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 5 days ago
refinefuture-ai/Qwen3-1.7B-REFFT
wxthon  published a model 5 days ago
refinefuture-ai/Qwen3-1.7B-REFFT
wxthon  updated a model 5 days ago
refinefuture-ai/Qwen3-0.6B-REFFT
View all activity

refinefuture-ai 's datasets

None public yet