A universal scalable machine learning model deployment solution
-
Updated
Jun 18, 2024 - Java
A universal scalable machine learning model deployment solution
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
AI + Data, online. https://vespa.ai
A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.
A scalable inference server for models optimized with OpenVINO™
Friendli: the fastest serving engine for generative AI
An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
A high-performance inference system for large language models, designed for production environments.
Serve, optimize and scale PyTorch models in production
A flexible, high-performance serving system for machine learning models
Lineage metadata API, artifacts streams, sandbox, API, and spaces for Polyaxon
A REST API for vLLM, production ready
Boosting DL Service Throughput 1.5-4x by Ensemble Pipeline Serving with Concurrent CUDA Streams for PyTorch/LibTorch Frontend and TensorRT/CVCUDA, etc., Backends
ClearML - Model-Serving Orchestration and Repository Solution
RayLLM - LLMs on Ray
Docs for torchpipe: https://github.com/torchpipe/torchpipe
In this repository, I will share some useful notes and references about deploying deep learning-based models in production.
Database system for AI-powered apps
Add a description, image, and links to the serving topic page so that developers can more easily learn about it.
To associate your repository with the serving topic, visit your repo's landing page and select "manage topics."