This repository includes our ongoing work on Intelligent Resource Management and Allocation strategies.

Fast and highly tuned bit vector implementation including space efficient rank and select support having only 3.51% space overhead.

Distributed Deep Learning Tutorial

Provide with pre-build flash-attention package wheels on Linux and Windows platforms using GitHub Actions

Parallel framework for large-scale GNN training

Rust tool to detect cell site simulators on an orbic mobile hotspot

A concise, beginner-friendly introduction to the core ideas of linear algebra.

Run system benchmarks to evaluate the impact of different memory allocation and cpu processes on times down to nanosecond scale.

Yet Another LLM Inference System

A unified framework across multiple programming platforms

Playing around "Less Slow" coding practices in C++ 20, C, CUDA, PTX, & Assembly, from numerics & SIMD to coroutines, ranges, exception handling, networking and user-space IO

Primary repository for the Trilinos Project

Analyze computation-communication overlap in V3/R1.

Space-Efficient, High-Performance Rank & Select Structures on Uncompressed Bit Sequences

A software that assists a previous version of the proof of Gerver's conjecture, using a custom geometric branch-and-bound algorithm, and the exact rational QP solver powered by CGAL

Code used for the experiments in the paper "Partitioned Elias-Fano Indexes"

A library of inverted index data structures

Parallel framework for training and fine-tuning deep neural networks

Static Polymorphic Algorithms for Differential Equations

Parallel Code Evaluation Benchmark

Scripts for fine-tuning an HPC Code LLM

Ultimate Plumber is a tool for writing Linux pipes with instant live preview

Analyze graph/hierarchical performance data using pandas dataframes

Solve puzzles. Learn CUDA.

An introduction to ARM64 assembly on Apple Silicon Macs

Replace OpenAI with Llama.cpp Automagically.