Featured Posts and News

Simplifying AI Development at Scale: Google Cloud Integrates Anyscale's RayTurbo with GKE
04 . 09 . 2025

Simplifying AI Development at Scale: Google Cloud Integrates Anyscale's RayTurbo with GKE

02 . 12 . 2025

Deploying DeepSeek R1 on Anyscale

10 . 03 . 2024

Ray Summit 2024: Breaking Through the AI Complexity Wall

Human rated performance of different bill summarization

11 . 09 . 2023

LLM-based summarization: A case study of human, Llama 2 70b and GPT-4 summarization quality

By Justin Olsson and 
Waleed Kadous
End-to-end time

11 . 01 . 2023

Reproducible Performance Metrics for LLM inference

By Waleed Kadous, 
Kyle Huang, 
Wendi Ding, 
Liguang Xie, 
Avnish Narayan and 
Ricky Xu
factuality 373 examples

08 . 23 . 2023

Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper

By Waleed Kadous
fine-tune-img-1

07 . 05 . 2023

Fine tuning is for form, not facts

By Waleed Kadous and 
Kourosh Hakhamaneshi
Aviary Explorer

05 . 31 . 2023

Announcing Aviary: Open Source Multi-LLM Serving

By Waleed Kadous
numbers-cover-image

05 . 17 . 2023

Numbers every LLM Developer should know

By Waleed Kadous
qna-answering-questions-with

05 . 08 . 2023

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

By Waleed Kadous
doc-index-starter-langchain

04 . 18 . 2023

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

By Waleed Kadous
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, 
Jun Gong, 
Antoni Baum and 
Richard Liaw
3rdGenTasks andActors

11 . 30 . 2021

Deep Dive: Data Ingest in a Third Generation ML Architecture

By Eric Liang, 
Chen Shen, 
Clark Zinzow and 
Waleed Kadous
Uber Leveraging Ray

09 . 15 . 2021

The Third Generation of Production ML Architectures

By Waleed Kadous
WaleedKadous345

01 . 04 . 2021

Why I’m joining Anyscale

By Waleed Kadous