Towards Network-Efficient Cross-Regional Inference via Learned Activation Compression
TL;DR
Feather is presented, a system that reduces this overhead by compressing intermediate activations before transmission and reconstructing them before downstream layers resume execution, consistently outperforming existing compression schemes, including linear autoencoder, PCA, and SVD.
Abstract
Large transformer models are increasingly deployed across geographically distributed GPU clusters due to capacity, cost, and locality constraints. When inference is partitioned across sites, intermediate activations must be transmitted over wide area network (WAN) links at each partition boundary, introducing significant communication overhead. We present Feather, a system that reduces this overhead by compressing intermediate activations before transmission and reconstructing them before downstream layers resume execution. Feather learns a compact representation of activation tensors using a lightweight neural codec trained with a reconstruction objective while keeping the original model frozen. Across encoder and decoder transformer models, Feather achieves up to 48× activation compression while maintaining accuracy close to the baseline model. Under representative WAN conditions (e.g., 10 Gbps bandwidth and a 10 ms RTT), this reduction yields up to 4.96× improvement in end-to-end latency, consistently outperforming existing compression schemes, including linear autoencoder, PCA, and SVD.