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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix authentication bypass on /inference/v1/generate
- [WIP][Kernel] Fuse QK RMSNorm AR + RoPE for MiniMax M2
- [Model] Support for Zyphra ZAYA1 models
- fix(model_loader): deterministic suffix mapping for Gemma4 MoE quantization
- [kv_offload]: Add request_finished method to OffloadingManager and decouple store policy
- [Model] Support MOSS-VL
- [Scheduler] Optimize priority queue removals with lazy deletion and batch rebuild
- [RFC]: Add DeepStream as a video loader backend for GPU-accelerated Video decode
- [Bug]: ValueError when CUDA_VISIBLE_DEVICES is a MIG device UUID
- [Bug]: Engine crashes on startup with 'DeepGEMM backend not available' for standard bf16 models on H100
- Docs
- Python not yet supported