Lists (1)
Stars
GEMMul8 (GEMMulate): GEMM emulation and its extension to BLAS-like matrix operations using INT8/FP8 matrix engines based on the Ozaki Scheme II
GPU-accelerated linear solvers based on the conjugate gradient (CG) method, supporting NVIDIA and AMD GPUs with GPU-aware MPI, NCCL, RCCL or NVSHMEM
Performance-portable, length-agnostic SIMD with runtime dispatch
A tool for debugging and assessing floating point precision and reproducibility.
A number format that inspects your code by logging the arithmetic results.
An open collaborative repository for reproducible specifications of HPC benchmarks and cross site benchmarking environments
Graph-based operator learning in arbitrary geometries
tools for energy efficiency related expewriments
Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!
A 15TB Collection of Physics Simulation Datasets
[NeurIPS 2021] Galerkin Transformer: Neural Operator built on Attention for PDEs
High Performance Linpack for Next-Generation AMD HPC Accelerators
[Neurips 2024] A benchmark suite for autoregressive neural emulation of PDEs. (≥46 PDEs in 1D, 2D, 3D; Differentiable Physics; Unrolled Training; Rollout Metrics)
A markup-based typesetting system that is powerful and easy to learn.
A differentiable PDE solving framework for machine learning
Recent Advances on Machine Learning for Computational Fluid Dynamics: A Survey
NVIDIA HPCG is based on the HPCG benchmark and optimized for performance on NVIDIA accelerated HPC systems.
This repository containts materials for End-to-End AI for Science
High-performance and differentiation-enabled nonlinear solvers (Newton methods), bracketed rootfinding (bisection, Falsi), with sparsity and Newton-Krylov support.
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
[DEPRECATED] Moved to ROCm/rocm-libraries repo. NOTE: develop branch is maintained as a read-only mirror
Learning in infinite dimension with neural operators.