Gavin Li
One of the scalability problem we saw is when processing huge data, we need to have large number of reduce splits, which makes the memory overhead of shuffle writers becomes...
## Add Block-wise INT8 Quantization This PR adds deepseek-style block-wise INT8 quantization support to ComfyUI, enabling ~50% memory reduction with limited accuracy loss and improved performance on large layers. ###...
## Summary This PR adds support for **SVDQuant INT4 quantization** as a new `QuantizedLayout` in ComfyUI, enabling faster inference and reduced VRAM usage. ## Key Changes ### 1. New Quantization...