Pith. sign in

REVIEW 3 cited by

Mamba-PTQ: Outlier Channels in Recurrent 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 2407.12397 v1 pith:4772KWBY submitted 2024-07-17 cs.LG cs.AIcs.NE

classification cs.LGcs.AIcs.NE
keywords llmsmodelsrecurrentquantizationlayersactivationattention-basedchannels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Modern recurrent layers are emerging as a promising path toward edge deployment of foundation models, especially in the context of large language models (LLMs). Compressing the whole input sequence in a finite-dimensional representation enables recurrent layers to model long-range dependencies while maintaining a constant inference cost for each token and a fixed memory requirement. However, the practical deployment of LLMs in resource-limited environments often requires further model compression, such as quantization and pruning. While these techniques are well-established for attention-based models, their effects on recurrent layers remain underexplored. In this preliminary work, we focus on post-training quantization for recurrent LLMs and show that Mamba models exhibit the same pattern of outlier channels observed in attention-based LLMs. We show that the reason for the difficulty of quantizing SSMs is caused by activation outliers, similar to those observed in transformer-based LLMs. We report baseline results for post-training quantization of Mamba that do not take into account the activation outliers and suggest first steps for outlier-aware quantization.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Neural Weight Compression for Language Models

    cs.LG 2025-10 conditional novelty 6.0 of 10

    A single learned neural codec, trained once on real LLM weights, compresses Llama-scale models to 4-6 bits per weight with near-FP16 accuracy, beating hand-crafted quantization at those bitrates.

  2. Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2

    cs.NE 2025-02 reject novelty 6.0 of 10

    A 370M MatMul-free LLM is mapped onto Intel Loihi 2 and reported to achieve up to 3x higher generation throughput with about 2x less energy than transformer LLMs on an edge GPU, based on preliminary measurements that ...

  3. Quantizing Small-Scale State-Space Models for Edge AI

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Quantization-aware training with a frozen state matrix lifts sequential MNIST accuracy from 40% under post-training quantization to 96%, and a heterogeneous precision scheme cuts memory by 6 times.

Pith tools