LLM inference in C/C++

Sourcetrail - free and open-source interactive source explorer

Official inference framework for 1-bit LLMs

High-speed Large Language Model Serving for Local Deployment

Customizable automatic UML diagram generator for C++ based on Clang.

BanditPAM C++ implementation and Python package

Platform Abstraction C++ Libraries

An easy-to-use and fast library for task-based parallelism, utilizing coroutines.

This is an archive of materials produced for an introductory class on CUDA programming at Stanford University in 2010

Interactive C/C++ preprocessor macro debugger

Source code repository for the projects from CUDA for Engineers

A framework that support executing unmodified CUDA source code on non-NVIDIA devices.

example programs for https://github.com/a2flo/floor (dnn, nbody, warp, hlbvh, path tracer, other)

Solution of Programming Massively Parallel Processors

Sample code to extract descriptors from the HPatches dataset.

An efficient C++ implementation of various sequential and parallel maximum flow algorithms.

Implementation of dsp sift in c++ (in development)

A repository for topics related to optimizing C++ code

sGLOH2 Descriptor OpenCV Implementation

Accumulated Stability Voting descriptor for OpenCV.

femF2BP is a C++ code implementation of the finite element method for solving Full 2-Body Problem