FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding

arXiv:2609.24433v1 Announce Type: new Abstract: Low-bit vision-language-action inference must reduce observation-to-action latency while preserving robot behavior. We present FoldQuantVLA, a post-training quantization framework that carries a consistent activation representation through calibration, weight rounding, and native integer execution. It combines channel scaling and block Hadamard transforms with dynamic per-token quantization, without policy retraining. Custom TensorRT plugins execute projections in both the language backbone and iterative action expert with four-bit weights and activations (W4A4) on Ada GPUs and Jetson AGX Orin. Evaluation spans LIBERO, SimplerEnv, and two robot platforms. Across three GR00T checkpoints and pi_{0.5}, W4A4 achieves 1.20 to 1.33imes speedups over floating-point TensorRT on Orin and 1.25 to 1.52imes on desktop. Retaining language attention-output and feed-forward down projections at eight bits (W8A8) improves held-out action fidelity on all four checkpoints. Across four real-robot tasks, this configuration raises observed GR00T N1.7 success from 80.0% with uniform W4A4 to 92.5% over 80 trials per configuration, with a measured additional Orin latency of 1 ms.

Source: arXiv cs.RO | 2026-09-22