Pith. sign in

REVIEW 5 cited by

Layer-Condensed KV Cache for Efficient Inference of Large Language Models

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 2405.10637 v2 pith:ZOZN4RW4 submitted 2024-05-17 cs.CL

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

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the transformer architecture consumes a significant amount of memory, especially when the number of layers is large for deep language models. In this paper, we propose a novel method that only computes and caches the KVs of a small number of layers, thus significantly saving memory consumption and improving inference throughput. Our experiments on large language models show that our method achieves up to 26$\times$ higher throughput than standard transformers and competitive performance in language modeling and downstream tasks. In addition, our method is orthogonal to existing transformer memory-saving techniques, so it is straightforward to integrate them with our model, achieving further improvement in inference efficiency. Our code is available at https://github.com/whyNLP/LCKV.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Long-context memory can be organized by caching intermediate residual states and recomputing only query-conditioned upper layers over a bounded retrieved pack.

  2. Do Value Vectors in Deep Layers Need Context from the Residual Stream?

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    Deep transformer layers can replace context-dependent value vectors with per-token lookup tables (Bank of Values), improving validation loss and the 21-benchmark average at 135M–780M while cutting FLOPs and the value cache.

  3. CaliDrop: KV Cache Compression with Calibration

    cs.CL 2025-07 conditional novelty 6.0 of 10

    CaliDrop adds a stale-query calibration term on top of token eviction, improving accuracy at high KV compression ratios with modest throughput overhead.

  4. Structured Thoughts For Improved Reasoning And Context Pruning

    cs.CL 2026-07 conditional novelty 5.5 of 10

    Structured try/outcome SFT improves math reasoning by up to 8% over standard SFT and enables pruning ~85% of context with ~9% accuracy drop.

  5. TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference

    cs.LG 2025-08 conditional novelty 5.0 of 10

    TPLA splits the latent KV cache across tensor-parallel GPUs while keeping every head's full view, yielding 1.79x and 1.93x decode speedups on DeepSeek-V3 and Kimi-K2 at 32K context with modest accuracy loss.

Pith tools