01August 11, 2026/Radostin Stoyanov

On-the-fly snapshot compression for elastic inference at scale

Accelerating snapshot-based model serving with on-the-fly LZ4 memory compression in CRIU.

02August 11, 2026/Fergus Finn

The case for disaggregated LLM serving

Three checkable conditions under which disaggregated prefill is never worse than aggregated serving, and the reasons it's usually better. Plus an inventory-theory model of traffic drift: cold starts, safety stock, and a map of the shocks a deployment can ride out.

03July 30, 2026/Peter Bhabra

Gigatoken: making tokenisation care about the hardware

A first-principles tour of the SIMD scanners, cache-aware layouts, huge pages and worker scheduling behind Gigatoken.

04July 27, 2026/Jamie Dborin

You Could Have Come Up With Kimi Delta Attention

Guide to the DeltaNet Family of linear attention mechanisms.

05July 23, 2026/Fergus Finn

Throughputmaxxing: DeepSeek-V4-Flash on Isambard-AI

Single-node serving throughput for DeepSeek-V4-Flash: baseline, MLA/DP-attention, and MoE kernel choice.

06July 21, 2026/Fergus Finn

NVLink, NVSwitch, and all that

Why scale-up links are fast and short, how NVSwitch grew the domain from a board to a rack, and what TPU, UALink, and scale-up Ethernet do differently.

07July 9, 2026/Fergus Finn

Reverse-engineering NVIDIA's cuda-checkpoint for faster cold starts

Freezing a live CUDA process to host memory and thawing it again, what the driver does — and doesn't — do to make that work, and how understanding that lets us restore CUDA processes up to 4x faster.

08July 2, 2026/Fergus Finn

Width vs. depth: speculating on the margin

Some thinking about how to trade off batching and speculative decoding in a running inference engine.

09June 30, 2026/Peter Bhabra

The swarm that designs itself

We rebuilt Moonshot's Kimi agent swarm and pointed it at a real codebase: ~53× fewer tokens and ~45× cheaper than one long-context agent.

10June 29, 2026/Fergus Finn

What happens when you run a CUDA kernel

Tracing one vector-add kernel from nvcc all the way down to the warps that execute it.

11June 22, 2026/Jamie Dborin

Prediction: A Frontier Open Source LLM Will Be Released On 3rd December 2026

Using artificial analysis benchmarks we try to predict when an open source LLM will be released that matches frontier LLMs.

12June 22, 2026/Jamie Dborin

Anatomy of a Diffusion Language Model

A breakdown of the modelling choices of three new and popular diffusion language models.