jishminor

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

opencv

Open Source Computer Vision Library

llama.cpp

LLM inference in C/C++

act

Run your GitHub Actions locally 🚀

llama

Inference code for LLaMA models

bark

🔊 Text-Prompted Generative Audio Model

llama_index

LlamaIndex is a data framework for your LLM applications

llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

slim

Slim(toolkit): Don't change anything in your container image and minify it by up to 30x (and for compiled languages even more) making it secure too! (free and open source)

alpaca-lora

Instruct-tune LLaMA on consumer hardware

candle

Minimalist ML framework for Rust

dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.

DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

nebuly

The user analytics platform for LLMs

proxychains

proxychains - a tool that forces any TCP connection made by any given application to follow through proxy like TOR or any other SOCKS4, SOCKS5 or HTTP(S) proxy. Supported auth-types: "user/pass" for SOCKS4/5, "basic" for HTTP.

LoveIt

❤️A clean, elegant but advanced blog theme for Hugo 一个简洁、优雅且高效的 Hugo 主题

glow

Compiler for Neural Network hardware accelerators

inference

Reference implementations of MLPerf™ inference benchmarks

dlpack

common in-memory tensor structure

VectorDBBench

A Benchmark Tool for VectorDB

tinymembench

Simple benchmark for memory throughput and latency

STREAM

STREAM benchmark

maskcam

Jetson Nano-based smart camera system that measures crowd face mask usage in real-time.

processwatch

papi

DAMOV

DAMOV is a benchmark suite and a methodical framework targeting the study of data movement bottlenecks in modern applications. It is intended to study new architectures, such as near-data processing. Described by Oliveira et al. (preliminary version at https://arxiv.org/pdf/2105.03725.pdf)

armnn_tflite_backend

TensorFlow Lite backend with ArmNN delegate support for Nvidia Triton

perfsage

smarter-inference

Inference as a Service with Arm optimized Triton and a custom admission controller.