richardliaw
Re:Nvidia Dynamo: A Datacenter Scale Distributed Inference Serving Fra...
on Thursday March 20, 2025 @12:08PM (#43425117)
> If you have 1 massive job, Ray sucks and doesn't provide table stakes.
Can you say more?
A comprehensive guide to building RAG-based LLM applications for production
Re:Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custo...
on Friday August 11, 2023 @01:31PM (#37091373)
I'm really glad to see a post like this come out. I've seen so many discussions online about customizing models -- this post really does cut through the noise.
Really like the evaluation methodology, and seems well-written as well.
Ray – an open source project for scaling AI workloads
Continuous batching enables 23x throughput in LLM inference
Anyscale's Aviary is a dashboard for evaluating Open Source LLMs
Numbers every LLM Developer should know
How to build a LLM search engine using a self-hosted LLM
Ray is the next generation ML framework
Anyscale raises $40M Series B to revolutionize serverless computing
Re:SpaCy v3.0 Nightly
on Thursday October 15, 2020 @01:05PM (#24790907)
This is a huge release! Weights and Biases support, transformers, Ray support -- it just never stops!
Cloud Computing in Python for all major clouds
Large Scale Training at Berkeley AI Research
Ray (from UC Berkeley), for the Curious
Ray for the Curious
Re:Anyscale, from the creators of the Ray distributed computing projec...
on Wednesday December 18, 2019 @07:36PM (#21830993)
Interesting. What do you mean when you say: "versus the authors re-applying some of same research in their own thing."
And does "code distribution" just mean to release as open source?
Tune: A scalable framework for hyperparameter tuning from UC Berkeley
Re:Google Vizier: A Service for Black-Box Optimization
on Monday August 27, 2018 @12:36PM (#17852472)
Very related open source project from the RISE Lab at UC Berkeley: http://ray.readthedocs.io/en/latest/tune.html