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 10 hours ago

refinefuture-ai/SmolVLM2-500M-Video-Instruct-REFFT

wxthon  published a model about 10 hours ago

refinefuture-ai/SmolVLM2-500M-Video-Instruct-REFFT

wxthon  updated a model 3 months ago

refinefuture-ai/Qwen3-Smoke

View all activity

Team members 1