Is PagedAttention superseded?

PagedAttention (KV-cache compression): superseded — cited as a baseline and beaten by newer methods. 5 paper(s) critique it, 0 beat it on benchmarks — #37 of 234 most-superseded. Sub-problem: cluster led by Palu. Newer alternatives in the same sub-problem include ArborKV, RDKV, EchoKV, VQKV, Self-Indexing KVCache.

Method Drift›KV-cache compression

Superseded baseline#37 of 234 most-superseded

PagedAttention

KV-cache compression

superseded — cited as a baseline and beaten by newer methods

5 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites PagedAttention as a baseline.

“System-level approaches like PagedAttention optimize KV storage to mitigate fragmentation, yet remain agnostic to the semantic importance of content under tight budgets.”
— ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning
“Orthogonally, system-level solutions like PagedAttention kwon2023efficientmemorymanagementlarge optimize memory management but do not reduce the fundamental size of the cache itself.”
— SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression
“Despite these advancements, no existing long-context benchmarks evaluate KV cache reuse scenarios.”
— SCBench: A KV Cache-Centric Analysis of Long-Context Methods
“applies paging techniques to reduce memory fragmentation but maintains full precision storage”
— GPU-Accelerated INT8 Quantization for KV Cache Compression in Large Language Models
“These systems treat all transferred KV at uniform precision; adds per-token precision differentiation”
— SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.