rewirebio.iobenchmarks
Result

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) of HyInv FP32 reference sampler (timing configuration) (HyInv report) on Timing backbones for the HyInv inference-time measurements

2,633 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)

Methods

Tested configuration
HyInv FP32 reference sampler (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
Procedure
Latency of a design request on one NVIDIA H20 (HyInv report)
Evaluation
Latency of a design request for hyinv-reference-sampler on one NVIDIA H20 (HyInv report)
Coverage
Not reported scored / Not reported eligible
Uncertainty
Not reported by the source
Evidence
Author-reported evaluation · source checkedHyInv Technical Report (Hyra Team, 2026-10-14) · Table 1, row 'HyInv, FP32 reference sampler', column '128 designs (ms), 402 res.' (page 5 of 21)

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Reproduction

Split
timing input
Adaptation
Each system runs its own released implementation at its published setting; HyInv's rows use the supervised-stage weights and a rewrite temperature of 0.23
Scoring implementation
PyTorch 2.7.1, CUDA 12.9, TF32 for matrix products off unless stated, on one NVIDIA H20 of a node on which nothing else ran. The timed region starts at host arrays and ends at the sampled tokens on the device: upload, backbone batch, encoder and structure terms and all 16 decoder passes of every candidate batch, but not model loading, graph capture or kernel compilation (first call 67.7 ms to 834 ms per shape bucket). Every call draws fresh seeds and nothing is cached across calls. HyInv rows were timed with the supervised-stage weights and a rewrite temperature of 0.23. Baselines ran with their released implementations in FP32 without graph capture or compilation, DPLM-2 3B in BF16 autocast, each at its published setting.

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Reported result
2,633
Individual claims
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Table 1, row 'HyInv, FP32 reference sampler', column '128 designs (ms), 402 res.' (page 5 of 21)

Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
Retrieved: 2026-11-06T09:52:00Z

source checked

["independent-cell-check","deterministic-table-parse","pdf-text-parse","source-hash-verification"] · 2026-11-06T00:00:00Z

author reported

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.printed_value

Source artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted.

Inspected artifact

Extraction artifact SHA-256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419

Extraction artifact

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: hyinv-20261106-result-design-latency-hyinv-reference-sampler-ms-402

metric
runtime
metric direction
lower
metric qualifier
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
missing metadata
uncertainty: reason: unreported
numeric value
2633
printed value
2,633
review
artifact sha256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419; method: independent-cell-check; deterministic-table-parse; pdf-text-parse; source-hash-verification; method note: Independent review pass. The pinned PDF was re-downloaded at the pinned commit and its SHA-256 checked against the source record; pdftotext -layout reproduced the archived text layer byte for byte. npm run batch -- check-values was run over the whole batch against that text layer (value-check.tsv). The 170 cells of Tables 6, 7, 8 and 9 and the 290 cells of the Figure 14 and Figure 15 matrices were then re-read by a reviewer script that finds each row by its printed label and splits the printed cells by position, written for this pass without using the extractor's parser; every printed value and column matched. Column assignment in Figure 14 was confirmed against the labelled columns of Table 2 and against Section 5.2's prose figures; Figure 15's was confirmed by the coordinator reading the rotated column headers on the rendered page 17, which match Figure 14's order. Table 1, Figure 4a and the eleven prose values were read by hand against the text layer. Each claim was re-read against the passage its locator names.; retrieval url: https://raw.githubusercontent.com/Tencent-Hunyuan/Hyra-results/0dcc533cc9f8f76c90ecbfe944df816b6672328a/AI4Science/hyinv/HyInv_Technical_Report.pdf; reviewed at: 2026-11-06T00:00:00Z; reviewer: claude; reviewer note: Claude research agent; no human review claimed. Reviewed by a different agent from the one that extracted the batch. Transcription checked against the pinned source; nothing was reproduced and no value was recomputed.
source locator
Table 1, row 'HyInv, FP32 reference sampler', column '128 designs (ms), 402 res.' (page 5 of 21)
unit
millisecond
unit detail
Printed as '2,633' under the column heading '128 designs (ms), 402 res.'; the request is 128 designs for a 402-residue backbone
Related records

Suggest a correction