Saved in:
Bibliographic Details
Main Authors: Guo, Yipin, Joshi, Siddharth
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.01708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910202377273344
author Guo, Yipin
Joshi, Siddharth
author_facet Guo, Yipin
Joshi, Siddharth
contents Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to better load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers generate a KV cache that must be transferred to decode workers before token generation can begin. With these workers residing on different physical systems, this transfer becomes a significant bottleneck to serving LLMs at scale. This bottleneck gets exacerbated for long-input and agentic workloads. Existing lossless codecs are not suited to this setting as they primarily target offline weight compression, run on the CPU, or use variable-length coding whose decompression is fast but compression is too slow to keep up with KV production during prefill. We introduce SplitZip, a GPU-friendly lossless compressor for KV cache transfer that preserves KV tensors bitwise and integrates into existing serving frameworks without changes to model execution. SplitZip exploits redundancy in floating-point exponents of KV activations, encoding the most frequent exponent values with fixed-length codes and routing rare exponents through a sparse escape stream of (position, value). An offline calibrated top-16 exponent codebook eliminates online-histogramming, while the regular dense path and sparse escape correction make both encoding and decoding efficient on GPUs. On real BF16 activation tensors, SplitZip achieves $613.3$ GB/s compression throughput and $2181.8$ GB/s decompression throughput, substantially outperforming prior lossless compressors on the latency-critical codec path. End-to-end transfer experiments show up to $1.32\times$ speedup for BF16 KV cache transfer, $1.30\times$ speedup for TTFT, and $1.23\times$ increase on Request Throughput. The same approach extends to FP8 KV caches, providing up to $1.14\times$ compression over native E5M2.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01708
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
Guo, Yipin
Joshi, Siddharth
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to better load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers generate a KV cache that must be transferred to decode workers before token generation can begin. With these workers residing on different physical systems, this transfer becomes a significant bottleneck to serving LLMs at scale. This bottleneck gets exacerbated for long-input and agentic workloads. Existing lossless codecs are not suited to this setting as they primarily target offline weight compression, run on the CPU, or use variable-length coding whose decompression is fast but compression is too slow to keep up with KV production during prefill. We introduce SplitZip, a GPU-friendly lossless compressor for KV cache transfer that preserves KV tensors bitwise and integrates into existing serving frameworks without changes to model execution. SplitZip exploits redundancy in floating-point exponents of KV activations, encoding the most frequent exponent values with fixed-length codes and routing rare exponents through a sparse escape stream of (position, value). An offline calibrated top-16 exponent codebook eliminates online-histogramming, while the regular dense path and sparse escape correction make both encoding and decoding efficient on GPUs. On real BF16 activation tensors, SplitZip achieves $613.3$ GB/s compression throughput and $2181.8$ GB/s decompression throughput, substantially outperforming prior lossless compressors on the latency-critical codec path. End-to-end transfer experiments show up to $1.32\times$ speedup for BF16 KV cache transfer, $1.30\times$ speedup for TTFT, and $1.23\times$ increase on Request Throughput. The same approach extends to FP8 KV caches, providing up to $1.14\times$ compression over native E5M2.
title SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2605.01708