Havuz

GleamLM大语言模型全栈训练平台——核心代码用 PyTorch 从零实现，最低仅需 12GB 消费级显卡即可完整训练，另有一套工业代码与手写实现消费同一份数据逐层对照。模型训练支持CLI和可视化训练。

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

Open-source Environment toolkit of claw-like agents, support task/harness generation and evaluation

Learn Agentic AI, Deep Learning, Agentic Engineering, RAG and Multi-Agent Workflows.

Agentic AI platform transforming passive CCTV into proactive railway safety intelligence. Real-time behavioural detection (suicide risk, pic

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware

A self-hosted studio for generating images, video, and audio with diffusion models.

Streamline AI Workloads on Kubernetes: Universal Python SDK Guide 2026

🚀 Engram-PEFT: An unofficial implementation of DeepSeek Engram. Inject high-capacity conditional memory into LLMs via sparse retrieval PEFT

This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind

a LLM inference engine to run on consumer hardware

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

Static reproducibility checks, experiment replay, and verification for ML pipelines.

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

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

A tiny language model that talks like a house cat named Miso.

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

Recomputation-free, context-independent KV caching for large language models

Reproducible OpenEnv-compatible reinforcement-learning environments for social-media integrity moderation.

Unofficial fairseq-free PyTorch implementation of UTMOS (v1, 2022), matching the original system.

One GPU. Full LLM workflow. Real benchmarks. No cloud required.

AI-powered deepfake detector that classifies uploaded face images and videos as Real or Fake with confidence scores. Full-stack app built wi

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

Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.

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

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

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

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

Taiwanese Hokkien (Taigi) speech-to-text transcriber - MediaTek Breeze-ASR-26 with faster-whisper, tuned for RTX 3050 4GB low-VRAM GPUs. Gra

AI watermark removal built for Apple Silicon. SynthID-class pixel regeneration, visible vendor labels and provenance metadata, with every pi

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

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

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matry

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

[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

Pyramis-L3D: hierarchical sparse attention research prototype (code only; weights on Hugging Face)

Local text-to-speech: 28 voices, 10 languages, voice cloning, SDKs for Python, Swift, Go, Rust and TypeScript

🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit

A desktop-native Windows system tray Telegram bot that monitors AniList for new anime announcements and releases with network auto-recovery,

Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: System 1.5 decision models that think in loops, no

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct

Offline multi-speaker meeting-speech toolkit: planted-ground-truth synthetic meeting factory, VAD, speaker embeddings, diarization (AHC/spec

Tiny-MoE is a lightweight Mixture-of-Experts language model built entirely from scratch in native PyTorch and trained end-to-end on Kaggle u

PyTorch-native framework for fault-tolerant distributed training of foundation models on AI clusters

Production-ready batch inference for Cohere’s Arabic/English ASR model, with optimized Silero VAD, multi-file GPU batching, subtitles, and o

Windows utility focused on cuda setup, nvidia local AI, and cuda environment for local AI workflows.

Watch a real AI model think - live 3D visualization of a transformer's actual forward pass: tokens, embeddings, attention, neurons, sampling