All

2 repositories

nvllm
Public
(Experimental) A high-throughput and memory-efficient inference and serving engine for LLMs with a optimized GB10 kernel
nvidia cuda-kernels cutlass
nvidia cuda-kernels cutlass local-inference vllm llm-inference qwen paged-attention self-hosted-ai gb10
Python
•
Apache License 2.0
•16k•6•0•0•Updated Apr 25, 2026Apr 25, 2026
nvfp4-Collection
Public
Collection of models ready for GB10
Apache License 2.0
•0•0•0•0•Updated Apr 21, 2026Apr 21, 2026

ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.