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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Performance][torch.compile]: FlashInfer Attention + quant fusion performance issue with TP=4
- [Feature]: Qwen3 Omini AttributeError: 'Qwen3OmniMoeProcessor' object has no attribute '_get_num_multimodal_tokens'
- [Bugfix]lora replace_layer support custom op
- [Bug][RL]: Port Conflict
- Starscream Changes to support CPX NPS4
- [Bugfix][offline_inference][data_parallel] Fix race condition in data_parallel by utilizing distributed barrier
- [Feature]: MoE LoRA for quantized models
- Fix tool call id missing issue.
- [Feat][Sched] Support Balance Scheduling
- [Feature]: Add support for fused fp8 output to FlashAttention 3
- Docs
- Python not yet supported