Pith. sign in

REVIEW 2 cited by

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy

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 2411.03513 v1 pith:XQYIY75K submitted 2024-11-05 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords slicingdynamiclayerconstantmodelperformanceredundancyapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT. By transitioning from constant to dynamic slicing, our method leverages the newly proposed Layer Redundancy (LR) score, which assesses how much change each layer changes its input by measuring the cosine similarity of the input to the output of the layer. We use this score to prune parts of individual layers based on redundancy in such a way that the average pruned percentage for all layers is a fixed value. We conducted extensive experiments using models like Llama3-8B and Mistral-7B on multiple datasets, evaluating different slicing bases and percentages to determine optimal configurations that balance efficiency and performance. Our findings show that our dynamic slicing approach not only maintains but, in many cases, enhances model performance compared to the baseline established by constant slicing methods. For instance, in several settings, we see performance improvements of up to 5% over the SliceGPT baseline. Additionally, a perplexity decrease by as much as 7% was observed across multiple benchmarks, validating the effectiveness of our method. The code, model weights, and datasets are open-sourced at https://github.com/RazvanDu/DynamicSlicing.

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. LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment

    cs.CL 2024-12 conditional novelty 4.0 of 10

    LSAQ assigns higher quantization precision to layers deemed important by the overlap of top-k input and output token sets, and reports small accuracy and perplexity gains over a cosine-similarity baseline.

  2. 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.

Pith tools