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 supported23 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Memory Leak Issue in Load Testing Scenario
- [Feature][CUDAGraph]: Audit CUDAGraph support in attention backends
- Feature/deepseek v31 lora support
- [Bug]: AMD ROCM6.4.2 No module named 'amdsmi' No module named 'libtpu' No module named 'intel_extension_for_pytorch'
- [Spec Decode] Add Tensor Parallel Ngram decoding
- [Draft][v1] Add cross-attn support for FlexAttention backend
- [GPT-OSS] Persistent Masked Activation Kernel
- [Bug]: vLLM failure (ray.exceptions.RayChannelTimeoutError) observed since v0.10.2, with tp=8, pp=4
- [Bugfix] Respect ignore list for NVFP4/BF16 mixed MoE checkpoints
- [RFC]: Tracking Spec Decode Support
- Docs
- Python not yet supported