dacorvo

gtest-cmake-example

A sample project using GoogleTest with CMake

tensorsandbox

My tensorflow sandbox

fpsmeter

A utility script to provide an average FPS value based on CSS transitions

js-delaunay-effect

Delaunay Triangulation applied on WebCam stream

linux-shlib-link-samples

A few examples of how to link Linux shared libraries with secondary dependencies

build-benchmark

Compare build systems performance for a large C project

kconfig-samples

Illustrate the use of the Kconfig and Kbuild tools

dotfiles

My dotfiles

pyconfig

A curses interface to the Kconfig library that mimics Kconfig's menuconfig

cs231n

Assignments for stanford cs231n course

linux-qemu-from-scratch

Build a minimal Linux system and boot it from QEMU

ao

The torchao repository contains api's and workflows for quantization and pruning gpu models.

c_modules_section_sample

Illustrates decentralized modules declaration in C using ELF sections

c_sandbox

My sandbox of tiny C projects to test compiler or libc behavior

deploy-tgi-sagemaker

ec2-vs-dev

hfgraphtransforms

kaizouman.github.io

Personal blog

llm-hosting-container

Large Language Model Hosting Container

llmperf

LLMPerf is a library for validating and benchmarking LLMs

meta-rpi-playground

Experimenting with yocto and the Pi

ml_floats

A simple tool to compare floating point representations used in Machine Learning

onnx_integer

A proof-of-concept to convert a quantized ONNX model to an integer graph

sandbox-optimum-neuron

sandbox-transformers

smoothquant

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

text-generation-inference-tests

torch-int

This repository contains integer operators on GPUs for PyTorch.

transformers-neuronx

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs