rewirebio.iobenchmarks
Dataset

Timing backbones for the HyInv inference-time measurements

The single backbones of 148, 402 and 250 residues on which the HyInv report times a design request.

Evaluation results

17 evaluations · 27 results. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: CMLM (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
439 ms 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 cmlm on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 4a, bar 'CMLM', printed label (page 5 of 21)
Configuration: DPLM-2 3B (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
996 s 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)
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 dplm-2-3b on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 4a, bar 'DPLM-2 3B', printed label (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
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 exact FP32 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
130 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-exact-fp32 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, exact FP32 path', column '128 designs (ms), 148 res.' (page 5 of 21)
Configuration: HyInv exact FP32 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
303 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-exact-fp32 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, exact FP32 path', column '128 designs (ms), 402 res.' (page 5 of 21)
Configuration: HyInv exact FP32 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
14.5 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-exact-fp32 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, exact FP32 path', column '10,000 designs (s)' (page 5 of 21)
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
999 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-reference-sampler 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, FP32 reference sampler', column '128 designs (ms), 148 res.' (page 5 of 21)
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
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)
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-reference-sampler 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, FP32 reference sampler', column '128 designs (ms), 402 res.' (page 5 of 21)
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
129 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-reference-sampler 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, FP32 reference sampler', column '10,000 designs (s)' (page 5 of 21)
Configuration: LigandMPNN (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
79 s 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)
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 ligandmpnn on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 4a, bar 'LigandMPNN', printed label (page 5 of 21)
Configuration: LM-Design 650M (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
15 s 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)
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 lm-design-650m on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 4a, bar 'LM-Design 650M', printed label (page 5 of 21)
Configuration: PiFold (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
3,044 ms 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 pifold on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 4a, bar 'PiFold', printed label (page 5 of 21)
Configuration: ProteinMPNN grouped (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
7,667 ms 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 proteinmpnn-grouped on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 4a, bar 'ProteinMPNN grouped', printed label (page 5 of 21)
Configuration: ProteinMPNN (low-noise, grouped) (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
7,653 ms 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 proteinmpnn-low-noise-grouped on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 4a, bar 'ProteinMPNN (low-noise, grouped)', printed label (page 5 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
1,071 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 proteinmpnn 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 'ProteinMPNN', column '128 designs (ms), 148 res.' (page 5 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
2,907 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 proteinmpnn 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 'ProteinMPNN', column '128 designs (ms), 402 res.' (page 5 of 21)
Configuration: ProteinMPNN (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
142 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 proteinmpnn 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 'ProteinMPNN', column '10,000 designs (s)' (page 5 of 21)
Configuration: ProteinZero V2 (ESM1) (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
3,025 ms 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 proteinzero-v2-esm1 on one NVIDIA H20 (HyInv report)

hyinv-20261106-protocol-design-latency-h20

Aggregation: Not reported

HyInv Technical Report (Hyra Team, 2026-10-14) · Figure 4a, bar 'ProteinZero V2 (ESM1)', printed label (page 5 of 21)
Configuration: ProteinZero V2 (ESM2) (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
1,070 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 proteinzero-v2-esm2 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 'ProteinZero V2', column '128 designs (ms), 148 res.' (page 5 of 21)
Configuration: ProteinZero V2 (ESM2) (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
2,918 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 proteinzero-v2-esm2 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 'ProteinZero V2', column '128 designs (ms), 402 res.' (page 5 of 21)
Configuration: ProteinZero V2 (ESM2) (HyInv report)Protocol: Latency of a design request on one NVIDIA H20 (HyInv report)
Dataset: Timing backbones for the HyInv inference-time measurements
141 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 proteinzero-v2-esm2 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 'ProteinZero V2', 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)
Configuration: HyInv exact FP32 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
9.6× 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-exact-fp32 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, exact FP32 path', column 'Speed-up vs ProteinMPNN' (page 5 of 21)

Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-11-21-adc15377fab2 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

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.

7 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance
Reported name
148 res. / 402 res. / 250-residue backbone
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'

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

not individually reviewed

No individual claim review recorded

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

Audit details

Field: attributes.reported_name

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

Scope note
One 148-residue and one 402-residue backbone for the 128-design columns and one 250-residue backbone for the 10,000-design column. Every system designs 128 candidates per request with a maximum candidate batch of 32.
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'

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

not individually reviewed

No individual claim review recorded

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

Audit details

Field: attributes.scope_note

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

Source location
Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'

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

not individually reviewed

No individual claim review recorded

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

Audit details

Field: attributes.source_locator

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

Split
timing input
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'

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

not individually reviewed

No individual claim review recorded

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

Audit details

Field: attributes.split

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

Version
As used for the HyInv technical report's timings (2026-10-14)
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'

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

not individually reviewed

No individual claim review recorded

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

Audit details

Field: attributes.version

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

Description
The single backbones of 148, 402 and 250 residues on which the HyInv report times a design request.
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'

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

not individually reviewed

No individual claim review recorded

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

Audit details

Field: description

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

Name
Timing backbones for the HyInv inference-time measurements
Context-only references
HyInv Technical Report (Hyra Team, 2026-10-14)

Original source ↗

Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'

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

not individually reviewed

No individual claim review recorded

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

Audit details

Field: name

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

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: source checked

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

Technical metadata for this record is tracked under stable ID hyinv-20261106-data-latency-backbones.

Source locator: Table 1 header and footnote; Figure 4a; Appendix F 'Timing protocol'

Related records

Suggest a correction