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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Engine core dies on KV-connector load failure for hybrid-KV models — `_update_requests_with_invalid_blocks` assumes a single KV cache group
- [Bugfix] Keep intermediate prefill chunks mamba-block-aligned with spec decode
- [Bug]: Gemma 4 Finetune won't think
- [Bug]: Integer overflows in merge_attn_states.cu
- [Bugfix][KVConnector][Mooncake] Wire LookupKeyServer/Client close into store teardown
- Preserve tensor dtypes when loading quantized tensorizer models
- [v2 of #45506] EngineArgs CLI plumbing for --sleep-mode-backend
- [Tokenizer] Add batch_split_message tokenizer mode for lossless segmented encoding
- fix: correct line filtering logic in use_existing_torch.py (closes #42363)
- [Bugfix] /sleep endpoint should return idempotent signal when engine already sleeping
- Docs
- Python not yet supported