@no_stp_on_snek: Always start with uncompressed k and compressed V and go more aggressively from there. Model families have different se…

X AI KOLs Following News

Summary

A tip on KV-cache compression for transformer models: start with uncompressed keys and compressed values, then adjust based on model family sensitivity; try asymmetric before symmetric compression.

Always start with uncompressed k and compressed V and go more aggressively from there. Model families have different sensitivities to K compression in particular. Asym first over sym.
Original Article
View Cached Full Text

Cached at: 05/23/26, 06:11 PM

Always start with uncompressed k and compressed V and go more aggressively from there.

Model families have different sensitivities to K compression in particular.

Asym first over sym.

Similar Articles

The risk of KV cache compression

arXiv cs.LG

This paper theoretically characterizes the minimax risk of KV cache compression in transformers, providing design principles for accurate compression under causal masking, and instantiates them in a practical algorithm with promising results on LongBench.

KV Cache Compression 900000x Beyond TurboQuant and Per-Vector Shannon Limit

Hacker News Top

A new paper proposes sequential KV cache compression using probabilistic language tries and predictive delta coding, achieving theoretical compression ratios of ~914,000× beyond TurboQuant by exploiting the sequential structure of language model tokens rather than treating vectors independently.