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
- [Bench] Add Triton NVFP4 GEMM
- [Feature]: Add LORA Model Name in Open Telemetry
- [Bug]: This flash attention build does not support tanh softcapping: gemma-2-2b-it on H100 NVL
- [Usage]: Problem with concurrency in encoder-based embedder serving with V1 Engine
- [RFC] Default no plugin loading
- [Bug]: Qwen 3 VL 30bA3 Flash Attention head dim
- add a warmup mode in CUDAGraphMode
- Simplify vLLM deployment on AWS with new Ansible playbooks and step-by-step instructions & video guide
- [Qwen3-Next][Perf][Attention] Replace torch.zeros with torch.empty to reduce overhead
- [Bug]: GPU VRAM continuously increase during Qwen3-VL usage over days until OOM
- Docs
- Python not yet supported