Architecting Intelligence

Pawan K Jha
  • 0.0 (0)
  • Technology
  • Weekly

AI systems, LLM engineering, ML infrastructure, and production AI architecture.

Episodes

  1. Sep 27

    Looped Transformers: Can Models Think Longer Without Generating More Tokens?

    Can a model spend more time reasoning without generating more tokens? In the first Architecting Reasoning talk, we explore looped transformers: how they reuse layers for iterative computation, how they differ from standard transformers, and what recurrent depth could mean for reasoning and test-time compute. We also discuss ideas from Universal Transformers, Looped Transformers as Programmable Computers, and recent work on latent reasoning.

  2. Jun 28

    Self-Attention, QKV, and the Foundation of KV Cache | Architecting LLM Inference — Part 2A

    Before you can understand the KV cache, you need to understand how LLMs build context. That's what this episode is about. In Part 2A of Architecting LLM Inference, we build the foundation for everything that follows — starting with what context means inside a language model, and ending with exactly why the KV cache exists. What we cover: What context and contextual representation mean in practiceHow RNNs, CNNs, attention, state-space models, and GNNs each represent context differentlyHow self-attention builds contextual representationsCausal attention and causal maskingQuery, Key, and Value — explained through a real-world analogyHow attention scores are calculatedWhy autoregressive decoding is sequential across tokensHow attention leads directly to the KV cacheThe mental model that makes it click: Queries ask. Keys match. Values carry the information. In Part 2B, we go fully into the KV cache — what it stores, why Queries are not cached, how memory grows with sequence length, and why KV cache becomes the #1 bottleneck in production LLM inference. ▶️ Watch the full video on YouTube: https://youtu.be/gMKNWM7_U4Y Subscribe to follow the complete Architecting LLM Inference series.

  3. Jun 4

    Flashcard #001: LLM Inference Lifecycle

    Part of the Architecting Intelligence Flashcards series — short visual notes on AI, LLM systems, and ML infrastructure.

  • 3 Episodes

About

AI systems, LLM engineering, ML infrastructure, and production AI architecture.

Information