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
- fix: ensure EngineDeadError uses correct message and suppresses context properly (closes #42363)
- [Bug]: NixlPushConnector — decode-side KV blocks of an aborted remote-KV load are never reclaimed when the prefill node never reports completion (KV cache leak)
- [Bugfix] Handle missing req_id in `update_from_output()` with PP + tool-calling
- [Core][Model] State-Aware Monolingual Constraints for DeepSeek-R1 (V1)
- [security] fix(lora): contain filesystem resolver paths
- [Kernel] ReplaySSM opt-in AR decode for Mamba2 (#46187)
- [Doc] Clarify prefix caching metrics and APC verification workflow
- fix(reasoning): guard rfind in ernie45 streaming </response> branch
- [Bug]: PP2 + tool calling KeyError in scheduler.py: req_id missing from req_id_to_index
- [Rust Frontend] Support `--max-log-len`
- Docs
- Python not yet supported