https://ramdi.fr/tags/compression/Recent content in Compression on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000https://ramdi.fr/github-stars/cavemem-deterministic-compression-and-local-memory-for-ai-coding-assistants/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/cavemem-deterministic-compression-and-local-memory-for-ai-coding-assistants/Cavemem offers a local-first persistent memory layer for AI coding assistants, compressing session data with a deterministic grammar to reduce token count by 75%. It stores observations in SQLite with hybrid search and runs without a daemon.https://ramdi.fr/github-stars/vllm-compressor-practical-quantization-and-compression-for-large-language-model-inference/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/vllm-compressor-practical-quantization-and-compression-for-large-language-model-inference/vLLM Compressor applies advanced quantization and compression techniques to large language models, enabling optimized inference without requiring full model definitions.https://ramdi.fr/github-stars/peazip-a-native-cross-platform-archive-manager-built-with-pascal/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/peazip-a-native-cross-platform-archive-manager-built-with-pascal/PeaZip is a native, lightweight archive manager supporting 200+ formats across Windows, Linux, macOS, built with Lazarus/FreePascal. It avoids Electron overhead and integrates multiple compression libs.