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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core] Add container snapshot configuration and Worker lifecycle hooks (1/3)
- [Bugfix][CUDA] Reject fp8_inc KV cache dtype during config validation
- [Bug][CPU][Spec Decode]: --use-fp64-gumbel silently ignored in CPU recovered-token sampling (inv_q downcast to fp32); in-code comment claims otherwise
- [CI][Refactor] Comprehensive `AiterExperts` test coverage and possible split
- [Bugfix][XPU] Disable the static Triton launcher for UVA
- [Model] Enable tower/connector LoRA token counts for Phi-4-multimodal
- [Bugfix][Frontend] Stop double-encoding tool call arguments
- [Bugfix][Frontend] Apply model-default reasoning parser in GPU-less render server
- [Logging] Log KV cache block pool size and per-group blocks per request
- [WIP][Model] Validate weight mapping in model initialization tests
- Docs
- Python not yet supported