Pith. sign in

REVIEW 4 cited by

Quamba: A Post-Training Quantization Recipe for Selective State Space 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 2410.13229 v2 pith:WVUXSWOQ submitted 2024-10-17 cs.LG cs.AI

classification cs.LGcs.AI
keywords quantizationssmsmodelsaccuracyactivationsoutputselectivespace
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

State Space Models (SSMs) have emerged as an appealing alternative to Transformers for large language models, achieving state-of-the-art accuracy with constant memory complexity which allows for holding longer context lengths than attention-based networks. The superior computational efficiency of SSMs in long sequence modeling positions them favorably over Transformers in many scenarios. However, improving the efficiency of SSMs on request-intensive cloud-serving and resource-limited edge applications is still a formidable task. SSM quantization is a possible solution to this problem, making SSMs more suitable for wide deployment, while still maintaining their accuracy. Quantization is a common technique to reduce the model size and to utilize the low bit-width acceleration features on modern computing units, yet existing quantization techniques are poorly suited for SSMs. Most notably, SSMs have highly sensitive feature maps within the selective scan mechanism (i.e., linear recurrence) and massive outliers in the output activations which are not present in the output of token-mixing in the self-attention modules. To address this issue, we propose a static 8-bit per-tensor SSM quantization method which suppresses the maximum values of the input activations to the selective SSM for finer quantization precision and quantizes the output activations in an outlier-free space with Hadamard transform. Our 8-bit weight-activation quantized Mamba 2.8B SSM benefits from hardware acceleration and achieves a 1.72x lower generation latency on an Nvidia Orin Nano 8G, with only a 0.9% drop in average accuracy on zero-shot tasks. The experiments demonstrate the effectiveness and practical applicability of our approach for deploying SSM-based models of all sizes on both cloud and edge platforms.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing

    cs.LG 2025-08 conditional novelty 6.0 of 10

    An end-to-end Mamba edge accelerator using hardware-friendly approximations, INT8 quantization, and NAS achieves 4.95x-5.62x lower latency and 1.63x-19.9x smaller models than ViT/CNN baselines.

  2. Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs

    cs.CL 2026-08 conditional novelty 5.0 of 10

    On consumer GPUs, LoRA+ gives the best energy-focused fine-tuning score in 19 of 24 small-model task configurations, while QLoRA wins the memory-focused score when peak VRAM is the binding constraint.

  3. QS4D: Quantization-aware training for efficient hardware deployment of structured state-space sequential models

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Quantization-aware training allows S4D sequence models to run at much lower precision, cutting estimated hardware costs by up to two orders of magnitude while keeping accuracy.

  4. 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