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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Use proper ternary in InProcessCoreClient.get_output
- [BugFix] Initialize model_config for Qwen3-VL MoE
- [serving] Upgrade unknown-field log from DEBUG to WARNING in OpenAIBaseModel
- [Bugfix] Refresh forward-context tensors before FULL CUDA graph replay
- Fail closed on missing speculative draft probabilities
- [Misc] Add unit test for round_int8 INT8 Quant kernel
- [Feature] Support MTP speculative decoding for Bailing hybrid models
- fix: improve health check robustness for EngineDeadError and other exceptions (closes #42363)
- [Bugfix] Avoid full prompt logprobs materialization in V1
- [Bug]: vllm start with TieringOffloadingSpec mmap_obj error
- Docs
- Python not yet supported