Designing High-Performance GPU Cores with TileLang: Tensor GEMMs, Fused Softmax, FlashAttention, and Auto-Tuning

TileLang is a high-level domain-specific language in Python for simplifying GPU kernel creation. The guide demonstrates step-by-step implementation of complex tasks: tensor GEMMs, fused softmax, and FlashAttention, where the compiler handles low-level CUDA details.

AI Agent Race on Smartphones: Nubia, StepFun and Honor Compete in Models, Hardware and Apps

Chinese smartphone makers Nubia and Honor, along with AI startup StepFun, are racing to deploy AI agents on smartphones. Nubia integrates StepFun's Step-2 model for on-device voice assistants, while Honor offers its own AI agent platform. The competition spans AI models, hardware acceleration, and application ecosystems.

ByteDance Nubia Technology (努比亚) Honor