Pith. sign in

REVIEW 9 cited by

MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding

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 2406.09297 v3 pith:QQQUQSKZ submitted 2024-06-13 cs.LG

classification cs.LG
keywords memorymlkvkey-valuesizetransformerattentionefficientinference
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Auto-regressive inference of transformers benefit greatly from Key-Value (KV) caching, but can lead to major memory bottlenecks as model size, batch size, and sequence length grow at scale. We introduce Multi-Layer Key-Value (MLKV) sharing, a novel approach extending KV sharing across transformer layers to reduce memory usage beyond what was possible with Multi-Query Attention (MQA) and Grouped-Query Attention (GQA). Evaluations on various NLP benchmarks and inference metrics using uptrained Pythia-160M variants demonstrate that MLKV significantly reduces memory usage with minimal performance loss, reducing KV cache size down to a factor of 6x compared to MQA. These results highlight MLKV's potential for efficient deployment of transformer models at scale. We provide code at https://github.com/zaydzuhri/pythia-mlkv

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

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

  1. Accurate KV Cache Quantization with Outlier Tokens Tracing

    cs.CL 2025-05 conditional novelty 6.0 of 10

    OTT improves 2-bit KV cache quantization by identifying low-magnitude key outlier tokens and keeping them full-precision, outperforming KIVI across several LLMs and benchmarks.

  2. TransMLA: Multi-Head Latent Attention Is All You Need

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A framework that converts pretrained GQA models into MLA models using RoRoPE, FreqFold, and balanced KV low-rank compression, regaining baseline performance with only a few billion fine-tuning tokens.

  3. CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning

    cs.LG 2024-11 reject novelty 6.0 of 10

    Attention pairs (Q-K and V-O) are SVD-decomposed so pruning or fine-tuning touches only a small singular-factor matrix, yielding better pruning tolerance and small PEFT gains.

  4. SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling

    cs.LG 2026-06 conditional novelty 5.0 of 10

    A LoRA update split into several fixed, differently-scaled low-rank experts with orthogonal input directions improves fine-tuning accuracy at the same parameter count.

  5. Chain-of-Model Learning for Language Model

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A nested Transformer with causally ordered hidden chains offers multiple sub-model sizes, chain-based expansion, and KV-cache sharing for faster prefilling.

  6. Multi-matrix Factorization Attention

    cs.LG 2024-12 conditional novelty 5.0 of 10

    MFA and MFA-KR factorize the attention QK circuit with shared low-rank key and value projections, matching or beating MHA accuracy at a small fraction of the KV cache.

  7. A Survey on Large Language Model Acceleration based on KV Cache Management

    cs.AI 2024-12 conditional novelty 4.0 of 10

    A survey that classifies KV cache management techniques for faster LLM inference into token-level, model-level, and system-level categories, with benchmark resources.

  8. More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression

    cs.CL 2024-12 conditional novelty 4.0 of 10

    Storing 4x as many KV cache tokens at 4-bit precision outperforms storing 1x tokens at 16-bit precision on long-context benchmarks at equal data-memory budgets.

  9. Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures

    cs.LG 2025-08 unverdicted novelty 3.0 of 10

    Memory-augmented Transformer research is organized into a three-axis taxonomy bridging neuroscience memory concepts to network designs, but no new result is produced.

Pith tools