Flux 2 image generation model pure C inference. Contribute to antirez/iris.c development by creating an account on GitHub.
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.
Reverse-engineering GGUF | Post-Training Quantization
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
A new era for software testing - <antirez>
videlalvaro/ane-book
Production LLM inference on the Apple Neural Engine — a practitioner's guide, complete with converters, Swift runtimes, and validated model manifests
Discontinuity-Aware 2D Neural Fields
Neural image representations offer the possibility of high fidelity, compact storage, and resolution-independent accuracy, providing an attractive alternative to traditional pixel- and grid-based representations. However, coordinate neural networks fail to capture discontinuities present in the image and tend to blur across them; we aim to address this challenge. In many cases, such as rendered images, vector graphics, diffusion curves, or solutions to partial differential equations, the locations of the discontinuities are known. We take those locations as input, represented as linear, quadratic, or cubic \bez curves, and construct a feature field that is discontinuous across these locations and smooth everywhere else. Finally, we use a shallow multi-layer perceptron to decode the features into the signal value. To construct the feature field, we develop a new data structure based on a curved triangular mesh, with features stored on the vertices and on a subset of the edges that are marked as discontinuous. We show that our method can be used to compress a 100,000^2-pixel rendered image into a 25MB file; can be used as a new diffusion-curve solver by combining with Monte-Carlo-based methods or directly supervised by the diffusion-curve energy; or can be used for compressing 2D physics simulation data.
Muse Glimmer: Meta’s 30B Model Built for Efficient Inference
Inside Meta’s 30B local reasoning model and its tiny KV cache
