Shreyansh Singh

JANUARY 24, 2021

After my last post on deploying Machine Learning and Deep Learning models using FastAPI and Docker, I wanted to explore a bit more on deploying deep learning models. My last post discussed a server-side method for deploying the model. It already has a large collection of some pretrained models.

Deep Learning 52

Deep Learning Neural Network Machine Learning ML 52

The MLOps Blog

MARCH 28, 2023

In this second installment of the series “Real-world MLOps Examples,” Paweł Pęczek , Machine Learning Engineer at Brainly , will walk you through the end-to-end Machine Learning Operations (MLOps) process in the Visual Search team at Brainly. Their user base spans more than 35 countries.

Machine Learning 59

Machine Learning Automation Data Scientist ML 59

AWS Machine Learning Blog

DECEMBER 13, 2023

In this post, we showcase fine-tuning a Llama 2 model using a Parameter-Efficient Fine-Tuning (PEFT) method and deploy the fine-tuned model on AWS Inferentia2. We then use a large model inference container powered by Deep Java Library (DJLServing) as our model serving solution.

Auto-complete 115

Auto-complete Machine Learning Deep Learning Python 115

The MLOps Blog

MAY 10, 2023

When working on real-world machine learning (ML) use cases, finding the best algorithm/model is not the end of your responsibilities. It is crucial to save, store, and package these models for their future use and deployment to production. Reusability & reproducibility: Building ML models is time-consuming by nature.

Python 105

Python Metadata ML Deep Learning 105

The MLOps Blog

APRIL 5, 2023

Have you ever spent weeks or months building a machine learning model, only to later find out that deploying it into a production environment is complicated and time-consuming? Or have you struggled to manage multiple versions of a model and keep track of all the dependencies and configurations required for deployment?

ML 69

ML Machine Learning Deep Learning Metadata 69

AWS Machine Learning Blog

APRIL 10, 2023

You don’t have to be an expert in machine learning (ML) to appreciate the value of large language models (LLMs). ML practitioners keep improving the accuracy and capabilities of these models. ML practitioners keep improving the accuracy and capabilities of these models.

Large Language Models 72

Large Language Models Deep Learning Software Development LLM 72

The MLOps Blog

JUNE 27, 2023

As you delve into the landscape of MLOps in 2023, you will find a plethora of tools and platforms that have gained traction and are shaping the way models are developed, deployed, and monitored. Open-source tools have gained significant traction due to their flexibility, community support, and adaptability to various workflows.

Machine Learning 134

Machine Learning Metadata Data Quality Data Scientist 134

TensorFlow

APRIL 28, 2023

Posted by Chansung Park and Sayak Paul (ML and Cloud GDEs) Generative AI models like Stable Diffusion 1 that lets anyone generate high-quality images from natural language text prompts enable different use cases across different industries. Then an initial noise is sampled, which is fed to the Diffusion model along with the text embeddings.

Machine Learning 52

Machine Learning ML Deep Learning Linked Data 52

AWS Machine Learning Blog

MAY 9, 2023

Amazon SageMaker Serverless Inference allows you to serve model inference requests in real time without having to explicitly provision compute instances or configure scaling policies to handle traffic variations. This is called a cold start.

Auto-complete 67

Auto-complete Machine Learning ML Software Development 67

The MLOps Blog

AUGUST 3, 2023

This article was originally an episode of the ML Platform Podcast , a show where Piotr Niedźwiedź and Aurimas Griciūnas, together with ML platform professionals, discuss design choices, best practices, example tool stacks, and real-world learnings from some of the best ML platform professionals. Stefan: Yeah. Stefan: Yeah. What is DAGWorks?

ML 52

ML Data Scientist Software Engineer Machine Learning 52

AWS Machine Learning Blog

JUNE 9, 2023

ONNX ( Open Neural Network Exchange ) is an open-source standard for representing deep learning models widely supported by many providers. ONNX provides tools for optimizing and quantizing models to reduce the memory and compute needed to run machine learning (ML) models.

ML 91

ML Computer Vision NLP Deep Learning 91

Heartbeat

MAY 29, 2023

These models have the potential to revolutionize industries ranging from customer service to scientific research, but their capabilities and limitations are still not fully understood. We will explore how to better understand the data that these models are trained on, and how to evaluate and optimize them for real-world use.

Large Language Models 78

Large Language Models LLM Machine Learning Natural Language Processing 78

AWS Machine Learning Blog

MAY 31, 2023

PyTorch is a machine learning (ML) framework based on the Torch library, used for applications such as computer vision and natural language processing. In this post, we dive deep to see how Amazon SageMaker can serve these PyTorch models using NVIDIA Triton Inference Server.

ML 85

ML Auto-classification Auto-complete Natural Language Processing 85

AWS Machine Learning Blog

DECEMBER 14, 2023

Amazon SageMaker Studio offers a broad set of fully managed integrated development environments (IDEs) for machine learning (ML) development, including JupyterLab, Code Editor based on Code-OSS (Visual Studio Code Open Source), and RStudio. Both JupyterLab and Code Editor can be launched using a flexible workspace called Spaces.

Generative AI 101

Generative AI AI Tools ML AI 101

TensorFlow

JANUARY 18, 2023

Posted by Chansung Park, Sayak Paul (ML and Cloud GDEs) TensorFlow Extended ( TFX ) is a flexible framework allowing Machine Learning (ML) practitioners to iterate on production-grade ML workflows faster with reliability and resiliency. Finally, you will see how we implemented CI/CD into the mix by leveraging GitHub Actions.

Data Ingestion 52

Data Ingestion ML DevOps Automation 52

AWS Machine Learning Blog

APRIL 18, 2023

Large language models (LLMs) with billions of parameters are currently at the forefront of natural language processing (NLP). These models are shaking up the field with their incredible abilities to generate text, analyze sentiment, translate languages, and much more.

Large Language Models 66

Large Language Models LLM NLP Deep Learning 66

AWS Machine Learning Blog

JUNE 6, 2023

PyTorch is a machine learning (ML) framework that is widely used by AWS customers for a variety of applications, such as computer vision, natural language processing, content creation, and more. The following figure shows a performance benchmark of fine-tuning a RoBERTa model on Amazon EC2 p4d.24xlarge With the recent PyTorch 2.0

ML 69

ML Deep Learning BERT Python 69

AWS Machine Learning Blog

APRIL 18, 2023

Large language models (LLMs) with billions of parameters are currently at the forefront of natural language processing (NLP). These models are shaking up the field with their incredible abilities to generate text, analyze sentiment, translate languages, and much more.

LLM 52

LLM NLP Deep Learning ML 52

The MLOps Blog

MAY 9, 2023

One of the most prevalent complaints we hear from ML engineers in the community is how costly and error-prone it is to manually go through the ML workflow of building and deploying models. Building end-to-end machine learning pipelines lets ML engineers build once, rerun, and reuse many times.

ML 98

ML Machine Learning Metadata Automation 98

The MLOps Blog

MARCH 21, 2023

Moving across the typical machine learning lifecycle can be a nightmare. From gathering and processing data to building models through experiments, deploying the best ones, and managing them at scale for continuous value in production—it’s a lot. How to understand your users (data scientists, ML engineers, etc.).

Machine Learning 69

Machine Learning Data Scientist ML Metadata 69

The MLOps Blog

DECEMBER 29, 2022

Every episode is focused on one specific ML topic, and during this one, we talked to Kyle Morris from Banana about deploying models on GPU. Who is an expert in today’s topic, which is deploying models on GPU. How would you explain deploying models on GPU in one minute? Kyle, to warm you up a little bit.

ML 52

ML Auto-complete Machine Learning Python 52

AWS Machine Learning Blog

FEBRUARY 19, 2024

Amazon SageMaker multi-model endpoints (MMEs) are a fully managed capability of SageMaker inference that allows you to deploy thousands of models on a single endpoint. In this post, we discuss a solution in which an MME can dynamically adjust the compute power assigned to each model based on the model’s traffic pattern.

ML 96

ML Auto-complete Deep Learning Software Engineer 96

AWS Machine Learning Blog

SEPTEMBER 6, 2023

Multi-model endpoints (MMEs) are a powerful feature of Amazon SageMaker designed to simplify the deployment and operation of machine learning (ML) models. With MMEs, you can host multiple models on a single serving container and host all the models behind a single endpoint.

Generative AI 103

Generative AI AI Modeling Deep Learning ML 103

AWS Machine Learning Blog

JANUARY 9, 2023

Machine learning (ML) applications are complex to deploy and often require the ability to hyper-scale, and have ultra-low latency requirements and stringent cost budgets. Deploying ML models at scale with optimized cost and compute efficiencies can be a daunting and cumbersome task. Single-model based ML applications.

ML 74

ML Auto-complete Auto-classification Deep Learning 74

AWS Machine Learning Blog

AUGUST 8, 2023

Recent scientific breakthroughs in deep learning (DL), large language models (LLMs), and generative AI is allowing customers to use advanced state-of-the-art solutions with almost human-like performance. However, in addition to model invocation, those DL application often entail preprocessing or postprocessing in an inference pipeline.

BERT 78

BERT Deep Learning Auto-classification ML 78