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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [WIP][Core/DBO][4/N] Support alternate low-latency schedule
- [Spec Decode] Add Tensor Parallel Ngram decoding
- [Bug]: Cuda invalid device ordinal error since v0.11.0 with tensor-parallel-size 2 with 2xH100
- [Misc] [CI/Build] PTX Warning
- [Draft][v1] Add cross-attn support for FlexAttention backend
- [Bug]: deploying Qwen3-VL-30B-A3B on AMD MI308X GPU, failed to start with worker process dying unexpectedly after loading weights
- [GPT-OSS] Persistent Masked Activation Kernel
- [Bug]: vLLM failure (ray.exceptions.RayChannelTimeoutError) observed since v0.10.2, with tp=8, pp=4
- [Kernel] Support attention sinks in vLLM
- [Bug]: Multi-node Multimodal Inference Fails with V1 Engine: `RayChannelTimeoutError` and `EngineDeadError`
- Docs
- Python not yet supported