Dave Gaunkysaltyoldgeek.hashnode.dev·May 16, 2024Setting Up an Ollama + Open-WebUI ClusterWhy? Having set up an Ollama + Open-WebUI machine in a previous post I started digging into all the customizations Open-WebUI could do, and amongst those was the ability to add multiple Ollama server nodes. This got me thinking about setting up multi...ollama
Mirza Bilalmirzabilal.com·Jan 14, 2024The Downside of Vertical Scaling GPU InstancesThe artificial intelligence, machine learning, and generative AI application's growth have swelled the demand for high-performance GPU workloads. To fulfill these needs, cloud services have introduced a broad range of instances to fulfill diverse nee...83 readsCloud Scaling Strategiesgpu intensive tasks
Md Ameenuddin Siddiquiaisemi.hashnode.dev·Nov 20, 2023Brain floatThere is a trend in DL towards using FP16 instead of FP32 because lower precision calculations seem to be not critical for neural networks. Additional precision gives nothing, while being slower, takes more memory and reduces speed of communication. ...VLSI circuit design
Mirza Bilalmirzabilal.com·Oct 25, 2023How To Enable Hardware Acceleration on Chrome, Chromium & Puppeteer on AWS in Headless modeRunning Google Chrome with hardware acceleration in headless mode can be more challenging than it appears. We embarked on this journey with Remotion, which is an excellent framework that enables developers to "Make Videos Programmatically". On our wa...5.4K readsgoogle chrome browser
ANIL TIRLIOĞLUforasynxasynx.hashnode.dev·Dec 7, 2020Getting started to Vitis acceleration flow with Zynq 7000We all know, sometimes it is just hard to get started learning things from vendor documentations. This tutorial will follow beginner friendly steps to run your first accelerator on an FPGA. ℹ This tutorial will be more beneficial when used in conjun...31 readsvitis
