Result

Inference throughput (Autoregressive generation; generated tokens per second) of GenomeOcean-4B, BF16, vLLM generation (Yu et al. 2026) on 96 GTDB Bacteria genome sequences bounded to 102,400 tokens (Yu et al. 2026)

1818.79 ± 7.95 Inference throughput (Autoregressive generation; generated tokens per second)

Methods

Tested configuration: GenomeOcean-4B, BF16, vLLM generation (Yu et al. 2026)
Protocol: GenomeOcean-4B autoregressive generation throughput, power, energy efficiency and perplexity, BF16 versus FP8 (Yu et al. 2026 Table 4)
Dataset: 96 GTDB Bacteria genome sequences bounded to 102,400 tokens (Yu et al. 2026)
Procedure: GenomeOcean-4B autoregressive generation throughput, power, energy efficiency and perplexity, BF16 versus FP8 (Yu et al. 2026 Table 4)
Evaluation: GenomeOcean-4B BF16 generation (Yu et al. 2026)
Coverage: Not reported scored / Not reported eligible
Uncertainty: SD 7.95
Evidence: Author-reported evaluation · source checkedFP8 Inference in Genomic Foundation Models: Theoretical vs. Realized Speedups on GenomeOcean · Table 4, row Protocol 'Baseline', Quantization Scheme 'BF16', column 'Throughput (tok/s)'

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: Five trials, seeds 42-46; perplexity on 96 fixed sequences
Adaptation: None (pretrained checkpoint, post-training quantization only)
Scoring implementation: Not reported

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 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Reported result 1818.79 ± 7.95 Individual claims	FP8 Inference in Genomic Foundation Models: Theoretical vs. Realized Speedups on GenomeOcean Original source ↗ Table 4, row Protocol 'Baseline', Quantization Scheme 'BF16', column 'Throughput (tok/s)' Version: bioRxiv preprint version 1, posted 2026-08-14 (PDF footer); bioRxiv API date 2026-08-18 Retrieved: 2026-10-11T21:42:49Z	source checked ["source-hash-verification","pdf-text-parse","rendered-source-visual-check","independent-cell-check"] · 2026-10-12T07:50:32Z author reported Audit details Independent review 2026-10-12: printed value, numeric value, metric, qualifier, unit, direction, uncertainty, locator and configuration and protocol identity match the source. Transcribed, not reproduced. Field: `attributes.printed_value` Source artifact SHA-256: `ca54817d1f1a308f09bd3022e56cf6f8b86a875b110da0a38fe31236e39ca076` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval (a second download differed in 40 bytes). The pdftotext -layout text layer (poppler) of both downloads has SHA-256 bec6e695ce46c4ebd6692e01a1a93167e212dffbb97b6558f1da88b1eb453501. Inspected artifact Extraction artifact SHA-256: `ca54817d1f1a308f09bd3022e56cf6f8b86a875b110da0a38fe31236e39ca076` Extraction artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

FP8 Inference in Genomic Foundation Models: Theoretical vs. Realized Speedups on GenomeOcean · Original source · bioRxiv preprint version 1, posted 2026-08-14 (PDF footer); bioRxiv API date 2026-08-18

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: model-execution-20261011-result-yu2026-genomeocean-4b-bf16-vllm-throughput

metric: inference-throughput
metric direction: higher
unit: sample-per-second
metric qualifier: Autoregressive generation; generated tokens per second
unit detail: tokens per second (generated tokens), printed tok/s
printed value: 1818.79 ± 7.95
numeric value: 1818.79
source locator: Table 4, row Protocol 'Baseline', Quantization Scheme 'BF16', column 'Throughput (tok/s)'
uncertainty: type: standard_deviation; value: 7.95; printed: ± 7.95; n: 5; scope: Five trials with random seeds 42-46
review: method: source-hash-verification; pdf-text-parse; rendered-source-visual-check; independent-cell-check; method note: Archived PDF matched the pinned SHA-256; a fresh bioRxiv download had the same text-layer SHA-256. Tables 3 and 4 parsed from pdftotext -layout with a separate review script, including every ± value, and every cell read against a 170 dpi render of page 8.; reviewer: claude; reviewer note: Claude (Opus 5.5) review agent reviewer-exec, independent of the extractor uc-execution; no human review claimed; reviewed at: 2026-10-12T07:50:32Z; artifact sha256: ca54817d1f1a308f09bd3022e56cf6f8b86a875b110da0a38fe31236e39ca076; retrieval url: https://www.biorxiv.org/content/10.64898/2026.08.09.743676v1.full.pdf; note: Independent review 2026-10-12: printed value, numeric value, metric, qualifier, unit, direction, uncertainty, locator and configuration and protocol identity match the source. Transcribed, not reproduced.

Related records

evaluation: GenomeOcean-4B BF16 generation (Yu et al. 2026)

Suggest a correction