A cross-platform, high performance renderer for Gaussian Splatting using Vulkan Compute. Supports ✅ Windows, Linux, macOS, iOS, and visionOS

Grok open release

Fast Inference of MoE Models with CPU-GPU Orchestration

The impossibly small web framework for Python and MicroPython.

A flexible web-based editor, converter, visualization tool, for geospatial data

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

Arduino Simulator in JavaScript

Reference implementation of Mistral AI 7B v0.1 model.

Build highly concurrent, distributed, and resilient message-driven applications using Java/Scala

Code, Dataset for SeeAct

[ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces

Modular Monolith architecture demonstration with Spring Modulith and DDD

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

Companion repo for complete Docker course

A generalized information-seeking agent system with Large Language Models (LLMs).

Modern C++ Programming Course (C++11/14/17/20)

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Some information for working with the Together inference API for Open Source AI models

FreeInit: Bridging Initialization Gap in Video Diffusion Models

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

A curated list of papers and resources based on "Large Language Models on Graphs: A Comprehensive Survey".

YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking

A unified evaluation framework for large language models

ChemGCN is a graph convolutional network to predict water solubilities of small molecules.

C++ TensorRT Implementation of NanoSAM

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.