Pith. sign in

REVIEW 10 cited by

You Only Cache Once: Decoder-Decoder Architectures for 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 2405.05254 v2 pith:P7XRNOTI submitted 2024-05-08 cs.CL

You Only Cache Once: Decoder-Decoder Architectures for Language Models

classification cs.CL
keywords yococachesmodelonceonlycontextcross-decoderdecoder-decoder
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce a decoder-decoder architecture, YOCO, for large language models, which only caches key-value pairs once. It consists of two components, i.e., a cross-decoder stacked upon a self-decoder. The self-decoder efficiently encodes global key-value (KV) caches that are reused by the cross-decoder via cross-attention. The overall model behaves like a decoder-only Transformer, although YOCO only caches once. The design substantially reduces GPU memory demands, yet retains global attention capability. Additionally, the computation flow enables prefilling to early exit without changing the final output, thereby significantly speeding up the prefill stage. Experimental results demonstrate that YOCO achieves favorable performance compared to Transformer in various settings of scaling up model size and number of training tokens. We also extend YOCO to 1M context length with near-perfect needle retrieval accuracy. The profiling results show that YOCO improves inference memory, prefill latency, and throughput by orders of magnitude across context lengths and model sizes. Code is available at https://aka.ms/YOCO.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

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

  1. Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression

    cs.CL 2025-02 unverdicted novelty 7.0

    KV cache compression causes task-dependent degradation in high-density reasoning due to disrupted CoT links; ShotKV mitigates this by preserving few-shot examples as indivisible semantic units through phase separation...

  2. What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

    cs.LG 2026-07 conditional novelty 6.0

    KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.

  3. You Only Index Once: Cross-Layer Sparse Attention with Shared Routing

    cs.CL 2026-06 unverdicted novelty 6.0

    CLSA shares both KV cache and routing indices across decoder layers to amortize top-k selection, delivering up to 7.6x decoding speedup and 17.1x throughput at 128K context while preserving accuracy.

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

    cs.CL 2026-06 unverdicted novelty 6.0

    Deeper transformer layers benefit from context-free token-specific value vectors in a Bank of Values lookup table, improving performance over standard attention with less compute.

  5. Block-Based Double Decoders

    cs.LG 2026-05 unverdicted novelty 6.0

    Block-based double decoders use doubly-causal block attention masks to combine decoder-only training efficiency with encoder-decoder inference efficiency, outperforming standard encoder-decoders in scaling experiments.

  6. Block-Based Double Decoders

    cs.LG 2026-05 unverdicted novelty 6.0

    Block-based double decoders achieve full supervision in pretraining like decoder-only models and efficient inference like encoder-decoders through doubly-causal block-based attention masks, outperforming encoder-decod...

  7. Kimi Linear: An Expressive, Efficient Attention Architecture

    cs.CL 2025-10 unverdicted novelty 6.0

    Kimi Linear hybridizes linear attention with a new KDA module to beat full attention on tasks while slashing KV cache by 75% and speeding decoding up to 6x.

  8. LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

    cs.CL 2024-10 unverdicted novelty 6.0

    LightTransfer identifies lazy layers in LLMs like LLaMA and replaces their attention with streaming attention to form hybrid models, delivering up to 2.17x throughput with under 1.5% drop on LongBench and strong resul...

  9. Q-Delta: Beyond Key-Value Associative State Evolution

    cs.AI 2026-06 unverdicted novelty 5.0

    Q-Delta extends linear attention by introducing a query-conditioned delta rule that incorporates mixed key-query errors into recurrent state updates for improved stability and performance.

  10. Gated Delta Networks: Improving Mamba2 with Delta Rule

    cs.CL 2024-12 unverdicted novelty 5.0

    Gated DeltaNet integrates gating and delta rules into linear transformers, outperforming Mamba2 and DeltaNet on language modeling, reasoning, retrieval, and long-context tasks.