rewirebio.iobenchmarks
Configuration

HyInv BF16 path (timing configuration) (HyInv report)

HyInv run by the fastest BF16 path, as timed in the report's inference-time measurements.

2 evaluations · 4 results

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 HyInv BF16 path (timing configuration) (HyInv report). Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluated Checkpoint: HyInv as released 2026-11-02; technical report dated 2026-10-14

Evaluations and results

2 evaluations · 4 results. Different protocols are not a single leaderboard.

Dataset: Timing backbones for the HyInv inference-time measurements

Sorted by Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 148-residue backbone) (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 configurationProtocol and datasetRuntime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 148-residue backbone)Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 402-residue backbone)Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is a library of 10,000 designs for a 250-residue backbone)Speedup (Printed speed-up against the released ProteinMPNN implementation under the report's timing protocol on one NVIDIA H20; ProteinMPNN's own cell is printed as a dash, so the baseline has no value)
HyInv BF16 path (timing configuration) (HyInv report)EvaluationLatency of a design request on one NVIDIA H20 (HyInv report)24.750.62.1Not reported
HyInv BF16 path (timing configuration) (HyInv report)EvaluationSpeed-up of a design request over ProteinMPNN on one NVIDIA H20 (HyInv report)Not reportedNot reportedNot reported57×
All 4 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: HyInv BF16 path (timing configuration) (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
24.7 Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 148-residue backbone)
millisecond · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Latency of a design request for hyinv-bf16 on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 1, row 'HyInv (BF16)', column '128 designs (ms), 148 res.' (page 5 of 21)
Configuration: HyInv BF16 path (timing configuration) (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
50.6 Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is 128 designs for a 402-residue backbone)
millisecond · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Latency of a design request for hyinv-bf16 on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 1, row 'HyInv (BF16)', column '128 designs (ms), 402 res.' (page 5 of 21)
Configuration: HyInv BF16 path (timing configuration) (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
2.1 Runtime (Median wall-clock time of one design request on one NVIDIA H20, 128 candidates per request with a maximum candidate batch of 32 unless the request is the 10,000-design library; the timed region excludes model loading, CUDA graph capture and kernel compilation; the backbone length is named per result; the request is a library of 10,000 designs for a 250-residue backbone)
second · lower

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Latency of a design request for hyinv-bf16 on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 1, row 'HyInv (BF16)', column '10,000 designs (s)' (page 5 of 21)
Configuration: HyInv BF16 path (timing configuration) (HyInv report)Protocol: Speed-up of a design request over ProteinMPNN on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
57× Speedup (Printed speed-up against the released ProteinMPNN implementation under the report's timing protocol on one NVIDIA H20; ProteinMPNN's own cell is printed as a dash, so the baseline has no value)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Speed-up of hyinv-bf16 over ProteinMPNN on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-speedup-vs-proteinmpnn-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Table 1, row 'HyInv (BF16)', column 'Speed-up vs ProteinMPNN' (page 5 of 21)

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

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview 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

2 source records and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID hyinv-20261106-config-hyinv-bf16-timing.

Source locator: Table 1 row 'HyInv (BF16)' and its footnote; Figure 4a; Appendix F 'The two numerical paths' and 'Timing protocol'

Related records

How to cite

HyInv BF16 path (timing configuration) (HyInv report). Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/hyinv-20261106-config-hyinv-bf16-timing/

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

Suggest a correction