arXiv AI
Attention-Weighted Value Projection for KV-Cache Compression
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 7
AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD
arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free r...
arXiv AI
Jun 9
STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control
arXiv:2606. 08382v1 Announce Type: cross Abstract: Low-rank projection has emerged as a promising approach for compressing the KV cache by exploiting hidden-dimension redundancy.
arXiv Machine Learning
Jul 28
DynaCalKV: Key-Value Cache Compression via Head Grouping and Adaptive Rank Allocation
arXiv:2607. 24331v1 Announce Type: new Abstract: As the inference phase of Large Language Models (LLMs) requires handling long context windows, the Key-Value (KV) cache initially appears to address this challenge but eventually becomes a significant bottleneck as the context window continues to grow.
arXiv Machine Learning
Sep 22
KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation
arXiv:2609.24298v1 Announce Type: new Abstract: What limits KV-cache compression at extreme bit-rates? We argue that it is not the choice of compression scheme, but how its budget is allocated across...
arXiv AI
Oct 15
BELT : BEhavior-Aligned Low-Rank KV Cache Compression with Learned Top-k Rank Allocation
arXiv:2610.17966v1 Announce Type: cross Abstract: Long-context inference makes the key-value (KV) cache a major memory bottleneck for large language models. We propose BELT, a low-rank KV cache compr...
arXiv AI
Oct 5
CORE: COverage CAlibration and Evicted-Mass REdistribution for KV Cache
arXiv:2610.02235v1 Announce Type: cross Abstract: Long-context decoding is increasingly constrained by key--value (KV) cache memory and bandwidth. Existing fixed-budget compression methods typically...