royinx

PyMacroRecord

Free and Open Source Macro Recorder with a modern GUI using Python

Llama-2-Onnx

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

compute-sanitizer-samples

Samples demonstrating how to use the Compute Sanitizer Tools and Public API

Rust-CUDA

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.

candle

Minimalist ML framework for Rust

llama

Inference code for Llama models

deployment

RAPIDS Deployment Documentation

bitsandbytes

8-bit CUDA functions for PyTorch, modified to build on NVIDIA Jetson

linkerd2

Ultralight, security-first service mesh for Kubernetes. Main repo for Linkerd 2.x.

gpt-migrate

Easily migrate your codebase from one framework or language to another.

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

CV-CUDA

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

dbscan-cuda

并行计算作业 DBSCAN algorithm with C++ and CUDA

Competitive-Programming

Competitive Programming problem solutions.

Nsight-Systems-Docker-Image

Nsight Systems in Docker

python_cuda_test

nvjpeg-python

nvjpeg for python

How_to_optimize_in_GPU

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

nvdiffrec

Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

dmls-book

Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022)

transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

cpp-cheat-sheet

C++ Syntax, Data Structures, and Algorithms Cheat Sheet

open-gpu-kernel-modules

NVIDIA Linux open GPU kernel module source

de-git

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

yolov7_d2

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

kernel_tuner

Kernel Tuner

triton_ensemble_model_demo

triton server ensemble model demo

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.