kaixih

tf_op_graph

A visualization tool to display TF-Grappler optimized op graph

cudnn_frontend_test

A scalable code framework for CuDNN frontend APIs

cudnn_migration

Migrate your cuDNN v7 legacy APIs to cuDNN v8 frontend APIs

benchmark_gemm_fusion

horovod

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

layer_norm

addons

Useful extra functionality for TensorFlow 2.x maintained by SIG-addons

kaixih.github.io

paxml

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.

praxis

tensorflow

An Open Source Machine Learning Framework for Everyone

atex

A TensorFlow Extension: GPU performance tools for TensorFlow.

benchmark_layer_norm

config_files

Commonly used config files in linux

cudnn_repro

depthwise_conv2d_benchmark

dl_samples

Code samples to use deep learning frameworks, libraries.

flax

Flax is a neural network library for JAX that is designed for flexibility.

iree_playground

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

JAX-Toolbox

JAX-Toolbox

JAX101

jax_101

MHA_EinsumDense

slate

Slate is a Jekyll theme for GitHub Pages

tmp_logs

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.

xla

A machine learning compiler for GPUs, CPUs, and ML accelerators

xla_fp8_perf_test

xla_fp8_testing