Running NVFP4 Nemotron on a CPU, then mapping every embedding-compression method at matched byte budgets. The two quantizations compose.
Semantic Compression
An introduction to the idea that code should be approached with a mindset towards compressing it semantically, rather than orienting it around objects.
TinyPNG – Compress AVIF, WebP, PNG and JPEG images
Free online image optimizer for faster websites! Reduce the file size of your AVIF, WEBP, JPEG and PNG images while preserving the image quality.
Why Futhark?
A high-performance and high-level purely functional data-parallel array programming language that can execute on the GPU and CPU.
Dictionary Compression is finally here, and it's ridiculously good
Dictionary compression could completely change how applications send data over the web. It's recently gained broad support, and offers absurd real-world...
Modern GPU Programming For MLSys — Modern GPU Programming For MLSys
Machine learning systems sit at the heart of modern AI workloads. In these systems, performance often comes down to the quality of a small number of GPU kernels. Attention kernels, LLM prefill and decode kernels, low-precision block-scaled GEMMs, fused MoE layers, and other large fused kernels all directly shape end-to-end speed in both training and serving.
JPEG XL
The JPEG XL Image Coding System[8] (JPEG XL, sometimes shortened to JXL) is an image format that supports both lossy and lossless compression. It was developed by the Joint Photographic Experts Group (JPEG), Google and Cloudinary. It is a free and open standard defined by ISO/IEC 18181. The standard consists of four parts that cover the Core coding system, File format, Conformance testing, and Reference software, respectively.
Compression is prediction | ngrok blog
Compression and LLMs are trying to solve the exact same problem: predicting what comes next. Learn the fundamentals of compression and how better prediction leads to better shrinkage.
Squoosh
Squoosh is the ultimate image optimizer that allows you to compress and compare images with different codecs in your browser.
Word embedding
In natural language processing, a word embedding is a representation of a word. The embedding is used in text analysis. Typically, the representation is a real-valued vector that encodes the meaning of the word in such a way that the words that are closer in the vector space are expected to be similar in meaning. Word embeddings can be obtained using language modeling and feature learning techniques, where words or phrases from the vocabulary are mapped to vectors of real numbers.
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.
I hate compilers
You'd think that given the same bytes of input you'd get the same bytes of output. lol. lmao. No, you don't. It's complicated.
Astra for Coding: Why Are We Doing This Again?
Some thoughts on Astra and newfangled long-horizon models.
Handsum: An LQIP Image File Format
Low Quality Image Placeholders (LQIPs) are very small (both in terms of file size and pixel dimensions) images that load very quickly, providing immediate visual feedback while full-resolution images load slowly in the background. They are small-in-file-size enough that it’s feasible to base64-encode and inline them into a web page, minimizing network round-trips and improving page load times.
DASL — Data-Addressed Structures & Links
A small set of simple, standard primitives to work on content-addressed data.
DASL — Data-Addressed Structures & Links
A small set of simple, standard primitives to work on content-addressed data.
