Pith. sign in

REVIEW 5 cited by

Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production

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 2211.10017 v1 pith:VXKTKKIG submitted 2022-11-18 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords modelslargescalesignificantlybetterdeployinferencelanguage
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Mixture of Experts (MoE) models with conditional execution of sparsely activated layers have enabled training models with a much larger number of parameters. As a result, these models have achieved significantly better quality on various natural language processing tasks including machine translation. However, it remains challenging to deploy such models in real-life scenarios due to the large memory requirements and inefficient inference. In this work, we introduce a highly efficient inference framework with several optimization approaches to accelerate the computation of sparse models and cut down the memory consumption significantly. While we achieve up to 26x speed-up in terms of throughput, we also reduce the model size almost to one eighth of the original 32-bit float model by quantizing expert weights into 4-bit integers. As a result, we are able to deploy 136x larger models with 27% less cost and significantly better quality compared to the existing solutions. This enables a paradigm shift in deploying large scale multilingual MoE transformers models replacing the traditional practice of distilling teacher models into dozens of smaller models per language or task.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression

    cs.AR 2025-05 conditional novelty 6.0 of 10

    Ecco compresses LLM weights and KV cache with shared k-means patterns and Huffman coding, and adds a parallel hardware decoder, to roughly quadruple memory capacity and speed up decode by up to ~3x.

  2. MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

    cs.LG 2025-05 conditional novelty 6.0 of 10

    MxMoE assigns mixed bitwidths at the linear-block level in MoE models using an ILP that balances measured quantization sensitivity and expert activation frequency, then auto-generates fused Group-GEMM kernels, improvi...

  3. TileLang: A Composable Tiled Programming Model for AI Systems

    cs.LG 2025-04 conditional novelty 6.0 of 10

    TileLang is a tiled DSL and compiler that decouples scheduling from dataflow and reports performance at or near state-of-the-art vendor kernels on modern GPUs.

  4. Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference

    cs.AI 2024-12 conditional novelty 6.0 of 10

    A quantized two-step all-reduce kernel reduces tensor-parallel communication overhead in LLM inference, achieving up to 3.18x faster all-reduce and 2.06x TTFT speedup on L40 GPUs.

  5. A Survey on Inference Optimization Techniques for Mixture of Experts Models

    cs.LG 2024-12 conditional novelty 3.0 of 10

    A structured survey of MoE inference optimization that categorizes existing techniques into model, system, and hardware levels and summarizes reported speedups and memory savings.

Pith tools