks
- [Core][Feature] Input metadata dump on crash
- [Core] Add Additional Metrics to vLLM Server
- [Core][AMD] Migrate fully transparent sleep mode to ROCm platform
- [V1] Feedback Thread
- add support for AMD MI25/50/60
- Implements dual-chunk-flash-attn backend for dual chunk attention with sparse attention support
- [Frontend] Disaggregate prefill decode with zmq
- Docs
- Python not yet supported