tuttlebr Goto Github PK

apple-py

GPU-accelerated PyTorch training on Mac

automl

cluster-maintenance

General maintenance for my home servers using Ansible

daedalus

Basement-Grade Kubernetes Cluster

dali

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

deepstream

disney-marathon-weather

Wonder what the weather might be on race day?

facedetect

Detects one or more faces in the given image / video using NVIDIA Triton Inference Server

flair-on-nvidia-triton

Scripts to help deploy the Flair ner-english-fast model on Triton Server as a TorchScript model.

generative-style-transfer

Generative-style-transfer with tensorflow 2

gfpgan

Face Restoration with a Generative Facial Prior

gtc-2023-se52140

Developer Breakout - Accelerating Enterprise Workflows With Triton Server and DALI

kubeflow-servers

Customized docker images which can run on Kubeflow.

kubernetes-jupyterlab

A simple configuration for launching a Jupyterlab on Kubernetes.

kubernetes-wireguard-server

Helm based deployment for a WireGuard server on Kubernetes

layoutlmv3-triton-server

An NVIDIA Triton Server workflow for OCR and the LayoutLMv3 Transformer Model

llm-continuous-batching-benchmarks

multi-node-k8s-ml

End-to-end deployment for multi-node training using GPU nodes on a Kubernetes cluster.

nemo-supervised-fine-tuning

Supervised Fine Tuning (SFT) is the process of finetuning all of the model's parameters on supervised data of inputs and outputs that teaches the model how to follow user specified instructions.

nvfuser

Testing the new, integrated compilers in PyTorch.

nvidia-megatron-on-triton

An end-to-end framework for training and deploying LLMs with billions and trillions of parameters. This example uses the publicly available 20 billion GPT variant.

quickperf

A simple performance collection tool to determine the performance of a GPU enabled environment.

rapids-dash

Testing plotly demo with cudf and Kubernetes

riva-speech-skills

State-of-the-art models, fully accelerated pipelines, and tools to easily add Speech AI capabilities to real-time applications like virtual assistants, call center agent assist, and video conferencing.

sleep_sounds

steganography

A simple notebook demonstrating an image manipulation technique called steganography!

t5-faster-transformer

My working repo for following the NVIDIA blog post originally written by Denis Timonin, Bo Yang Hsueh, Dhruv Singal and Vinh Nguyen

t5-tensorrt-llm

T5 model on TensorRT-LLM & Triton Inference Server

terraform-oci-arch-postgresql

Terraform module to deploy PostgreSQL on Oracle Cloud Infrastructure (OCI).

terraform-oci-arch-redis

terraform-oci-arch-redis