artob
Follow
Highlights
- Pro
ML
Getting crystal-like representations with harmonic loss
This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov
MLX support for the Open Neural Network Exchange (ONNX)
Run LLMs and agents on TEEs leveraging NVIDIA GPU TEE and Intel TDX technologies.
A high-throughput and memory-efficient inference and serving engine for LLMs
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning
Two conversational AI agents switching from English to sound-level protocol after confirming they are both AI agents
Merlion: A Machine Learning Framework for Time Series Intelligence
A lightweight data processing framework built on DuckDB and 3FS.
Exploration work on executing CUDA kernels on Apple Silicon (Metal-compatible code).
OpenAPI Generator allows generation of API client libraries (SDK generation), server stubs, documentation and configuration automatically given an OpenAPI Spec (v2, v3)
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
SGLang is a fast serving framework for large language models and vision language models.
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Rust library for generating vector embeddings, reranking. Re-write of qdrant/fastembed.
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.