Efficient Triton Kernels for LLM Training

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

A service for autodiscovery and configuration of applications running in containers

Playing with the Tigress software protection. Break some of its protections and solve their reverse engineering challenges. Automatic deobfuscation using symbolic execution, taint analysis and LLVM.

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

Linux kernel module to support Turbo mode and RGB Keyboard for Acer Predator notebook series

FlagGems is an operator library for large language models implemented in Triton Language.

Automatic ROPChain Generation

OpenDILab RL HPC OP Lib, including CUDA and Triton kernel

SymGDB - symbolic execution plugin for gdb

LLVM based static binary analysis framework

A performance library for machine learning applications.

🔥🔥🔥 A collection of some awesome public CUDA, cuBLAS, TensorRT, Triton and High Performance Computing (HPC) projects.

Ozoz dotfiles for bspwm, i3WM

ClearML - Model-Serving Orchestration and Repository Solution

(WIP)The deployment framework aims to provide a simple, lightweight, fast integrated, pipelined deployment framework for algorithm service that ensures reliability, high concurrency and scalability of services.

Resources About Dynamic Binary Instrumentation and Dynamic Binary Analysis

NVIDIA-accelerated, deep learned model support for image space object detection

NVIDIA-accelerated DNN model inference ROS 2 packages using NVIDIA Triton/TensorRT for both Jetson and x86_64 with CUDA-capable GPU