RefineFuture.AI

AI & ML interests

A new approach of running LLM/LMs' inference/training on GPU/NPU backends through C++ implementation and compile for High-Performance and Easy-to-Use

Recent Activity

wxthon  updated a model about 15 hours ago

refinefuture-ai/LFM2.5-8B-A1B-REFFT

wxthon  published a model about 15 hours ago

refinefuture-ai/LFM2.5-8B-A1B-REFFT

wxthon  updated a model 7 days ago

refinefuture-ai/GLM-4.6V-Flash-REFFT

View all activity

Team members 1