A front-end and back-end virtualization framework for the collaborative computing power
最近更新: 19小时前A solution for large model inference, such as DeepSeek, built with full-stack open-source components.
最近更新: 3天前Build a heterogeneous integrated XPU migration capability to achieve AI computing power decoupling and seamless migration of training tasks, supporting scenarios such as AI training fault recovery, service scheduling, and resource integration.
最近更新: 6天前User-space ownership-based memory management component - the underlying infrastructure for heterogeneous memory pooling.
最近更新: 8天前LMCache is an LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios.
最近更新: 10天前The repository used for release of CCF Heterogeneous Programming Competition Problems.
最近更新: 14天前XSched is a preemptive scheduling framework for diverse XPUs (referring to various accelerators, such as GPUs, NPUs, ASICs, and FPGAs) across different brands, generations, and software platforms.
最近更新: 17天前User-space ownership-based memory management component - the underlying infrastructure for heterogeneous memory pooling.
最近更新: 21天前
