Papers › Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

24 Oct 2024arXiv:2410.19123archive 2025-07-28

Ruisi Cai, Yeonju Ro, Geon-Woo Kim, Peihao Wang, Babak Ehteshami Bejnordi, Aditya Akella, Zhangyang Wang

The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved efficiency and performance. Despite their benefits, MoE models face significant challenges during inference, including inefficient memory management and suboptimal batching, due to misaligned design choices between the model architecture and the system policies. Furthermore, the conventional approach of training MoEs from scratch is increasingly prohibitive in terms of cost. In this paper, we propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models (in contrast to "upcycling" generalist MoEs), avoiding the high costs of ground-up training. Our approach employs activation sparsity to extract experts. To compose experts, we examine the widely-adopted layer-wise router design and show its redundancy, and thus we introduce the pre-gating router decoupled from the MoE backbone that facilitates system-friendly pre-computing and lookahead scheduling, enhancing expert-aware batching and caching. Our codesign therefore addresses critical gaps on both the algorithmic and system fronts, establishing a scalable and efficient alternative for LLM inference in resource-constrained settings. Read-ME outperforms other popular open-source dense models of similar scales, achieving improvements of up to 10.1% on MMLU, and improving mean end-to-end latency up to 6.1%. Codes are available at: https://github.com/VITA-Group/READ-ME.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 11 ran (7 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

vita-group/read-me officialmentioned in paperjaxSyntology: 16 samples, 11 ran (4 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
1ran · our draft was wrong
3ran; the contract check could not run
3ran
5unverified

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from vita-group/read-me. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

vita-group/read-me official repository 16 samples, 11 ran (4 instrument-failed) · 5 unverified
gelu_fast in 39 papers src/transformers/activations_tf.py ran · honoured contract fingerprinted no licence file found · pointer only · 37a5eed2dbd663ca · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
get_config_class_from_processor_class in 29 papers utils/create_dummy_models.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 3d999b95009c7537 · report fixture: signature processor_class:callable/0/? · returned type · level recorded 2026-09-25
get_intermediate moe_fication/get_activations.py ran no licence file found · pointer only · 834b335b08e359db · report fixture: signature model:callable/0/?, dataloader:list/1/dict · returned dict · level recorded 2026-09-26
get_processor_types_from_config_class in 29 papers utils/create_dummy_models.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 0c0b81b081919d8e · report fixture: signature config_class:callable/0/?, allowed_mappings:list/1/str · returned tuple · level recorded 2026-09-25
hertz_to_mel in 6 papers src/transformers/audio_utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 9a09cbf63a4ddff4 · report fixture: signature freq:ndarray/1/float, mel_scale:str/0/str · returned ndarray · level recorded 2026-09-26
loss_func in 26 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
moe_fication/train_red.py ran · our draft was wrong no licence file found · pointer only · c2877c234b2d0e3f · report fixture: signature feat:Tensor/3/float, pred:Tensor/3/float, mask_list:Tensor/2/float, mse_loss:callable/0/?, ce_loss:callable/0/?, accelerator:DummyAccelerator/0/?, rescale:bool/0/bool, idx:int/0/int · returned tuple · level recorded 2026-09-22
mel_filter_bank in 5 papers src/transformers/audio_utils.py ran no licence file found · pointer only · 7e7c601df5b22499 · report fixture: signature num_frequency_bins:int/0/int, num_mel_filters:int/0/int, min_frequency:float/0/float, max_frequency:float/0/float, sampling_rate:int/0/int, norm:NoneType/0/?, mel_scale:str/0/str, triangularize_in_mel_space:bool/0/bool · returned ndarray · level recorded 2026-09-26
mel_to_hertz in 6 papers src/transformers/audio_utils.py ran · honoured contract no licence file found · pointer only · 2650530d2f0dd9b2 · report fixture: signature mels:float/0/float, mel_scale:str/0/str · returned float64 · level recorded 2026-09-26
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input
src/transformers/activations_tf.py ran · honoured contract no licence file found · pointer only · cc8c8c3ebf0c343f · report fixture: signature x:ndarray/2/float · returned EagerTensor · level recorded 2026-09-26
quick_gelu in 43 papers src/transformers/activations_tf.py ran · honoured contract fingerprinted no licence file found · pointer only · e2d56cb91f999bef · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
thresholding moe_fication/generate_mask.py ran no licence file found · pointer only · 16b1aa5f7cc4afe6 · report fixture: signature data:dict/0/?, N_feature:int/0/int, remain_rate:float/0/float · returned dict · level recorded 2026-09-26
get_architectures_from_config_class in 29 papers utils/create_dummy_models.py unverified no licence file found · pointer only · b176efb26f72e507 · report
get_configuration_file in 13 papers src/transformers/configuration_utils.py unverified no licence file found · pointer only · dd3166a87bc972ff · report
main in 235 papers moe_fication/train_red.py unverified no licence file found · pointer only · 01f915e04e3d24d0 · report
save_activations moe_fication/get_activations.py unverified no licence file found · pointer only · 15b393fa2449cd6e · report
train_predictor moe_fication/train_red.py unverified no licence file found · pointer only · 2d40c8a96666defc · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Read-ME (graph method: Read-ME). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. loss_func entry · level 1 · ran · our draft was wrong · c2877c234b2d0e3f

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2410.19123") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

MMLUMixture-of-ExpertsScheduling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MoE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections