Introducing EntroPack: a PyTorch tensor compression library that quantizes your model at flexible birrates to fit your exact GPU memory budget.
💻 Open Sourced at: https://github.com/modelscope/entropack
🎛️ Flexible compression: entropy-coding-based calibration-free quantization that offers arbitrary bpp (bits per parameter), not bound by fixed precisions like 4-bit or 8-bit.
⚡ GPU-native decoding: fast, fused decoding and reconstruction in a single kernel, with minimum overhead, suitable for compute-intensivie workloads such as Diffusion denoising and Transformers-Prefill.
🏆 Make the best use of your GPU VRAM: customized bpp for your exact GPU budget. For example, on a 16G GPU, Qwen-Image-2.1 can be quantized with at 4.8 bpp, resulting in 15.86 GiB usage while cutting reconstruction error from NF4's 9.40% to 4.26%.
📦 Ready to try: pre-quantized weights for Z-Image-Turbo, Qwen-Image-2.1, and MiniMax-H3 at 4 to 8 bpp, for DiffSynth-Studio and ComfyUI. The extreme Z-Image build reaches 2.3 bpp, shrinking its DiT weights to 1.6 GB, around one-seventh of BF16.
📜 Licensed under Apache 2.0.
📄 Technical report: https://modelscope.ai/papers/2609.34185
🤖 https://modelscope.ai/models/DiffSynth-Studio/EntroPackPreQuants