Havuz

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a plat

Transformers for decision models: fine-tune, load and serve calibrated decsion-model on any Hugging Face model.

A moddable training framework for pre-training ablations.

This repo is a alternative solution for standard self-attention. It uses tree routing with learnable functions for cheaper self-attention wh

Autonomous AI trading system powered by Kronos. Forecasts markets, builds portfolios and paper-trades automatically with GitHub Actions.

Interactive desktop app with 51 labs covering ML fundamentals, transformers, RAG, agents, fine-tuning and quantization and more.

由 AI 自动完成 AutoDL 实例开关机的 Claude Code skill，含空闲自动关机、预算核对与用量记账

Guía gratuita de IA generativa avanzada en español (311 págs.): Transformer, post-entrenamiento, inferencia, GPU, difusión, agentes, segurid

Stanford CS336《从头构建大语言模型》2026 中配版：18 篇中文技术博客 + 19 篇「图-字幕」原始文稿，基于 video2blog-skill 整理。

Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭

A fancy NVIDIA GPU monitor for the terminal. One Python file, no dependencies.

Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security

iPAS AI 應用規劃師（中級）考綱教科書 v0.3 開源版（含三冊完整教材、219 題模擬題、300 題官方試題解析索引與 PDF 編譯工具）

7 Days to Die Trainer 2026: Survival Stats and Inventory Editor Guide

Hardware-aligned latent deliberation framework decoupling System 2 continuous reasoning from System 1 autoregressive decoding.

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an

High-performance CUDA inference engine for Qwen models, written from scratch in C++/CUDA

Ultimate 7 Days To Die Survival Stats Editor & Item Modifier 2026

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning

AuK, tek bir doğal dil talimat arayüzüyle konuşma üretimi ve düzenleme görevlerini gerçekleştiren açık ağırlıklı bir speech modelidir.

Neden yükseliyor · Yeni yayımlanmış bir model olarak kısa sürede 1308 yıldız almış; son 28 gündeki 30 commit ve 5 farklı yazar da aktif geliştirmeye işaret ediyor. README ayrıca vLLM-Omni, SGLang-Omni ve audio.cpp desteğini, modelin farklı inference ekosistemlerine taşınmasını sağlayan somut ilgi göstergeleri olarak listeliyor.

A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)

Ground Truth: A working developer's path into AI and machine learning, with interactive explanations, reproducible Python labs, and practica

Namaste AI — Free handwritten notes and study material covering AI concepts from the Namaste AI course. Explore the history of AI, neural ne

Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from

An optimized handwritten digit recognition model delivering exceptional accuracy, high-speed performance, and compatibility with low-end har

Cooking AGI / AGI 大锅烩 · Bilingual (English / 中文) ML & LLM notes with worked examples, step-by-step figures and coding practice. Free to read

AI-powered fake news detection system with multiple ML models and explainability.

AI-powered real-time object detection, tracking, and video intelligence platform using YOLO and computer vision.

kimi-k3-in-c, Kimi K3 modelinde inference çalıştırmayı hedefleyen bağımlılıksız bir C99 motorudur.

Neden yükseliyor · 57 günde 8.683 yıldız alması ve Kimi K3'ü 8 GB RAM'li CPU'da çalıştırma iddiası dikkat çekiyor; ancak son 28 gündeki 12 commit'in tek yazardan gelmesi, ilginin bağımsız teknik doğrulama veya geniş katkıcı tabanıyla desteklendiğini göstermiyor.

Build and train a mini Kimi K3 from scratch — a pure-PyTorch playground from a custom 88M model to 2T-scale LLM profiles.

Compose neural architectures as typed, executable graph cards with two-way PyTorch sync, step-by-step local execution, and a constrained AI

A mental-model-first field guide to Audio AI — from raw waveforms to production voice systems. Covers ASR, TTS, audio classification, Transf

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

A refined, premium landing page for Tech Alpha, a modern AI startup brand built to showcase services, projects, portfolio work, and founder

Practical Codex workflows for research, academic writing, app development, general planning, and technical operations.

100 days, 100 sources: a daily public learning log of modern AI - LLMs, agents, RAG, fine-tuning, MLOps and more. Daily on Threads, X, and B

Supertonic-ZH — fast on-device Mandarin TTS (pure ONNX). Now with streaming synthesis for real-time dialogue (low first-audio latency, barge

A practical Generative AI engineering lab exploring LLM foundations, tokenization, deployment strategies, and real-world AI system design.

CPU-first, eager-execution tensor/autograd runtime and LLM inference engine written in pure Zig

A stateful AI Intrusion Prevention System (IPS) that reassembles TCP packet fragments in sequence order and uses PyTorch deep learning model

Tenstorrent backend plugin for vLLM.

Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → paralleli

Voynich Manuscript Decoded: Elu-Sinhala Phonetic Transcription & Vocabulary Toolkit 2026

Comprehensive illustrated notes for Stanford CS336 (Spring 2025) — Language Modeling from Scratch. Live: qihongruan.github.io/cs336/

[ECCV 2026] WarpI2I: Image Warping for Image-to-Image Translation.

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。