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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Model] Add K-EXAONE-2.0-750B-A37B-DSpark
- [Test] Extend shared tool-parser parity suite to 6 more parsers
- [Bugfix] Reject heterogeneous vocab with local argmax reduction
- [Bug]: EPLB fails to transport E8M0 expert state
- [CI Failure]: PyTorch Fullgraph test_custom_compile_config fails with cudaErrorStreamCaptureInvalidated
- [Perf][Frontend] Optimize DecodeStream priming with a bounded prompt tail
- [Bug]: Structured outputs (response_format/guided_json) crashes the entire engine on the CPU backend — CPUModelRunner inherits GPU-only StructuredOutputsWorker
- [Tracking][Spec Decode] Adaptive DSpark Bring-Up Tracker
- [Bugfix] Gemma4 parser: decode JSON/Python string literals inside containers
- [Perf] Vectorize causal conv1d metadata indices
- Docs
- Python not yet supported