Reading Vertically: PHOTON and the KV-Cache Bottleneck
Author(s): Jun Nishimura Originally published on Towards AI. How a hierarchical architecture shrinks the growing KV cache — explained mostly in pictures. This is Part 1 of 3. Here we explain the PHOTON architecture (Ichikawa et al., 2025). Part 2 retrofits it …
Mamba2 is Literally Attention. Here’s How.
Author(s): Jun Nishimura Originally published on Towards AI. Part 2 of 3 — Mamba-2 and the State Space Duality. How the recurrence becomes a matmul, why Nemotron-H ships this one, for ML engineers who already speak fluent Transformer. 1. Why this one, …
Recent Posts
![[Day 37/100] Build Your Own Agent Memory Layer with Postgres and pgvector](https://miro.medium.com/v2/resize:fit:700/1*-Doos2nmUT3FPZ-Qxbk3Hw.png "[Day 37/100] Build Your Own Agent Memory Layer with Postgres and pgvector")
