#
Lists (1)
Starred repositories
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
【A common used C++ & Python DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流
how to optimize some algorithm in cuda.
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
A high-performance runtime framework for modern robotics.
NVIDIA DLA-SW, the recipes and tools for running deep learning workloads on NVIDIA DLA cores for inference applications.
NVIDIA Linux open GPU kernel module source
Example out-of-tree application that is also a module
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Generate diagrams from textual description
Open source AUTOSAR classic platform forked from the Arctic Core
Distributed Black-Box attacks against Image Classification.
This System Control Processor (SCP) firmware repository is no longer used and has been set to Read-only for archiving purposes. Please refer to the following active repository.
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Built and trained a convolutional network for end-to-end driving in a simulator using Tensorflow and Keras
Open-source simulator for autonomous driving research.
Primary Git Repository for the Zephyr Project. Zephyr is a new generation, scalable, optimized, secure RTOS for multiple hardware architectures.