Havuz

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.

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

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,

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.

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.

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

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

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

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

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

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

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

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

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

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

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

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

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）

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

🌟 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。

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。

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

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

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

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

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

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

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

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

Tenstorrent backend plugin for vLLM.

A curated collection of AI learning materials

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

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

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

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

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

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

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

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

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

Readable implementation of Mamba 3 SSM model

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

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

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

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.

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

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