Estimates H100 GPU-seconds/request from request shape and serving settings, using 91 published runs from one checkpoint, vLLM build, and 2xH100 node.
| Held-out partition | Rows | Model MdAPE | Token-rate baseline | Coverage |
|---|---|---|---|---|
| Calibration, 32K | 11 | 7.1% | 13.0% | 90.9% |
| Test, 128K | 14 | 6.5% | 8.6% | 64.3% |
OOD, unseen tunedmax |
12 | 14.6% | 6.5% | 41.7% |
The frozen test gate passed: MdAPE was below 25%, with 24.6% improvement over the stronger baseline. Coverage missed nominal 80% on test and OOD; the token-rate baseline won OOD.
- Source:
SamMausberg/capp-vllm-bench,results/results.csv, commit7e195dbc1192092e4765c166953e1bdcd533cb72 - Git blob:
f7add3069a6c3d6fcdadce00bb2907f61566a9c0; mirror SHA-256:282675fdea50480ea1fa6106caa8b29e523ea90735c7d4b37558d5c2410c364b - Corpus:
CohereLabs/command-a-plus-05-2026-w4a4, patched vLLM 0.26.0, tensor parallelism 2, two NVLink H100 80GB GPUs, random-token prompts - Groups:
(config_id, input_len); none cross fit, calibration, test, or OOD - Target:
2 * total tokens per request / aggregate token throughput
The 91-row ledger includes every miss. Features exclude duration, throughput, latency, memory, and KV utilization; artifacts contain no currency. servemodel.* remains the complete v1 schema namespace for compatibility.
Python 3.11+; no runtime dependencies.
python -B run.py build --output artifacts/local_rebuild
python -B verify_independent.py artifacts/local_rebuild
python -B tools/generate_figure.py --check
python -B tools/verify_project.py
The independent verifier imports no producer code and rebuilds the split, fit, interval, 91 predictions, metrics, and hashes. Re-signed tamper tests reject leakage and GPU-hour mutation semantically.
Predict with python -B run.py predict or the installed h100-serving-estimator predict command. Dollar fields appear only with a positive --usd-per-h100-hour value.
See METHODS.md and the canonical report.
This workload-specific observational model is not a portability claim, fleet simulator, or provider bill. OOD is descriptive and excluded from the gate.