Tabrizian

ant-design

An enterprise-class UI design language and React UI library

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

ninja

a small build system with a focus on speed

rr

Record and Replay Framework

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

cp-algorithms

Algorithm and data structure articles for https://cp-algorithms.com (based on http://e-maxx.ru)

paper-qa

LLM Chain for answering questions from documents with citations

libcudacxx

[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl

nanobind

nanobind: tiny and efficient C++/Python bindings

blog

Some notes on things I find interesting and important.

marl

A hybrid thread / fiber task scheduler written in C++ 11

awesome-model-quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

cpp-ipc

C++ IPC Library: A high-performance inter-process communication using shared memory on Linux/Windows.

atomic_queue

C++ lockless queue.

stdexec

`std::execution`, the proposed C++ framework for asynchronous and parallel programming.

High-Performance-Organizations-Reading-List

Ideas for creating and sustaining high performance organizations

ucx

Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)

langjam

pytriton

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.

python_backend

Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

rmm

RAPIDS Memory Manager

silifuzz

cppyy

wizardzines

sorted zines that collected from Julia Evans @b0rk twitter

pltalk

Schedule for the #PLTalk livestream. On Twitch here: https://www.twitch.tv/jeanqasaur

MathsFromExamples

Source code, datasets and trained models for the paper Learning Advanced Mathematical Computations from Examples (ICLR 2021), by François Charton, Amaury Hayat (ENPC-Rutgers) and Guillaume Lample

multipy

torch::deploy (multipy for non-torch uses) is a system that lets you get around the GIL problem by running multiple Python interpreters in a single C++ process.

extrainterpreters

Utilities for using Python's PEP 554 subinterpreters

shmemq-blog

Shared memory queue benchmarks and tracing for blog