Papers › u-μP: The Unit-Scaled Maximal Update Parametrization

u-μP: The Unit-Scaled Maximal Update Parametrization

24 Jul 2024arXiv:2407.17465archive 2025-07-28

Charlie Blake, Constantin Eichenberg, Josef Dean, Lukas Balles, Luke Y. Prince, Björn Deiseroth, Andres Felipe Cruz-Salinas, Carlo Luschi, Samuel Weinbach, Douglas Orr

The Maximal Update Parametrization (μP) aims to make the optimal hyperparameters (HPs) of a model independent of its size, allowing them to be swept using a cheap proxy model rather than the full-size target model. We present a new scheme, u-μP, which improves upon μP by combining it with Unit Scaling, a method for designing models that makes them easy to train in low-precision. The two techniques have a natural affinity: μP ensures that the scale of activations is independent of model size, and Unit Scaling ensures that activations, weights and gradients begin training with a scale of one. This synthesis opens the door to a simpler scheme, whose default values are near-optimal. This in turn facilitates a more efficient sweeping strategy, with u-μP models reaching a loss that is equal to or lower than comparable μP models and working out-of-the-box in FP8.

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 13 code samples harvested from 1 repository linked to this paper: 12 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 12 ran (8 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

graphcore-research/unit-scaling officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 12 ran (4 instrument-failed) · 1 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

13 samples harvested: 12 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 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.

2ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
5ran
1unverified

Licence: 0 of the 13 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 graphcore-research/unit-scaling. “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.

graphcore-research/unit-scaling official repository 13 samples, 12 ran (4 instrument-failed) · 1 unverified
Parameter unit_scaling/parameter.py ran Apache-2.0 (permissive) · 8d7406030299bc46 · report fixture: signature data:Tensor/2/float, mup_type:str/0/str, mup_scaling_depth:NoneType/0/? · returned Parameter · level recorded 2026-09-24
format_to_tuple unit_scaling/formats.py ran · honoured contract Apache-2.0 (permissive) · 070a400b0ece5434 · report fixture: signature format:FPFormat/0/? · returned tuple · level recorded 2026-09-24
generate__all__ unit_scaling/_internal_utils.py ran Apache-2.0 (permissive) · de8aa1c681baa450 · report fixture: signature module_name:str/0/str, include_imports:bool/0/bool · returned list · level recorded 2026-09-24
has_parameter_data unit_scaling/parameter.py ran · violated contract fingerprinted Apache-2.0 (permissive) · d19cc5ff648afebd · report fixture: signature parameter:Tensor/2/float · returned bool · level recorded 2026-09-24
logarithmic_interpolation unit_scaling/core/functional.py ran fingerprinted Apache-2.0 (permissive) · e0c95afd064e25ed · report fixture: signature alpha:float/0/float, lower:float/0/float, upper:float/0/float · returned float · level recorded 2026-09-24
mult_docstring unit_scaling/docs.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a1e2fc6500a07813 · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-24
rms in 6 papers unit_scaling/core/functional.py ran Apache-2.0 (permissive) · 7f174b2d78b36837 · report fixture: signature x:Tensor/2/float, dims:tuple/1/int, keepdim:bool/0/bool, eps:float/0/float · returned Tensor · level recorded 2026-09-24
scale_bwd unit_scaling/scale.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · af14bc3abf24163b · report fixture: signature input:Tensor/2/float, scale:float/0/float · returned Tensor · level recorded 2026-09-24
scale_fwd unit_scaling/scale.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 99e5d990030cdf9a · report fixture: signature input:Tensor/2/float, scale:float/0/float · returned Tensor · level recorded 2026-09-24
to_grad_input_scale unit_scaling/constraints.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 311ddf75624e8833 · report fixture: signature output_scale:float/0/float, grad_input_scale:float/0/float · returned float · level recorded 2026-09-24
to_left_grad_scale unit_scaling/constraints.py ran fingerprinted Apache-2.0 (permissive) · e57d5ac2fdb91999 · report fixture: signature output_scale:float/0/float, left_grad_scale:float/0/float, right_grad_scale:float/0/float · returned float · level recorded 2026-09-24
tuple_to_format unit_scaling/formats.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 07ba3009b696a3c2 · report fixture: signature t:tuple/1/int · returned FPFormat · level recorded 2026-09-24
to_output_scale unit_scaling/constraints.py unverified Apache-2.0 (permissive) · 873f0a22bcd0444f · report

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