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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- fix: use 'vllm_' instead of 'vllm:' as prefix for prom metrics name
- [LoRA] Add TMA support to quantized fused_moe_lora kernel
- [DRAFT] pd disagg config for kimi-k2-thinking or deepseek-r1
- [DevEnv][NixOS] Add NixOS development environment with CUDA support
- Add shutdown timeout CLI and changed shutdown function to send SIGTERM to worker processes before SIGKILL
- [Usage]: about the Chinese documents
- [RFC]: How will vLLM adapt to more diverse KVCacheSpecs?
- [Bug]: When loading LoRA via load_lora_adapter, the inference becomes very slow with high CPU usage
- [Performance][CPU Backend]: 40% Performance drop observed on AWQ models from version 0.12.0 vs version 0.11.2
- [New Model]: Add support for telechat3 model
- Docs
- Python not yet supported