Pith. sign in

REVIEW 9 cited by

BlackMamba: Mixture of Experts for 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 2402.01771 v1 pith:5IEGTCO6 submitted 2024-02-01 cs.CL cs.AIcs.DCcs.LG

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

State-space models (SSMs) have recently demonstrated competitive performance to transformers at large-scale language modeling benchmarks while achieving linear time and memory complexity as a function of sequence length. Mamba, a recently released SSM model, shows impressive performance in both language modeling and long sequence processing tasks. Simultaneously, mixture-of-expert (MoE) models have shown remarkable performance while significantly reducing the compute and latency costs of inference at the expense of a larger memory footprint. In this paper, we present BlackMamba, a novel architecture that combines the Mamba SSM with MoE to obtain the benefits of both. We demonstrate that BlackMamba performs competitively against both Mamba and transformer baselines, and outperforms in inference and training FLOPs. We fully train and open-source 340M/1.5B and 630M/2.8B BlackMamba models on 300B tokens of a custom dataset. We show that BlackMamba inherits and combines both of the benefits of SSM and MoE architectures, combining linear-complexity generation from SSM with cheap and fast inference from MoE. We release all weights, checkpoints, and inference code open-source. Inference code at: https://github.com/Zyphra/BlackMamba

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. Hidden State Poisoning Attacks against Mamba-based Language Models

    cs.CL 2026-01 unverdicted novelty 7.0 of 10

    Short input phrases can irreversibly overwrite hidden states in Mamba models, impairing information retrieval on a new benchmark while leaving pure Transformer models unaffected.

  2. WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    WiSP achieves up to 1.95x decode throughput on low-resource MoE serving by dynamically paging reused experts and using MV-WSA to allocate VRAM between experts and KV cache, with the offline policy performing well on b...

  3. ZAYA1-8B Technical Report

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.

  4. ZUNA1.1: A more flexible EEG foundation model for Denoising and Super-resolution

    cs.LG 2026-07 conditional novelty 5.0 of 10

    ZUNA1.1, an open-source 380M EEG diffusion autoencoder, reconstructs variable-length, flexibly masked EEG at least as well as its predecessor and far better than spherical spline interpolation.

  5. Efficient RWKV-based Representation Learning for 3D Point Clouds

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    Introduces P-RWKV block and PointER self-supervised framework to adapt RWKV for efficient 3D point cloud representation learning.

  6. ZONOS2 Technical Report

    cs.SD 2026-06 unverdicted novelty 4.0 of 10

    ZONOS2 8B is a scaled MoE TTS model with 900M active parameters trained on 6M hours of data that reports competitive SOTA results on naturalness, speaker similarity, WER, and a new ZTTS1-Eval benchmark while releasing...

  7. ZONOS2 Technical Report

    cs.SD 2026-06 unverdicted novelty 3.0 of 10

    ZONOS2 8B scales a prior TTS system to 8B parameters with MoE architecture and 6M hours of data, reporting competitive benchmark performance on naturalness and speaker similarity while releasing weights.

  8. A Survey on Efficient Inference for Large Language Models

    cs.CL 2024-04 accept novelty 3.0 of 10

    The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.

  9. A Survey of Mamba

    cs.LG 2024-08 unverdicted novelty 2.0 of 10

    The paper consolidates existing research on Mamba models, their architecture variants, adaptations to different data modalities, and applications across domains.

Pith tools