triton-inference-server / server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
☆8,926Updated this week
Alternatives and similar repositories for server:
Users that are interested in server are comparing it to the libraries listed below
- Serve, optimize and scale PyTorch models in production☆4,301Updated this week
- NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source compone…☆11,350Updated last week
- Transformer related optimization, including BERT, GPT☆6,084Updated 11 months ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,711Updated this week
- ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator☆16,010Updated this week
- Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.☆14,423Updated last month
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆12,112Updated this week
- Ongoing research training transformer models at scale☆11,837Updated this week
- Fast and memory-efficient exact attention☆16,370Updated this week
- Development repository for the Triton language and compiler☆14,931Updated this week
- ONNX-TensorRT: TensorRT backend for ONNX☆3,044Updated 2 weeks ago
- A flexible, high-performance serving system for machine learning models☆6,251Updated this week
- A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep lear…☆5,323Updated this week
- PyTorch extensions for high performance and large scale training.☆3,278Updated 2 months ago
- Open standard for machine learning interoperability☆18,658Updated this week
- Standardized Serverless ML Inference Platform on Kubernetes☆3,993Updated this week
- Simplify your onnx model☆4,002Updated 6 months ago
- Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX☆2,386Updated last month
- Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.☆29,161Updated this week
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆8,585Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆6,818Updated this week
- TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain…☆9,715Updated this week
- The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!☆7,481Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆37,533Updated this week
- Optimized primitives for collective multi-GPU communication☆3,564Updated this week
- CUDA Templates for Linear Algebra Subroutines☆7,097Updated last week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,497Updated this week
- Tutorials for creating and using ONNX models☆3,469Updated 8 months ago
- Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.☆594Updated this week
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,249Updated last week