Skip to main content
Page 1

Training Highly Scalable Deep Recommender Systems on Databricks (Part 1)

September 4, 2024 by Rithwik Ediga Lakhamsani, Asfandyar Qureshi, Karan Jariwala, Lin Yuan, Lu Wang (Mosaic AI), Saaketh Narayan and Ning Wang in Generative AI
Recommender systems (RecSys) have become an integral part of modern digital experiences, powering personalized content suggestions across various platforms. These sophisticated systems and...

Beyond the Leaderboard: Unpacking Function Calling Evaluation

August 16, 2024 by Kartik Sreenivasan, Jeffrey Chen, Pallavi Koppol, Eitan Turok, Bay Foley-Cox, Asfandyar Qureshi and Sam Havens in Mosaic Research
1. Introduction The research and engineering community at large have been continuously iterating upon Large Language Models (LLMs) in order to make them...

Introducing Mixtral 8x7B with Databricks Model Serving

December 21, 2023 by Ahmed Bilal, Daya Khudia, Ankit Mathur, Asfandyar Qureshi, Bruce Fontaine, Linden Li, Maddie Dawson, Sandeep Krishnamurthy, Josh Hartman and Hagay Lupesko in Engineering Blog
Today, Databricks is excited to announce support for Mixtral 8x7B in Model Serving . Mixtral 8x7B is a sparse Mixture of Experts (MoE)...

Build GenAI Apps Faster with New Foundation Model Capabilities

December 11, 2023 by Ahmed Bilal, Asfandyar Qureshi, Margaret Qian, Jianwei Xie, Sue Ann Hong, Vladimir Kolovski, Mingyu Li and Ankit Mathur in Engineering Blog
Following the announcements we made last week about Retrieval Augmented Generation (RAG) , we're excited to announce major updates to Model Serving. Databricks...

LLM Inference Performance Engineering: Best Practices

October 12, 2023 by Megha Agarwal, Asfandyar Qureshi, Nikhil Sardana, Linden Li, Julian Quevedo and Daya Khudia in Mosaic Research
In this blog post, the MosaicML engineering team shares best practices for how to capitalize on popular open source large language models (LLMs)...