Moore Threads Corporation ORG

Character Animation (AnimateAnyone, Face Reenactment)

torch_musa is an open source repository based on PyTorch, which can make full use of the super computing power of MooreThreads graphics cards.

A refactored codebase for Gaussian Splatting. Training 3DGS in 50 seconds!

MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction models along with training and inference code, covering but not limited to end-to-end speech interaction, end-to-end speech translation and speech recognition.

a static analytical model for LLM distributed training

No description.

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

No description.

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

No description.

MUSA Templates for Linear Algebra Subroutines

An adapter layer that ensures torch_musa🔦 delivers a CUDA-compatible PyTorch experience.

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models on MTGPU.

No description.

Local tool-routing proxy for openclaw/opencode/hermes, accelerating tool calls by up to 7x before forwarding general requests to upstream models.

Open Source Computer Vision Library

No description.

No description.

Fork from https://github.com/deepseek-ai/FlashMLA

mujoco_warp_musa is a Python package extending MuJoCo Warp with MUSA compute backend, enabling GPU-accelerated physics simulation on MT MUSA architecture.Forked from https://github.com/google-deepmind/mujoco_warp

No description.

Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also integrates with pytorch and can trigger traces for distributed training applications.

3DGS-DX12-Viewer is a 3D Gaussian Splatting (GS) renderer implemented using DirectX 12. Leveraging the exceptional performance of Mesh Shaders, DX12GSViewer achieves unparalleled speed improvements.

MUSA AI Tensor Engine

No description.

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

Provides a Python interface to GPU management and monitoring functions. This is a wrapper around the MTML library.

No description.

No description.

Cooperative primitives for MUSA C++.

DeepEP: an efficient expert-parallel communication library

GUI multimodal visual understanding model, GUI datasets DeskVision

No description.

No description.

The C++ parallel algorithms library.

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

mujoco_musa is a C++ sub-repository providing native MUSA kernel libraries for GPU-accelerated physics simulation in mujoco_warp_musa.

Open Machine Learning Compiler Framework

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

Repository for OpenCV's extra modules

No description.

No description.

Mirror of https://git.ffmpeg.org/ffmpeg.git

PyTorch media decoding and encoding

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

No description.

No description.

Distributed multigrid linear solver library on GPU

Quantum chemistry and solid state physics software package

No description.

Open MPI main development repository

Lightning fast differentiable SSIM.

Image-processing software for cryo-electron microscopy

High-performance LLM operator library built on TileLang.

Kokkos C++ Performance Portability Programming Ecosystem: The Programming Model - Parallel Execution and Memory Abstraction

Forked from https://gitlab.com/libeigen/eigen

Fast Library for Approximate Nearest Neighbors

Sparse 3D FFT library with MPI, OpenMP, CUDA and ROCm support

No description.

axinfra is a lightweight array and compute infrastructure library for MUSA/CPU, providing device/stream management, array operations, and zero-copy interoperability with Warp, Torch, and DLPack.

Open ABI and FFI for Machine Learning Systems

PyTorch Extension Library of Optimized Graph Cluster Algorithms

A nvImageCodec library of GPU- and CPU- accelerated codecs featuring a unified interface

Datasets, Transforms and Models specific to Computer Vision

No description.

No description.

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

PyTorch Extension Library of Optimized Scatter Operations

PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)

Data manipulation and transformation for audio signal processing, powered by PyTorch

Qt Base (Core, Gui, Widgets, Network, ...)

No description.