timmoon10 Goto Github PK

aluminum

Aluminum GPU-aware Communication Library

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

census_scripts

Basic analysis of Census earnings data

cme250a

Materials for CME 250A Project

cnpy

library to read/write .npy and .npz files in C/C++

conduit

Simplified Data Exchange for HPC Simulations

cudamultishifttrsm

Multi-Shift Triangular Solve in CUDA

dihydrogen

elemental

Distributed-memory dense and sparse-direct linear algebra and optimization

euler

Project Euler Solutions

flash-attention

Fast and memory-efficient exact attention

gerrymander

A silly county-level redistricting project

havoqgt

icme_computing_refresher_2016

Practice Files for 2016 ICME Computing Refresher

keras

Deep Learning for humans

kfac-pytorch

Pytorch implementation of KFAC and E-KFAC (Natural Gradient).

lapack

LAPACK development repository

lbann

Livermore Big Artificial Neural Network Toolkit

lbann_cosmogan

Code to implement GANs for cosmological images using LBANN

libgeos.jl

Julia package for manipulation and analysis of planar geometric objects

megatron-lm

Ongoing research training transformer models at scale

metis.jl

Julia interface to Metis graph partitioning

mstrsmpaper2016

Accelerating eigenvector and pseudospectra computation using blocked multi-shift triangular solves

nemo

NeMo: a toolkit for conversational AI

onednn

oneAPI Deep Neural Network Library (oneDNN)

openblas

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

protoquant

Prototype routines for GPU quantization written using PyTorch.

spack

A flexible package manager that supports multiple versions, configurations, platforms, and compilers.

transformerengine

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