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
- [MM][Gemma4] Support `max_soft_tokens="auto"` to avoid wasting the vision budget on small images
- Gfx1250 wip rebase test
- [WIP] Support ViT full CUDA graph for Kimi K2.5
- docs: remove outdated LD_PRELOAD instructions [CPU-Backend]
- [Model] Add LoRA support for GteNewModel, NomicBertModel, and XLMRobertaModel
- [quant][autoround]Refactor INC quantization into package with INCScheme orchestrator
- [Bug]: vllm does not use all of the available RAM
- [Bug]: Unblock PyTorch C++20 Migration
- [Bug]: Buffer overflow when allocating memory error on Qwen3.5-122B-A10B-GPTQ-Int4 and NVFP4
- [Bug]: Gemma-4 + DFlash unservable on Ampere — non-causal + head_dim=256 has no compatible attention backend
- Docs
- Python not yet supported