Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.

An elegant PyTorch deep reinforcement learning library.

My learning notes for ML SYS.

PyTorch native quantization and sparsity for training and inference

A machine learning compiler for GPUs, CPUs, and ML accelerators

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

DeepGEMM: clean and efficient BLAS kernel library on GPU

Flax is a neural network library for JAX that is designed for flexibility.

OpenMMLab Detection Toolbox and Benchmark

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

The Modular Platform (includes MAX & Mojo)

Accessible large language models via k-bit quantization for PyTorch.

🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSy…

A high-throughput and memory-efficient inference and serving engine for LLMs

LLM training in simple, raw C/CUDA

Turn a Raspberry Pi into an Airplay server using RPiPlay to enable screen mirroring on tvs, monitors and projectors.

An open source python library for scalable Bayesian optimisation.

Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.

Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling serv…

LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source …

Minimal PyTorch implementation of YOLOv3

Image augmentation for machine learning experiments.

OverlapNet - Loop Closing for 3D LiDAR-based SLAM (chen2020rss)