antiagainst
Follow
Stars
TokenSpeed is a speed-of-light LLM inference engine.
Distributed Compiler and Optimized Parallel Kernels
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Small library for D3D12. Provides assert-like macro for HLSL that crashes the GPU.
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
📋 A list of open LLMs available for commercial use.
StableLM: Stability AI Language Models
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
antimatter15 / alpaca.cpp
Forked from ggml-org/llama.cppLocally run an Instruction-Tuned Chat-Style LLM
A collection of modern/faster/saner alternatives to common unix commands.
High-Performance Rendering Framework on Stream Architectures
Making large AI models cheaper, faster and more accessible
A profiler to disclose and quantify hardware features on GPUs.
📊 An infographics generator with 30+ plugins and 300+ options to display stats about your GitHub account and render them as SVG, Markdown, PDF or JSON!
Customized matrix multiplication kernels
Productive, portable, and performant GPU programming in Python.
Eureka is a feature-rich and highly customizable Hugo theme.
Sources for Arm Streamline's gator daemon, part of Arm Mobile Studio suite of performance analysis tools
A debian-based shell environment designed for Android and adb
Memory consumption and FLOP count estimates for convnets
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its…