Papers › Scaling Laws for Fine-Grained Mixture of Experts

Scaling Laws for Fine-Grained Mixture of Experts

12 Feb 2024arXiv:2402.07871archive 2025-07-28

Jakub Krajewski, Jan Ludziejewski, Kamil Adamczewski, Maciej Pióro, Michał Krutul, Szymon Antoniak, Kamil Ciebiera, Krystian Król, Tomasz Odrzygóźdź, Piotr Sankowski, Marek Cygan, Sebastian Jaszczur

Mixture of Experts (MoE) models have emerged as a primary solution for reducing the computational cost of Large Language Models. In this work, we analyze their scaling properties, incorporating an expanded range of variables. Specifically, we introduce a new hyperparameter, granularity, whose adjustment enables precise control over the size of the experts. Building on this, we establish scaling laws for fine-grained MoE, taking into account the number of training tokens, model size, and granularity. Leveraging these laws, we derive the optimal training configuration for a given computational budget. Our findings not only show that MoE models consistently outperform dense Transformers but also highlight that the efficiency gap between dense and MoE models widens as we scale up the model size and training budget. Furthermore, we demonstrate that the common practice of setting the size of experts in MoE to mirror the feed-forward layer is not optimal at almost any computational budget.

PaperPDFCodeCode Syntology ran

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 12 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 9 ran (4 with no instrument failure; 5 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

llm-random/llm-random officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 9 ran (5 instrument-failed) · 3 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

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
2ran
3unverified

Licence: 0 of the 12 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 llm-random/llm-random. “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.

llm-random/llm-random official repository 12 samples, 9 ran (5 instrument-failed) · 3 unverified
DenseEinMix lizrd/core/misc.py ran · our draft was wrong Apache-2.0 (permissive) · bedb49cd1f1a0de9 · report fixture: signature dinp:int/0/int, dout:int/0/int · returned EinMix · level recorded 2026-09-24
decode_bias_string lizrd/core/llm.py ran · violated contract Apache-2.0 (permissive) · 547620f3cabb823c · report fixture: signature bias:str/0/str · returned tuple · level recorded 2026-09-24
get_checkpoint_from_path lizrd/train/load_and_save_model.py ran · our draft was wrong Apache-2.0 (permissive) · ab08b9a954599b80 · report fixture: signature load_weights_path:str/0/str · returned dict · level recorded 2026-09-24
get_init_fun lizrd/core/initialization.py ran · our draft was wrong Apache-2.0 (permissive) · 60ccfd22a4396cc8 · report fixture: signature init_type:str/0/str, init_scale:float/0/float · returned function · level recorded 2026-09-24
get_init_weight lizrd/core/initialization.py ran Apache-2.0 (permissive) · 598beaf614d19cd9 · report fixture: signature shape:tuple/1/int, fan_in:int/0/int, init_type:str/0/str, scale:float/0/float, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-24
get_latest_checkpoint in 13 papers lizrd/train/load_and_save_model.py ran · our draft was wrong Apache-2.0 (permissive) · 4a3ee9eeb13ba96e · report fixture: signature dir_path:PosixPath/0/? · returned PosixPath · level recorded 2026-09-24
get_registered_name research/token_reduction/layer_manager.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · e1f8a72b6a93def9 · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-24
init_kaiming_uniform lizrd/core/initialization.py ran Apache-2.0 (permissive) · 4a31b2005d286506 · report fixture: signature shape:tuple/1/int, fan_in:int/0/int, scale:float/0/float, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-24
stop_gradient in 5 papers lizrd/core/misc.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 17f4154f5359d704 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
einsum in 6 papers lizrd/core/misc.py unverified Apache-2.0 (permissive) · 4418dc5a6351b911 · report
wrap_in_ddp lizrd/core/distributed.py unverified Apache-2.0 (permissive) · 01ee119a712b62ff · report
wrap_in_fsdp lizrd/core/distributed.py unverified Apache-2.0 (permissive) · ef09afdda4279503 · report

Tasks

Mixture-of-Experts

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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