Page 2 - Showing 4 of 12 posts
-
RoPE: From Permutation Invariance to Multi-Frequency
A deep dive into RoPE (Rotary Position Embedding), the standard position encoding for modern LLMs: the math, the engineering, and floating-point precision.
·llmtransformerminimindropeposition encoding -
Why Transformers Need Normalization: Gradients to RMSNorm
A deep dive into why deep neural networks need normalization, and how RMSNorm became standard in modern LLMs
·llmtransformerminiminddeep learningnormalization -
Frontend Intern Interviews at Chinese Startups: A Prep Guide
A systematic rundown of the technical topics, application data, and a complete prep checklist for frontend internship interviews at smaller Chinese companies.
·实习前端面试react -
My First-Ever Pull Request
A sophomore reflects on landing his first successful open-source pull request
·开源前端