compression

跨平台密码学工具箱。包含编解码，编码转换，加解密， 哈希，MAC，签名，大数运算，压缩，二维码功能，CTF等功能。

CSS & JavaScript minifier, in PHP. Removes whitespace, strips comments, combines files (incl. @import statements and small assets in CSS files), and optimizes/shortens a few common programming patterns.

A curated list for Efficient Large Language Models

🗜️Compress Image, Video, and Audio same like Whatsapp 🚀✨

Neural Network Compression Framework for enhanced OpenVINO™ inference

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

Context-Engine MCP - Agentic Context Compression Suite

A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ECCV'24]

On-device LLM Inference Powered by X-Bit Quantization

Context intelligence layer for LLM agents: persistent memory with write-time dedup, sensitivity tagging, conflict detection, and hierarchical decay. ~12ms. No LLM calls. MIT.

CP and Tucker decomposition for Convolutional Neural Networks

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.

TurboQuant KV cache compression plugin for vLLM — asymmetric K/V, 8 models validated, consumer GPUs

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

🤫 Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.

A family of highly efficient, lightweight yet powerful optimizers.

Convert long AI conversations into portable conversation state graphs for LLM handoffs.

Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simulation, Godzilla KVarN/TriAttention with SM86/SM89 qualification, CUDA weight sharing, and multi-GPU planning.

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.