Search papers, labs, and topics across Lattice.
This paper introduces OrbitQuant, a data-agnostic quantization method for diffusion transformers that addresses the inefficiencies of post-training quantization (PTQ) by utilizing a normalized, rotated basis for weight and activation quantization. By employing a randomized permuted block-Hadamard rotation, OrbitQuant eliminates the need for recalibrating data across different checkpoints or modalities, allowing for a single codebook to be effective across various inputs. The method achieves state-of-the-art results in PTQ for image and video generation tasks, demonstrating significant improvements in efficiency without compromising generation quality, even at low-bit settings like W2A4.
OrbitQuant achieves state-of-the-art post-training quantization for diffusion transformers, enabling efficient image and video generation without the need for data-specific calibration.
Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps, prompts, and guidance branches, forcing prior methods to re-fit calibration data for every new checkpoint or modality. We present OrbitQuant, a data-agnostic weight-activation quantizer that bypasses range estimation by quantizing in a normalized, rotated basis. In this basis, a randomized permuted block-Hadamard (RPBH) rotation concentrates each coordinate around one fixed, known marginal regardless of the input, so a single Lloyd-Max codebook serves all timesteps, prompts, and layers of a given input dimension. We extend the same quantizer to weight rows offline, absorbing the rotation into the weights so that it cancels inside each linear layer and only a forward rotation on the activations remains at runtime. The same recipe transfers from image to video with no per-modality tuning. Across FLUX.1, Z-Image-Turbo, Wan 2.1, and CogVideoX, it sets the state of the art for PTQ at several low-bit settings. It also pushes PTQ of image diffusion transformers to W2A4 with usable generation quality.
