Dilip ParasuServing Fastchat — Personal JourneySetup and run ~5 Models on single A100. Guide to serving models via VLLM and fastchat for evaluations!Apr 26Apr 26
Dilip ParasuBasics of Transformers and Huggingface — InferenceSo, we hear these “LLMs (Large Language Models)” terms too much put around everywhere. Here is my attempt in providing a code first…Dec 30, 2023Dec 30, 2023
Dilip ParasuBasics of Transformers and Huggingface — DatasetsIt’s important to note that these AI Models, their ability to recognize patterns and behave in certain ways, all trace back to the…Dec 30, 20231Dec 30, 20231
Dilip ParasuArch Linux is the Best for Deep Learning (for intermediate users)You know what? It’s been more than 2 years since I jumped into the Arch-based world, using it mainly for deep learning. I said goodbye to…Oct 25, 2023Oct 25, 2023
Dilip ParasuElegance of Keras Core and JAX comboSo, I gave a talk on JAX with Keras for Keras Community day, Coimbatore. I am putting the essence of my talk here.Sep 15, 2023Sep 15, 2023
Dilip ParasuMaximizing HPC Potential: Unveiling the Best CPU, Motherboard, and Memory [Part 1]Greetings, fellow HPC enthusiasts! Today, I’m excited to kick off a series of blog posts that delve into the fascinating world of…Jul 12, 2023Jul 12, 2023
![Maximizing HPC Potential: Unveiling the Best CPU, Motherboard, and Memory [Part 1]](https://miro.medium.com/v2/resize:fill:160:106/0*8lmiq4-4wyjM90aq.png)
![Maximizing HPC Potential: Unveiling the Best CPU, Motherboard, and Memory [Part 1]](https://miro.medium.com/v2/resize:fill:320:214/0*8lmiq4-4wyjM90aq.png)
