Stars
AI agents running research on single-GPU nanochat training automatically
Fast Hadamard transform in CUDA, with a PyTorch interface
Free, open-source SSH terminal, SFTP file manager & S3 browser for macOS, Windows & Linux. Alternative to Termius.
Powerful system-level package manager for Linux, macOS and Windows written in Rust – building on top of the Conda ecosystem.
MathCode: A Frontier Mathematical Coding Agent
PLDI'24 Artifact for "The T-Complexity Costs of Error Correction for Control Flow in Quantum Computation".
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
Development repository for the Triton language and compiler
A free and strong UCI xiangqi engine
CUDA Templates and Python DSLs for High-Performance Linear Algebra
Sparse Johnson-Lindenstrauss Transforms CUDA Kernel
`dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.
Official inference framework for 1-bit LLMs
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
A fast, effective data attribution method for neural networks in PyTorch
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
Build resilient language agents as graphs.
Open deep learning compiler stack for Kendryte AI accelerators ✨
A formalization of geometry in Coq based on Tarski's axiom system
Infrastructure for Machine Learning Guided Optimization (MLGO) in LLVM.
My learning notes for ML SYS.