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
- [Tool Calling][Bugfix] Schema-aware type correction various small fixes
- [Docs] Add PR checklist skill for coding agents
- [Security] Bound torchaudio resample kernel size
- [ROCm][Perf] Shard DSA prefill indexer rows across TP ranks
- [Prototype][MRV2] Stage DeepSeek decode tokens for imbalanced DBO graph replay
- [Bugfix][Pooling] Restore GTE-Qwen2 EOS handling on Transformers v5
- [Bugfix] Fix FlashInfer all_reduce backend selection
- XPU: --cpu-offload-gb (UVA) does not reduce peak device memory for compressed-tensors WNA16 MoE models
- [Bugfix][KV Offload] Bound unanswered P2P lookup waits
- [Spec Decode] Draft within the requests' top-k / top-p support
- Docs
- Python not yet supported