A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026

My Workflow for Understanding LLM Architectures

A learning-oriented workflow for understanding new open-weight model releases

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context Costs

2023, year of open LLMs

The Big LLM Architecture Comparison

From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture Design

LLM Research Papers: The 2026 List (January to May)

A curated roundup of notable LLM research papers that came out this year

Judge Arena: Benchmarking LLMs as Evaluators

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving

arXiv:2607. 02574v1 Announce Type: cross Abstract: The key-value (KV) cache has become a first-order memory object in LLM serving rather than a temporary per-request tensor.

Granite 4.1 LLMs: How They’re Built

Welcome Llama 3 - Meta's new open LLM

CodeGemma - an official Google release for code LLMs

How To Build Your Own LLM Runtime From Scratch

If you have ever wanted to actually build an LLM inference runtime yourself — pack your own weights, own every barrier, capture your own CUDA graphs — this is what that journey looks like on an H100. A step-by-step tour of a small runtime called annotated-llm-runtime, and the three bugs that produced most of the annotations.

Making thousands of open LLMs bloom in the Vertex AI Model Garden