News

User Story

Engineering

Culture

Amog Kamsetty

Hao Chen

Liguang Xie

ByteDance, the company behind Tiktok, leverages multi-modal models to enable many applications, such as text-based image retrieval or object detection.

bytedance-actor-pool

How ByteDance Scales Offline Inference with Multi-Modal LLMs

How ByteDance Scales Offline Inference with multi-modal LLMs to 200 TB Data

Jerry Liu

In this blog, we showcase how you can use LlamaIndex and Ray to build a query engine to answer questions and generate insights about Ray itself.

llamaindex-img-3

Build and Scale a Powerful Query Engine with LlamaIndex & Ray

Build and Scale a Powerful Query Engine with LlamaIndex and Ray

Eric Liang

Eric Liang headshot

Jules S. Damji

We conduct a comparison of three different solutions for offline batch inference: AWS SageMaker Batch Transform, Apache Spark, and Ray Data.

Figure 1. Throughput difference among three different solutions for 10GB batch inference


Figure 1

Offline Batch Inference | Ray, Apache Spark & SageMaker

Offline Batch Inference: Comparing Ray, Apache Spark, and SageMaker

Philipp Moritz

In part 2 of this blog series, we show you how to turbocharge embeddings in LLM workflows using LangChain and Ray Data.

Embedding - Stages of our Data Pipeline

Turbocharge LangChain: Guide to 20x Faster Embedding

Turbocharge LangChain: guide to 20x faster embedding

Matthew Deng

Richard Liaw

Richard Liaw headshot

Will Drevo

Ray Train

Distributed Deep Learning with Ray Train is Now In Beta

Distributed deep learning with Ray Train is now in Beta

Christy Bergman

Displaying [New York City Yellow Taxi](https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page) ride volumes, with 1 week hourly forecast.  Blue=observed, Orange=predicted, per validation dataset.  Forecast generated using Google’s Temporal Fusion Transformer algorithm implemented by Pytorch forecasting, and parallelized by Ray for faster runtime, either on a laptop or on any cloud.  Image by Author.  

forecasting blog 2 of 2 image 1

Time Series Forecasting using an LSTM version of RNN with PyTorch Forecasting and Torch Lightning

Ray Lightning

Introducing Ray Lightning: Multi-node PyTorch Lightning training made easy

Kai Fricke

XGBoost-Ray

Introducing Distributed XGBoost Training with Ray

Retrieval Augmented Generation with Huggingface Transformers and Ray

Archit Kulkarni

Ray x mlflow

Ray & MLflow | Taking Distributed ML Apps to Production

Ray & MLflow: Taking Distributed Machine Learning Applications to Production

Jack Parker-Holder

Pb2: Solo Gif

Population Based Bandits: Provably Efficient Online Hyperparameter Optimization

Ray Summit 2024, the annual Ray community conference, is back in San Francisco, CA this September 30th through October 2nd. It is a two-day event with a third day dedicated to training.

Call for Proposals is open Blog Post

Ray Summit 2024 Call for Proposals is now open

Intel and Anyscale have integrated Ray with Gaudi3. Gaudi3 is AI-optimized for efficient training and other machine learning workloads.

Anyscale - Intel

Accelerating AI: Harnessing Intel(R) Gaudi(R) 3 with Ray 2.10

Anyscale is teaming with NVIDIA to combine the developer productivity of Ray Serve and RayLLM with the cutting-edge optimizations from NVIDIA Triton Inference Server software and the NVIDIA TensorRT-LLM library.

NVIDIA-Anyscale Logo 1280x680.jpg

Low-latency Generative AI Model Serving with Ray, NVIDIA Triton Inference Server, and NVIDIA TensorRT-LLM

Generating embeddings is a critical task for developing successful RAG applications, and Anyscalew with Pinecone is the most cost-efficient solution for this workflow.

blog-anyscale-pincone

RAG at Scale: 10x Cheaper Embedding Computations with Anyscale and Pinecone

This section is used to order the "Types" and "Tags" that show up for filters on the Blog Index

Types

Products / Libraries

Blog

Hosted Anyscale is in Private Preview. Click here to request access!

Anyscale is the leading AI application platform. With Anyscale, developers can build, run and scale AI applications instantly.

Anyscale

Posts by Amog Kamsetty

No posts found.