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
- [CI] Add P2pNccl integration test + rename nixl_integration to pd_integration
- [Perf] Optimize async scheduling redundant copy, 0.9% E2E throughput improvement
- [BugFix] Fix mm_encoder_only init for qwen3 vl moe model
- [Core] Add Helix (Context + Tensor) Parallelism
- [Core] Configurable encoder compute and cache budget
- [RFC]:DeepSeek-R1 Moe offload
- [Bug]: The local deployment achieves about 30% higher accuracy compared to the server deployment.
- [Bug]: GLM-OCR POST bug
- [Bug]: DeepSeek-R1-0528-NVFP4 Missing TRTLLM-GEN kernel (decode) on GB200
- [Usage]: Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
- Docs
- Python not yet supported