Libraries & frameworks
DFloat11
LeanModels/DFloat11
A lossless LLM compression library that shrinks model weights by 30 percent for efficient GPU inference.
Topics
Related projects
meshoptimizer8.8kA C and C++ library of mesh optimization algorithms for faster GPU rendering, smaller meshes, and glTF processing.
SimpleMem3.9kAn efficient lifelong memory system for LLM agents with semantic compression, hybrid retrieval and multimodal support.
can-i-finetune-this795A practical planning tool that estimates whether a Hugging Face model fits your GPU for fine-tuning, with memory breakdowns and runnable recipes.
heretic40.4kA fully automatic command-line tool that removes safety alignment from transformers via optimized directional ablation with minimal quality loss.
toon25.6kA compact, token-efficient serialization of JSON for LLM prompts with TypeScript SDK, CLI, and lossless round-trips.
pandas-ai23.9kA Python library for conversational data analysis, letting users chat with SQL, CSV, and dataframes to query and chart.