Pith. sign in

REVIEW 2 cited by

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.02812 v1 pith:YJPQGCO3 submitted 2025-03-04 cs.CL cs.AI

classification cs.CLcs.AI
keywords compressiongenerationq-filterscacheattentionduringefficientkey-value
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Autoregressive language models rely on a Key-Value (KV) Cache, which avoids re-computing past hidden states during generation, making it faster. As model sizes and context lengths grow, the KV Cache becomes a significant memory bottleneck, which calls for compression methods that limit its size during generation. In this paper, we discover surprising properties of Query (Q) and Key (K) vectors that allow us to efficiently approximate attention scores without computing the attention maps. We propose Q-Filters, a training-free KV Cache compression method that filters out less crucial Key-Value pairs based on a single context-agnostic projection. Contrarily to many alternatives, Q-Filters is compatible with FlashAttention, as it does not require direct access to attention weights. Experimental results in long-context settings demonstrate that Q-Filters is competitive with attention-based compression methods such as SnapKV in retrieval tasks while consistently outperforming efficient compression schemes such as Streaming-LLM in generation setups. Notably, Q-Filters achieves a 99% accuracy in the needle-in-a-haystack task with a x32 compression level while reducing the generation perplexity drop by up to 65% in text generation compared to Streaming-LLM.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models

    cs.AI 2026-08 accept novelty 6.0 of 10

    KVDiagnosis is a diagnostic benchmark that pairs 59,800 compressed runs with FullCache controls and attaches cache, likelihood, attention, and decoding measurements to 12,520 failure rows, finding 63.2% of failures ha...

  2. RCStat: A Statistical Framework for using Relative Contextualization in Transformers

    cs.CL 2025-06 conditional novelty 6.0 of 10

    RCStat uses pre-softmax attention logits to define a Relative Contextualization score that improves adaptive KV-cache eviction and attention-head selection for attribution on LLaMA models.

Pith tools