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
- [Bugfix][Core] Validate sampling param size limits before reaching EngineCore
- [Bugfix][Model] Fix padding isolation in FunASR adaptor attention
- [Bugfix][Frontend] Accept list-form function_call_output in Responses API
- [Bugfix] Ignore empty projected KV-cache groups in PP
- [Bugfix] Intersect per-worker KV cache layout support
- [SpecDecode] Support Sequence-Length-Based Dynamic Speculative Decoding (`num_speculative_tokens_per_seq_len`)
- [Bugfix][KV Connector] Add error tracking for failed LMCache operations
- [ROCm] Avoid DSpark placeholder shared vocab allocations
- [Bugfix][Speculative Decoding] Fix Gemma4 MTP hidden-state buffer sizing
- [Metrics][LoRA] Publish LoRA load events and expose loaded adapters in metrics
- Docs
- Python not yet supported