Lists (2)
Starred repositories
Dinomaly2: A Unified Framework for Full-Spectrum Unsupervised Anomaly Detection
Research into AI engineering interview assignments, take-home challenges, and hiring practices from 2026
The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.
Lecture notes, tutorial tasks including solutions as well as online videos for the reinforcement learning course hosted by Paderborn University
A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.
Generate hands-on, multi-part technical tutorials on demand, with LLM skills tuned to make content approachable. Then you work through them yourself, by hand ✋
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
A vector index built on TurboQuant, written in Rust with Python bindings
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Learn it. Build it. Ship it for others.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖
Practical, Colab-friendly notebooks for fine-tuning and running audio AI models
[ICML 2026] ByteDance's All-in-One Video Generation Model for Human-Object Interaction Video Generation
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
real time face swap and one-click video deepfake with only a single image
The agent that grows with you
Beginner, advanced, expert level Rust training material
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
Embedded property graph database built for speed. Vector search and full-text search built in. Implements Cypher.
A lightweight, lightning-fast, in-process vector database
Give your agents the power of the Hugging Face ecosystem
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…