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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Qwen3.6 hybrid model with prefix caching + MTP3 causes tool-call leakage and needle recall failure, while no-MTP path is correct[错误]:
- [Bug]: Responses API null serialization breaks SMG deserialization
- [Installation]: old nccl version in docker container
- [LoRA] Integrate flashinfer MoE LoRA
- Revert "[Platform] Replace `torch.cuda.mem_get_info` with `torch.accelerator.get_memory_info`" (#44825)
- [Bug]: 较高版本 Transformers 与已知 Mindformers YAML 配置冲突,导致 AISBench 测试报错 TypeError: Can't instantiate abstract class MindformersTokenizer
- [Feature]: Support for Keye-VL-2.0-30B-A3B
- fix(security): validate g_idx bounds in CPU WNA16 GPTQ desc_act kernel
- [Bug]: Gemma4 MoE (26B-A4B) aborts with "nanobind::builtin_exception: Expected an MLIR object (got OpResultList)" during CUDA graph capture on H200 (SM90) with FA4
- [RFC]: Implement return indexer topk for sparse attention.
- Docs
- Python not yet supported