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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature][Responses] Support GPT-OSS output logprobs
- [Bug]: Mooncake Store split-load failures omit unattempted KV blocks from invalidation
- [Bug] Responses API silently drops a leading `developer` message for DeepSeek V4 when reasoning is enabled and no tools are set
- [Cleanup][Attention] Remove unused slot_mapping field from 5 backend metadata classes
- [Bugfix][Multimodal] Fix Qwen3-VL EVS M-RoPE positions for the outer vision marker and chunked prefill
- [Bug]: Video pruning (EVS / VidCom2): M-RoPE positions are wrong for chunks that start inside a Qwen3-VL video placeholder
- [Kernel][MoE] Add the NIXL EP v2 elastic EP all2all backend
- [WIP] [MoNe] [Compressed-Tensors] MoNe support for CT
- [ROCm] Enable eager PCP for DeepSeek-V4.1-Flash
- [Doc] Make agent test rules defaults with stated exceptions
- Docs
- Python not yet supported