antirez/iris.c

Z-Image - Efficient Image Generation with Single-Stream Diffusion

Z-Image: A powerful and efficient 6B-parameter image generation model with support for bilingual instructions and fast inference.

antirez/ds4

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Complete guide to samplers in Stable Diffusion

Dive into the world of Stable Diffusion samplers and unlock the potential of image generation.

Can LLMs Be Computers? | Percepta

We build a computer inside a transformer — executing arbitrary C programs for millions of steps with exponentially faster inference via 2D attention heads.

Can LLMs Be Computers? | Percepta

We build a computer inside a transformer — executing arbitrary C programs for millions of steps with exponentially faster inference via 2D attention heads.

ggml-org/llama.cpp

LLM inference in C/C++

ggml-org/llama.cpp

LLM inference in C/C++

Breaking Frontier Image Models Without Frontier AI

RISE breaks the defenses of all leading image models with an open-source attacker and an off-the-shelf judge, and the newest releases are even easier to break.

Pixel Dissolve Mask Generator

A code demo by Matthew Morete created on CodePen

neilsonnn/image-blaster

An image-to-world skillset for Claude.

Mistral Large 4 - Mistral AI

Mistral Large 4 is a state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. It features 52B active parameters and 1.05T total parameters, and a 1.6B vision encoder.

EricLBuehler/mistral.rs

Fast, flexible LLM inference

Calculating with lenses | Proceedings of the 20th ACM SIGPLAN workshop on Partial evaluation and program manipulation

Functional programs are particularly well suited to formal manipulation by equational reasoning. In particular, it is straightforward to use calculational methods for program transformation. Well-known transformation techniques, like tupling or the ...

Introduction - How to Write an Inference Engine

A zero-to-hero guide to Muse Glimmer on Apple Metal, kvpack, and disaggregated NVFP4 prefill.

Rémi in 🌁 for AIEF on Twitter / X

Projects like @antirez's ds4.c show that we can squeeze a lot of performance out of model-specific implementations instead of mapping everything back to generic ggml nodes.This probably means re-thinking the whole inference server: one central controller, many model runners as…— Rémi in 🌁 for AIEF (@remilouf) May 15, 2026