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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Torch.AcceleratorError: CUDA error: no kernel image is available for execution on the device
- [Bug]: class Request and block_hasher has cirular reference, may cause memory leak.
- [Usage]: suffix decoding
- [bugfix] add hasattr check for drafter in _build_attention_metadata with PP
- Preserve original class name in CachedTokenizer for HuggingFace compatibility
- [Feature]: Add support for NVIDIA Jetson AGX Thor
- [Bug]: Can run Speculative decode with PP >2?
- [Bug]: Streaming output issue in vLLM v0.10.2
- [Bug]: vllm+ray:vllm serve DeepSeek-V3.2V-AWQ ERROR.
- [Bug]: Failed to capture CUDA kernel data and GPU memory data when running vllm with tensor_parallel_size=1
- Docs
- Python not yet supported