Lightweight clipboard manager for macOS

Fully open data curation for reasoning models

CaDiCaL SAT Solver

Bundesgesetze und -verordnungen

Simple C++ borrow checker

A low-latency & high-throughput serving engine for LLMs

🟣 Concurrency interview questions and answers to help you prepare for your next software architecturea and design patterns interview in 2024.

What would you do with 1000 H100s...

SGLang is a fast serving framework for large language models and vision language models.

A low-latency & high-throughput serving engine for LLMs

Teaching and Learning Software Verification via SVF

Implementation of a Transformer, but completely in Triton

Development repository for the Triton language and compiler

Tensor Compute Primitives: Mid-level Intermediate Representation for Machine Learning Programs

An attempt at proxying vscode remote shell backend through cluster login nodes.

LLM Serving Performance Evaluation Harness

HeteroCL-MLIR dialect for accelerator design

Allo: A Programming Model for Composable Accelerator Design

Use of a Linux initramfs to fully automate the bootstrapping process

Scheduling application designed to mitigate some of the pain-points present throughout Georgia Tech's registration process.

Python compiler

clasp Common Lisp environment

SLOT: SMT-LLVM Optimizing Translation

The rustic MLIR bindings in Rust

An Extensible Compiler IR Framework

Fast and memory-efficient exact attention

Utilities intended for use with Llama models.