🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, NEON for ARM.

OSMVisualizer is a lightweight ROS 2 node with minimal dependencies designed to visualize OpenStreetMap (OSM) data in Foxglove, Lichtblick, or RViz2.

User-Mode Driver for Tenstorrent hardware

🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.

FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.

CubeSLAM: Monocular 3D Object Detection and SLAM

Arm NN ML Software.

The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

[ICCV 2025] Official code of "ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation"

Development repository for the Triton language and compiler

Development repository for the Triton-Linalg conversion

3DGS plugin/LiDARSimLib/Fisheye sensor for UE5 version of CARLA

A primitive library for neural network

Fast Multimodal LLM on Mobile Devices

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

✨✨Latest Advances on Multimodal Large Language Models

Low-bit LLM inference on CPU/NPU with lookup table

Use safetensors with ONNX 🤗

Camera IMU Calibration using an Extended Kalman Filter