Havuz

Distributed LLM inference fabric for heterogeneous local clusters. Features zero-copy SPSC ring buffers, automated tuning, and an OpenAI-com

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

A complete, structured end-to-end roadmap to become a versatile Generalist AI Engineer from Python/math foundations through ML/DL, CV, NLP,

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

🌟 [Survey & Benchmark] A unified taxonomy, geometric framework, and cross-domain benchmark for modern optimizers

PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors

A comprehensive hands-on, AI-first Python curriculum with 80+ interactive Jupyter notebooks for AI Engineers from core basics to LLMs, RAG,

AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation wi

👻 MoEWatch: A lightweight diagnostic and audit library for Mixture-of-Experts (MoE) models in HuggingFace Transformers — the pytest for MoE

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

Train decoder-only language models from scratch with PyTorch, featuring RoPE, RMSNorm, SwiGLU, and SDPA

Custom APRL machine-learning algorithm + a curated ML knowledge base of 923 papers, lectures, and explainers. NumPy classifier/regressor, te

The open-source alternative to Suno and ElevenLabs Music. Natural language music composition, run locally, own everything.

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

AI-powered urban issue detection platform using YOLOv8, React, Node.js, FastAPI, PostgreSQL, and Docker.

A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methodologies, and

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /rend

HackAI Morocco is a 4-day AI hackathon that brings together students from across Morocco for an unforgettable experience filled with innovat

A complete, hands-on journey from Python fundamentals to AI Engineering. Explore Data Analytics, Data Science, Machine Learning, Deep Learni

A modern, hands-on, self-paced course that takes you from your first line of Python to shipping a real AI-powered automation.

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)

AI Agent engineering and quantitative finance knowledge base: source-level architecture analysis, Agent-to-Agent protocol research, runnable

Building an Image-to-Video (I2V) Model from Scratch

Profine automatically profiles and optimizes PyTorch training jobs on real GPUs, delivering measurable speedups and lower GPU costs before t

ParseCrate: self-hosted document processing API powered by Docling and docling-serve. Converts PDF, DOCX, PPTX, HTML, and more to Markdown/J

This repository is a comprehensive, hands on roadmap to Python Mastery and AI Engineering. It is designed to take a learner from the very fo

Lynn 原生 LLM 推理引擎 · W4A8/NVFP4 量化 · 自写 CUDA/Triton kernel · MoE · 投机解码 | Lynn-native LLM inference engine for NVIDIA Blackwell

五引擎语音合成：VoxCPM2 / IndexTTS 2.5 / 2.0 / OpenVoice / Step-Audio-EditX，声音克隆、声音设计、剧本配音、流式生成，中英日韩界面 | Multi-engine TTS (5 engines): voice cloning

OpenSquilla, CLI, Web UI ve chat kanallarında çalışan, farklı LLM sağlayıcılarını ve araç kullanımını ortak bir agent döngüsünde birleştiren bir AI agent yazılımıdır.

Neden yükseliyor · 144 günde 7.059 yıldıza ulaşması ve son 28 günde 268 commit ile 9 farklı yazarın katkı vermesi güçlü ilgi ve kayda değer geliştirme etkinliği gösteriyor. Token maliyeti, model yönlendirme ve farklı kanallarda agent çalıştırma güncel ve somut ihtiyaçlar; ancak bu ölçümler tek başına ürün kalitesini veya benimsenme düzeyini kanıtlamaz.

A narrative walk through 90 years of AI history, paper by paper. 66 chapters from Turing 1936 to Blackwell 2025.

Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune,

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula

SpeakCrate: self-hosted text-to-speech API powered by Kokoro. OpenAI-compatible speech endpoint, 50+ voices across 9 languages, streamed aud

AI crypto trading bot with deep neural network (84.9% accuracy, 25 coins). BiLSTM + Attention trained on GPU. Bybit, Binance, OKX, Gate.io.

AI Image Generator is a powerful and user-friendly desktop application designed to help creators produce stunning, high-quality artwork, pho

🛡️ A modern, AI-powered WAF with visual forensic playback via rrweb. Protect your web apps with LLM-driven threat detection, real-time visua

A curated collection of AI learning materials

Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

A free, open GenAI curriculum built from scratch. Start from zero, build real projects, and work your way up to production AI systems.

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without ca

🌟 推理王国：关于 AI 推理机制的思想实验手册。从信息论、符号逻辑与表示学习出发，系统剖析大模型“智能”的本质。

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression wit

Readable implementation of Mamba 3 SSM model

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p