A transformer is a deep learning architecture based on self-attention mechanisms, designed to process sequential data in parallel. Transformers are the foundation of modern large language models and are widely used in natural language processing, computer vision, and generative AI.
Low-latency AI engine for mobile devices & wearables
LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.
电子鹦鹉 / Toy Language Model
Legend of Elya — N64 game with a real 819K-parameter transformer running on the VR4300 MIPS III CPU. Zelda-style dungeon, AI NPCs, byte-level inference at 60 tok/s. Built with libdragon SDK.
This library provides a set of functionalities for different type of deep learning (and ML) algorithms in C
Non-bijunctive attention collapse for LLM inference — POWER8 hardware AES (vcipher) + AltiVec vec_perm. Hebbian path selection, cross-head diffusion, O(1) KV prefiltering.
revised version of c2ada (http://c2ada.sf.net/)
Addon for Data support of Communicable State Machine(CSM)
Minimal GPT training and inference implementation from scratch
Экспериментальная трансформерная LLM для локального обучения, инференса и исследований GPU-ядер (PyTorch, Triton, Metal)
cunfyooz is a mEtAmOrPhIc engine implemented in C
Microwave oven transformer spot welder
使用opengl计算着色器实现的transformer (llama2)模型推理。implementation of the transformer (llama2) model,using OpenGL Compute Shader