Sneha GhantasalainThomson Reuters LabsTensor Parallel LLM InferencingAs models increase in size, it becomes impossible to fit them in a single GPU for inference. There are different types of model parallelism…Oct 24Oct 24
Sneha GhantasalainThomson Reuters LabsSlow Reads for S3 Files in Pandas & How to Optimize itAs part of one of our projects, we needed to load pickle files with sizes in the range of 10s of GBs from AWS S3 in AWS Sagemaker endpoints…Feb 17, 2023Feb 17, 2023
Sneha GhantasalaNLP: Word Embedding AlgorithmsWhat are Word Embedding Algorithms and why are they Useful?Apr 29, 2021Apr 29, 2021
Sneha GhantasalaML PAPER: STYLEGAN — TL;DRResearch paper: A Style-Based Generator Architecture for Generative Adversarial Networks Paper published — 29th March 2019 — by Nvidia…Dec 29, 2020Dec 29, 2020
Sneha GhantasalaML PAPER: CYCLEGAN — TL;DRResearch Paper: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial NetworksDec 29, 2020Dec 29, 2020
Sneha GhantasalaML PAPER: PIX2PIX — TL;DRResearch Paper: Image-to-Image Translation with Conditional Adversarial NetworksDec 27, 2020Dec 27, 2020
Sneha GhantasalaML PAPER: PROGRESSIVE GANs — TL;DRResearch paper: “PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION”Dec 27, 20201Dec 27, 20201
Sneha GhantasalaML PAPER: NEURAL STYLE TRANSFER — TL;DRResearch paper: “A Neural Algorithm of Artistic Style” by Leon A. Gatys, et. al published on September 2, 2015.Dec 27, 2020Dec 27, 2020