7B Verification Used 1.9%–14.8% of Generation GPU Time
CitationThese experiments, figures and data files are published by the TrueOpen.ai team. When citing or redistributing them, in whole or in part, state that the source is the TrueOpen.ai team and link to www.trueopen.ai. The same requirement is repeated in the download bundle's README, in CITATION.txt, and in the header of every CSV file.
This input-length experiment measured the compute-time ratio between three full teacher-forced prefill passes and one generation run. The ratio increased with input length while output length stayed fixed.
Measured Results
| Input tokens | 3 × full-prefill time / generation time |
|---|---|
| 50 | 1.9% |
| 200 | 2.1% |
| 1,000 | 3.3% |
| 4,000 | 8.2% |
| 8,000 | 14.8% |
Test Configuration
- Model: Qwen2.5-7B base, FP16.
- Hardware: one RTX PRO 6000 Blackwell GPU, 96 GB.
- Runtime: vLLM 0.20.1.
- Batch size: 1.
- Output length: fixed at 1,000 tokens.
What This Shows
Under these conditions, the compute time for three verification replays was substantially lower than the time required to generate the output. It demonstrates a possible compute-cost advantage of prefill-based verification; it does not measure model-substitution detection accuracy.
Measurement Scope
The ratio is 3 × tf_full / gen. It excludes networking, gas, queuing, evidence handling, and settlement. It is a batch-size-1 computation benchmark, not an end-to-end three-node service benchmark or evidence of deployed multi-task batch verification.
The preserved summary does not specify repeat counts or absolute timings. Complete logs are not available in the current website files.
Source: Historical evidence record EXP-02; “Step 2 Supplement”, §1, input-length sweep. This page reproduces the preserved experiment summary.