1 views collected around this technical thread.
This article explains Python's @ operator for matrix multiplication, shows basic usage with NumPy, contrasts it with element‑wise *, demonstrates matrix‑vector multiplication, highlights common dimension‑mismatch errors, and provides a concise summary for efficient linear‑algebra calculations.
The article details MNN’s CPU backend dynamic quantization for Transformer‑type models, describing runtime int8 conversion, block‑wise matrix‑multiply optimizations using ARM SMMLA/SDOT and AVX‑512 VNNI, weight‑group and batch‑wise quantization techniques, and reports up to three‑fold speed‑ups on Snapdragon 8 Gen 3.
The article explains how ARMv86’s new SMMLA and BFMMLA GEMM instructions are integrated into MNN to accelerate INT8 and BF16 matrix multiplication, delivering up to 90% speedup over ARMv82’s SDOT and FP16‑FMLA kernels through optimized kernels, tiling, and compatibility handling.
DeepMind’s AlphaTensor, built on AlphaZero and reinforcement learning, automatically discovers novel, provably correct matrix multiplication algorithms that outperform classic methods like Strassen’s, demonstrating how modern AI can automate algorithm discovery and significantly accelerate computations across many fields.
This article describes how the English fluency app leverages deep neural network (DNN) models for real‑time speech scoring on smartphones, detailing offline inference challenges, BLAS‑based matrix‑vector optimizations, sparsity exploitation, cache‑friendly implementations, fixed‑point and NEON acceleration, as well as model compression techniques to improve accuracy and latency.