refinefuture-ai/Qwen3-Smoke
Updated
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
View all activity
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