LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

TabICLv2: A state-of-the-art tabular foundation model

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Implementation of the sap-rpt-1-oss deep learning model with inference pipeline as described in the paper "ConTextTab: A Semantics-Aware Tabular In-Context Learner".

TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

A high-performance and light-weight router for vLLM large scale deployment

Modeling, training, eval, and inference code for OLMo

Bringing BERT into modernity via both architecture changes and scaling

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

A framework for efficient model inference with omni-modality models

RouterArena: An open framework for evaluating LLM routers with standardized datasets, metrics, an automated framework, and a live leaderboard.

The Future of Data Engineering — A CLI SQL client for the modern data stack, enabling AI-native context engineering for data.

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

LLM Semantic Router: Intelligent Mixture-of-Models (MoM) System with Privacy Preservation and Prompt Guard. The semantic router intelligently directs OpenAI compliant API requests to the most suita…

Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.

CLIP-Finder enables semantic offline searches of images from gallery photos using natural language descriptions or the camera. Built on Apple's MobileCLIP-S0 architecture, it ensures optimal perfor…

Achieve state of the art inference performance with modern accelerators on Kubernetes

Latency and Memory Analysis of Transformer Models for Training and Inference

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

Cloud Native Observability and Policy Engine for LLM Applications

GitHub Action to Create an AWS EC2 Self-hosted Runner

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks.This framework enables Claud…

Micro Llama is a small Llama based model with 300M parameters trained from scratch with $500 budget