Today the PyTorch team announced a 2.0 milestone, with focus on a new compiler speeding up PyTorch models with zero change in code. We tried it out in the past few weeks and here are the speedups we observed in our canonical training examples.
SOFTWARE
-
Key Components of End-to-End MLOps Platform Solutions
By
–
Here is a cheat sheet listing the key components of an end-to-end MLOps platform. The main advantage of a platform like @abacusai
: You can get most of these components out of the box in an integrated solution. -
Streamlit: Fast Data App Development Without Frontend Knowledge
By
–
.
@streamlit is one of the most useful and fastest way to build quick data apps without knowing any front-end technologies. If you are looking to learn how to build streamlit apps with code examples then check out the below repo is a must checkout -
Airbyte partners with Prefect for data integration
By
–
have not personally but Airbyte is very happy to be a Prefect partner!
-
MLOps: Implementing Procedures and Best Practices for AI Production
By
–
Adopting MLOps means putting in place procedures and best practices to maintain models for executing artificial intelligence inferences in production formally and efficiently. The name mimics the DevOps nomenclature model. Microblog and social design by @antgrasso #MLOps #AI
-
Dimensional Modeling and Data Model Implementation Best Practices
By
–
Design and implement various #data models with ease on our platform This blog post deep dives into dimensional modeling! Plus, walk through a live example of a physical data model implementation using our table creation and DDL best practices https://
dbricks.co/3sEhIg8 -
Fast DistilBERT Pipeline for CPU Inference Optimization
By
–
Fast DistilBERT on CPUs. @HaihaoShen
, @ZafrirOfir
, Bo Dong, Hengyu Meng, Xinyu Ye, Zhe Wang, Yi Ding, Hanwen Chang, Guy Boudoukh, @MosheWasserblat propose a new pipeline for creating and running Fast Transformer models on CPUs -
Apple optimizes Stable Diffusion for Silicon with Core ML
By
–
Honored to support Apple with our @diffuserslib code and Hub They built a heavily optimized Core ML version of SD that runs on Apple Silicon. And they think < 1s is within reach using distillation
Read the short blog post -> https://
hf.co/blog/diffusers
-coreml
… -
Model Builders Platform Emerges as Third Major AI Infrastructure
By
–
We’re maybe between cloud and models as #3 platform that model builders use to build and distribute models (like code builders use github to build and distribute code)
-
Building Data Lakes with Snowflake: ETL Architecture Guide
By
–
Builiding a Data Lake using Snowflake: This article was published as a part of the Data Science Blogathon. Introduction to Snowflake When we talk about the “doing” part of data engineering, people usually want to say something about ETL, like, “How is… https://
analyticsvidhya.com/blog/2022/10/b
uiliding-a-data-lake-using-snowflake/?utm_source=dlvr.it&utm_medium=twitter
…