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 cache-aware admission ordering
- [ROCm][RDNA3] Fix W4A16 split-K accuracy and determinism
- [Core] Apply prefill_schedule_interval outside data parallelism
- Fix DSML leaking for DeepSeek-v4 models
- [Bugfix] Don't let a structured-output request sample from an unmasked row
- [Core] Add XPress speculative decoding method
- [Bugfix][Multimodal] Honor modality-scoped mm_processor_kwargs in every model that reads them
- [Bug]: Qwen3.8-Flash-Next: greedy decoding is non-deterministic from persistent_topk in prefill when prompt length nears indexer_budget (sm121/GB10)
- [Kimi-K3] Add FlashInfer speculative KDA backend
- [MoE] enable all2all fi_one_sided by default only for GB200/GB300
- Docs
- Python not yet supported