JAX-Toolbox

jax-triton contains integrations between JAX and OpenAI Triton

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

Toy Gaussian Splatting visualization in Unity

A unified framework for 3D content generation.

LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents (ICLR 2024)

OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. …

KoLLaVA: Korean Large Language-and-Vision Assistant (feat.LLaVA)

Kimwoonggon - Cpp Libtorch Dll with GPU Verson of YOLOv8 Seg and inference in C#

C++ Implementation of PyTorch Tutorials for Everyone

Face Editor for Stable Diffusion

Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

A curation of awesome tools, documents and projects about LLM Security.

COCO to YOLO converter

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

Interpretability for sequence generation models 🐛 🔍

Paper collection on building and evaluating language model agents via executable language grounding

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

Python bindings for llama.cpp

Distribute and run LLMs with a single file.

👩‍💻👨‍💻 AI 엔지니어 기술 면접 스터디 (⭐️ 1k+)

[CVPR 24] The repository provides code for running inference and training for "Segment and Caption Anything" (SCA) , links for downloading the trained model checkpoints, and example notebooks / gra…

EfficientViT is a new family of vision models for efficient high-resolution vision.