JSON for Classic C++

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

The production-scale datacenter profiler (C/C++, Go, Rust, Python, Java, NodeJS, .NET, PHP, Ruby, Perl, ...)

CUDA for MNIST training/inference

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Schedule-Free Optimization in PyTorch

Audio playback and capture library written in C, in a single source file.

Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)

Chronos: Pretrained Models for Time Series Forecasting

(Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints" (https://arxiv.org/pdf/2305.13245.pdf)

Fast and memory-efficient exact attention

CUDA/Metal accelerated language model inference

Easily control Intel p-state driver on Linux

(CVPR 2023) Instance-Aware Domain Generalization for Face Anti-Spoofing

Fourth iteration of my personal website built with Gatsby

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Markdown source for Michael Abrash's Graphics Programming Black Book

Sychronized, streaming Python dictionary that uses shared memory as a backend

A pytorch trainer with a range of choice for backbones, losses, metrics and wandb sweeps.

Techniques for deep learning with satellite & aerial imagery

Omnivore: A Single Model for Many Visual Modalities

A slot map is a high-performance associative container with persistent unique 32/64 bit keys to access stored values.

Tests for all valid opcodes of the 6502 and 65C02 processor

Code-along Examples for the 6502 Assembly Crash Course Video.

Includes additional materials for the following keras.io blog post.