Stars
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…
Slap your MacBook, it yells back. Uses Apple Silicon accelerometer via IOKit HID.
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems
Automatically Generating Compiler Backends from Tensor Accelerator ISA Descriptions
FlagGems is an operator library for large language models implemented in the Triton Language.
[HPCA 2026] AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and versatility of software and hardware.
Ascend PyTorch adapter (torch_npu). Mirror of https://gitcode.com/Ascend/pytorch
A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology
Examples for Recommenders - easy to train and deploy on accelerated infrastructure.
A Datacenter Scale Distributed Inference Serving Framework
Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
FlashMLA: Efficient Multi-head Latent Attention Kernels
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
The Tensor Algebra SuperOptimizer for Deep Learning
Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training
oneAPI Deep Neural Network Library (oneDNN)
Puck is a high-performance ANN search engine
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
A community-maintained Python framework for creating mathematical animations.
A unified, comprehensive and efficient recommendation library
Set of datasets for the deep learning recommendation model (DLRM).