All Posts

rllib_figure_5

06 . 26 . 2023

Introducing RLlib Multi-GPU Stack for Cost Efficient, Scalable, Multi-GPU RL Agents Training

By Avnish Narayan and

Kourosh Hakhamaneshi

Cover image for 23X batch blog

06 . 22 . 2023

How continuous batching enables 23x throughput in LLM inference while reducing p50 latency

By Cade Daniel,

0 -Anyscale Databricks headline image

06 . 15 . 2023

Introducing the Anyscale Databricks Connector

Ray_2.5_main_image

06 . 13 . 2023

Ray 2.5 features training and serving for LLMs, Multi-GPU training in RLlib, and enhanced Ray Data support

By Richard Liaw and

Aviary Explorer

05 . 31 . 2023

Announcing Aviary: Open Source Multi-LLM Serving

By Waleed Kadous

Sewer inspection graphic

05 . 22 . 2023

Inspecting Sewer Line Safety Using Thousands of Hours of Video

By Lance Walter

numbers-cover-image

05 . 17 . 2023

Numbers every LLM Developer should know

By Waleed Kadous

batch_inference_fig_1

05 . 16 . 2023

Scaling Model Batch Inference in Ray: Using Actors, ActorPool, and Ray Data

By Eric Liang, Jules S. Damji, Zhe Zhang

main_streaming_image

05 . 11 . 2023

Streaming distributed execution across CPUs and GPUs

Stephanie Wang and

Ray_summit_2023_main_image

05 . 10 . 2023

10 must-attend Ray Summit sessions: Generative AI, scalable ML workloads, and more

By Jules S. Damji and

qna-answering-questions-with

05 . 08 . 2023

Building a Self Hosted Question Answering Service using LangChain + Ray in 20 minutes

By Waleed Kadous

05 . 04 . 2023

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

By Amog Kamsetty,

Embedding - Stages of our Data Pipeline

05 . 03 . 2023

Turbocharge LangChain: guide to 20x faster embedding

By Amog Kamsetty and

main_image

04 . 27 . 2023

Announcing Ray 2.4.0: Infrastructure for LLM training, tuning, inference, and serving

By Richard Liaw,

Jules S. Damji and

doc-index-starter-langchain

04 . 18 . 2023

Building an LLM open source search engine in 100 lines using LangChain and Ray

By Waleed Kadous

liveeo-usecases

04 . 14 . 2023

LiveEO supercharges their ML infrastructure and accelerates their geospatial workloads practice

By Toby Rahloff,

fine-tune-stack

04 . 10 . 2023

How to fine tune and serve LLMs simply, quickly and cost effectively using Ray + DeepSpeed + HuggingFace

By Waleed Kadous,

Antoni Baum and

Figure-4

03 . 28 . 2023

Faster stable diffusion fine-tuning with Ray AIR