Pith. sign in

REVIEW 1 cited by

LoMA: Lossless Compressed Memory Attention

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 2401.09486 v2 pith:QM6FKZHE submitted 2024-01-16 cs.LG cs.CL

classification cs.LGcs.CL
keywords memorycachecompressedcompressionlomalosslessattentioncomputational
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Large Language Models (LLMs) face limitations due to the high demand on GPU memory and computational resources when handling long contexts. While sparsify the Key-Value (KV) cache of transformer model is a typical strategy to alleviate resource usage, it unavoidably results in the loss of information. We introduce Lossless Compressed Memory Attention (LoMA), a novel approach that enables lossless compression of the KV cache, thereby reducing the memory and computational demands during autoregressive generation. LoMA incorporates a specialized training or fine-tuning precedure alongside an autoregressive generation algorithm optimized for the compressed context. Our method compresses the KV cache after every $tc$ generated tokens with a compression ratio of $c$ and a target compressed length $t$, and this process occurs within a single inference pass without dependency on auxiliary models. We engineered an efficient training scheme involving specific inputs, attention masks, and position identifiers to instill this compression capability. Experimental validation has demonstrated that LoMA significantly reducing computational consumption and memory usage through achieving lossless KV cache compression.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression

    cs.CL 2025-07 conditional novelty 5.0 of 10

    FAEDKV compresses the KV cache by keeping the most important Fourier-frequency components of cached keys and values, reporting gains over eviction baselines on LongBench and position-flat retrieval on needle-in-a-hays...

Pith tools