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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Mypy] Fix adjust_request typing
- Enable eagle3 for MiniMax M2
- [Feature]: Add Rotorquant support
- [Speculative Decoding] Add DFlash speculators config parsing
- [KVConnector]: Add kv_connector_class_name to resolve name conflict with built-in connectors
- [Bugfix] Preserve torch profiler summary output on CPU
- Revert "[Bugfix] Fix DeepGemm E8M0 accuracy degradation for Qwen3.5 FP8 on Blackwell" (#38083)
- [Bugfix]Fix incorrect KV cache log output
- [torch.compile]: Disable Sequence Parallelism (SP) for piecewise compilation
- [Transformers v5] Base model and LoRA used in test has incorrect `tokenizer_config.json`
- Docs
- Python not yet supported