TorchCraft on A100 without cuequivariance kernels
A TorchCraft design run on NVIDIA A100 GPU with 80 GB memory, with the default torch kernels, timed per design.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Model Capabilities & Hardware Requirements
Deployment facts recorded for TorchCraft on A100 without cuequivariance kernels. Fields the record does not carry are marked not recorded.
Evaluated Checkpoint: As published in arXiv:2609.19770v1 Supplementary Table S9
Evaluations and results
5 evaluations · 5 results. Different protocols are not a single leaderboard.
Dataset: TorchCraft runtime benchmark design runs
Sorted by Runtime (wall-clock minutes per design at 100 residues, batch size 2 run divided by 2) (lower is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | Protocol and dataset | Runtime (wall-clock minutes per design at 100 residues, batch size 2 run divided by 2) | Runtime (wall-clock minutes per design at 200 residues, batch size 2 run divided by 2) | Runtime (wall-clock minutes per design at 300 residues, batch size 2 run divided by 2) | Runtime (wall-clock minutes per design at 400 residues, batch size 2 run divided by 2) | Runtime (wall-clock minutes per design at 500 residues, batch size 2 run divided by 2) |
|---|---|---|---|---|---|---|
| TorchCraft on A100 without cuequivariance kernelsEvaluation | TorchCraft runtime per design at 100 residues | 4.76 | Not reported | Not reported | Not reported | Not reported |
| TorchCraft on A100 without cuequivariance kernelsEvaluation | TorchCraft runtime per design at 200 residues | Not reported | 7.96 | Not reported | Not reported | Not reported |
| TorchCraft on A100 without cuequivariance kernelsEvaluation | TorchCraft runtime per design at 300 residues | Not reported | Not reported | 13.1 | Not reported | Not reported |
| TorchCraft on A100 without cuequivariance kernelsEvaluation | TorchCraft runtime per design at 400 residues | Not reported | Not reported | Not reported | 21.6 | Not reported |
| TorchCraft on A100 without cuequivariance kernelsEvaluation | TorchCraft runtime per design at 500 residues | Not reported | Not reported | Not reported | Not reported | 33.3 |
All 5 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: TorchCraft on A100 without cuequivariance kernels | Protocol: TorchCraft runtime per design at 100 residues Dataset: TorchCraft runtime benchmark design runs | 4.76 Runtime (wall-clock minutes per design at 100 residues, batch size 2 run divided by 2) minute · lower Uncertainty: Not reported by the source: No spread is printed; GPU cells are stated to be the mean of three runs without a spread. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceTorchCraft runtime at 100 residues, GPU w/o cuequivariance Not reported Aggregation: Not reported TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1); TorchX project site (torchx-cpl.github.io) · Table S9, row "GPU w/o cuequivariance", column "100 aa" |
| Configuration: TorchCraft on A100 without cuequivariance kernels | Protocol: TorchCraft runtime per design at 200 residues Dataset: TorchCraft runtime benchmark design runs | 7.96 Runtime (wall-clock minutes per design at 200 residues, batch size 2 run divided by 2) minute · lower Uncertainty: Not reported by the source: No spread is printed; GPU cells are stated to be the mean of three runs without a spread. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceTorchCraft runtime at 200 residues, GPU w/o cuequivariance Not reported Aggregation: Not reported TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1); TorchX project site (torchx-cpl.github.io) · Table S9, row "GPU w/o cuequivariance", column "200 aa" |
| Configuration: TorchCraft on A100 without cuequivariance kernels | Protocol: TorchCraft runtime per design at 300 residues Dataset: TorchCraft runtime benchmark design runs | 13.1 Runtime (wall-clock minutes per design at 300 residues, batch size 2 run divided by 2) minute · lower Uncertainty: Not reported by the source: No spread is printed; GPU cells are stated to be the mean of three runs without a spread. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceTorchCraft runtime at 300 residues, GPU w/o cuequivariance Not reported Aggregation: Not reported TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1); TorchX project site (torchx-cpl.github.io) · Table S9, row "GPU w/o cuequivariance", column "300 aa" |
| Configuration: TorchCraft on A100 without cuequivariance kernels | Protocol: TorchCraft runtime per design at 400 residues Dataset: TorchCraft runtime benchmark design runs | 21.6 Runtime (wall-clock minutes per design at 400 residues, batch size 2 run divided by 2) minute · lower Uncertainty: Not reported by the source: No spread is printed; GPU cells are stated to be the mean of three runs without a spread. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceTorchCraft runtime at 400 residues, GPU w/o cuequivariance Not reported Aggregation: Not reported TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1); TorchX project site (torchx-cpl.github.io) · Table S9, row "GPU w/o cuequivariance", column "400 aa" |
| Configuration: TorchCraft on A100 without cuequivariance kernels | Protocol: TorchCraft runtime per design at 500 residues Dataset: TorchCraft runtime benchmark design runs | 33.3 Runtime (wall-clock minutes per design at 500 residues, batch size 2 run divided by 2) minute · lower Uncertainty: Not reported by the source: No spread is printed; GPU cells are stated to be the mean of three runs without a spread. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceTorchCraft runtime at 500 residues, GPU w/o cuequivariance Not reported Aggregation: Not reported TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1); TorchX project site (torchx-cpl.github.io) · Table S9, row "GPU w/o cuequivariance", column "500 aa" |
Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.
Use this configuration
How it works, versions and access
Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
3 source records and release history
- TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Original source · arXiv:2609.19770v1, submitted 17 September 2026
- TorchX project site (torchx-cpl.github.io) · Original source · Project site as served on 2026-11-15
- TorchX torchcraft_gpu/README.md at commit ebf9dc6 · Original source · commit ebf9dc6676ecb1be505bc72f87de408995f0d8fd
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID torchcraft-20261115-config-runtime-gpu-no-cuequivariance.
Source locator: Supplementary Table S9, row 'GPU w/o cuequivariance'
Related records
- configuration of: TorchCraft
- uses model: TorchFold on pretrained AlphaFold 3 parameters
- system: TorchCraft runtime at 100 residues, GPU w/o cuequivariance
- system: TorchCraft runtime at 200 residues, GPU w/o cuequivariance
- system: TorchCraft runtime at 300 residues, GPU w/o cuequivariance
- system: TorchCraft runtime at 400 residues, GPU w/o cuequivariance
- system: TorchCraft runtime at 500 residues, GPU w/o cuequivariance
How to cite
TorchCraft on A100 without cuequivariance kernels. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/torchcraft-20261115-config-runtime-gpu-no-cuequivariance/
Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.
The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence