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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [KVCache] Add Triton software NVFP4 KV cache support
- [MM][Perf] Add PaddleOCR-VL encoder CUDA graph support
- [Bugfix][Model] Fix Qwen3 deepstack buffer device mismatch
- llmd+vllm+mori-ep(intra node wide-ep)+mori-io(write) for 1p1d with dp=ep=8 tp=1
- [Profiler] Get Detailed MultiModal Data Preprocessing Timing Stats
- [Feature]: Support DeepSeek-V4 FIM completion suffix rendering
- [Bug] MooncakeConnector: KV cache data corruption under concurrent PD transfers (batch_transfer_sync_write race)
- LMCache MP external KV cache key omits LoRA identity, allowing cross-adapter KV hits
- [Roadmap] Rust Frontend Feature Parity
- [Bug]: Deployed Qwen3.5-122B-A10B at L20 node 8; after a period of operation, the EngineCore encountered an issue.
- Docs
- Python not yet supported