Micron, SanDisk Stocks Tumble After Google Unveils AI Memory Compression Breakthrough

TurboQuant: Redefining AI efficiency with extreme compression

Writing Parallel File Compression with Memory Control

Google unveils TurboQuant, a new AI memory compression algorithm — and yes, the internet is calling it 'Pied Piper' | TechCrunch

Apply video compression on KV cache to 10,000x less error at Q4 quant

Google's TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x

A compression library that beats zstd/lzma on structured data and searches compressed archives

I fell asleep halfway through gs command so I built a PDF compression CLI with Rust

Dictionary Compression is finally here, and it's ridiculously good

Semantic Compression — why modeling “real-world objects” in OOP often fails

made a localstorage compression lib thats 14x faster than lz-string

μpack: Faster & more flexible integer compression

The mathematics of compression in database systems

Integer compression library

BUFF: Decomposed bounded floats for fast compression and queries

Using the Browser’s <canvas> for Data Compression

Show HN: A luma dependent chroma compression algorithm (image compression)

The Mechanics of Compression: How 100GB Becomes 25GB

I made a small library for perceptual image compression in the style of jpeg-recompress

Automating Image Compression

Efficient String Compression for Modern Database Systems

Hand-Crafting Domain-Specific Compression with an LLM

memvid v2: 18 MB → 143 KB (99.2% compression)

Streaming compression beats framed compression

Semantic Compression (2014)

Optical context compression is just (bad) autoencoding

Post-transformer inference: 224× compression of Llama-70B with improved accuracy

Maximizing Compression of Apple II Hi-Res Images

Text similarity search via normalized compression distance

Show HN: FastLanes based integer compression in Zig

More →