Haibin's blogfragments
Chunked KV-Cache Compression
A nice paper showing a problem inside the Chunked KV-Cache Compression. https://arxiv.org/pdf/2609.36322 Models like dpskv4 used chunked kv cache compression, it compressed 8 tokens each time into a kv vector to save kv…
A nice paper showing a problem inside the Chunked KV-Cache Compression. https://arxiv.org/pdf/2609.36322 Models like dpskv4 used chunked kv cache compression, it compressed 8 tokens each time into a kv vector to save kv memory. However the paper finds a pattern called phase specialization: for example, a token may be preserved well when it falls into 1st token of the 8 token chunks (phase 1), but become degraded if places it in 2nd/phase 2.
(DPSKv4 use sliding window 8 with steps 4. That means for compression, it first compressed 0-7, then 4-11, then 8-15 etc)
To learn what is chunked kv cache compression https://arxiv.org/pdf/2502.00299
If you need to cite this post
Haibin Lai. (October 9, 2026). “Chunked KV-Cache Compression” [Blog post]. Retrieved from https://www.haibinlaiblog.top/posts/chunked-kv-cache-compression/
@online{lai-chunked-kv-cache-compression,
title={Chunked KV-Cache Compression},
author={Haibin Lai},
year={2026},
url={https://www.haibinlaiblog.top/posts/chunked-kv-cache-compression/},
}