Havuz

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

To know what models don't say out loud.

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

Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. P

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

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

Best AI Workload Orchestrator for Kubernetes Python 2026

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

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

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur

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

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

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,

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

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

Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.

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

A Personalized Federated Learning (PFL-HCare) framework for IoT healthcare. Features MAML meta-learning, Differential Privacy (RDP), and gra

Official code for Echo-Memory: a controlled study of memory in action-conditioned video world models (Context, Compression, Spatial, State-S

Split FLUX.2 and LTX 2.3 across two GPUs (LAN or same-machine) — NVENC compresses activations live on the wire. Icarus (ComfyUI node) + Daed

Self-Tuning Multi-Agent AI Trading System 2026: 8-Source Signal Fusion & Kronos Model

WarMatrix 2026: Next-Gen Tactical Simulation & AI Command Console

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

Building a small LLM in PyTorch from scratch - a step-by-step journey inspired by Stanford CS336.

The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.

[Preprint] TBSM: Three-Body Scattering for Generative Modeling.

Scaler 2 Music Theory Tool 2026: Direct DAW Integration for Windows 10 and 11

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.

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

Streamline AI Workloads on Kubernetes: Universal Python SDK Guide 2026

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

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.

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

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

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

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

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