Archive

Writing

A collection of thoughts, tutorials, and architectural patterns.

Efficiently Serving LLMs
genaiMay 29, 2024

Efficiently Serving LLMs

Exploring techniques such as vectorization, KV caching, continuous batching, and LoRA

5 min
Generative AI with LLMs
genaiMar 1, 2024

Generative AI with LLMs

Exploring the details behind large language models including how LLMs work, and the best practices behind training, tuning and deploying them

14 min
Arabic Language Models
genaiFeb 24, 2024

Arabic Language Models

Investigating the landscape of open-source large language models (LLMs) designed to support Arabic language

15 min