| { |
| "status": "verified existing real-model receipts; no new GPU run for timing-only package update", |
| "pages_per_profile": 2078, |
| "hardware": "one H100 80GB", |
| "server_backend": "uni", |
| "tensor_parallel_size": 1, |
| "vllm": "0.26.0", |
| "profile": "FA3, MTP1, max_model_len=16384, max_num_seqs=192, max_num_batched_tokens=16384", |
| "model_weight_sha256": "81dd7609c589f3694ce75520c25af5010953231358de6aec4d03e8c6aac787e9", |
| "recommended_quality_preserving_profiles": [ |
| { |
| "mode": "single", |
| "measured_package": "3.5.0.post4", |
| "source_receipt": "/lustre/fsw/portfolios/nemotron/projects/nemotron_parse_dev/users/rchesler/analysis/general_postprocessor_speed_20261017/full/single_c256/complete.json", |
| "source_receipt_sha256": "07cd8d23d8e2724d496caf813348db7d8e94c7f65bf01d084206cbd5335ed1be", |
| "concurrency": 256, |
| "schedule": "staged", |
| "pages": 2078, |
| "complete_pages": 2045, |
| "inference_seconds": 134.78283468799782, |
| "inference_pages_per_second": 15.417393504226709, |
| "complete_inference_pages_per_second": 15.172555205073927, |
| "original_pipeline_seconds": 137.7506838600093, |
| "requests": { |
| "fullpage": 2078, |
| "detection": 0, |
| "crop": 0 |
| }, |
| "token_limited_responses": { |
| "fullpage": 33 |
| }, |
| "completion_tokens": 2719778, |
| "extraction_method": "saved fullpage stage wall timer; conservatively includes HTTP executor setup/teardown", |
| "generation_metrics": { |
| "mode": "single", |
| "pages": 2078, |
| "complete_pages": 2045, |
| "incomplete_pages": 33, |
| "concurrency": 256, |
| "postprocess_workers": 8, |
| "preprocessing_seconds": 10.932252227998106, |
| "pipeline_seconds": 137.7506838600093, |
| "processed_pages_per_second": 15.08522456492333, |
| "complete_pages_per_second": 14.845661325923103, |
| "stage_times": { |
| "fullpage_seconds": 134.78283468799782, |
| "postprocessing_seconds": 2.9462760030000936 |
| }, |
| "requests": { |
| "fullpage": 2078, |
| "detection": 0, |
| "crop": 0 |
| }, |
| "token_limited_responses": { |
| "fullpage": 33 |
| }, |
| "completion_tokens": 2719778, |
| "postprocessing": { |
| "infer_headers": true, |
| "render_charts": true, |
| "split_chart_value_percent": true, |
| "relocate_chart_captions": true, |
| "normalize_text": true, |
| "deduplicate": true |
| }, |
| "allow_partial": true, |
| "timing_excludes": [ |
| "initial image preparation", |
| "output serialization", |
| "server startup", |
| "warmup requests" |
| ], |
| "timing_includes": [ |
| "all mode inference stages", |
| "predicted-region crop preparation", |
| "merge and document rendering" |
| ], |
| "keys_sha256": "e2800a56d79085a612e2677e87fabd9735be7d92479cd68ad750ff3b49f67d3a", |
| "input_pages": 2078, |
| "output_serialization_seconds": 1.2913870430202223, |
| "pipeline_plus_serialization_seconds": 139.04207090302953, |
| "pages_per_second_with_serialization": 14.945116873649235, |
| "complete": true |
| } |
| }, |
| { |
| "mode": "double", |
| "measured_package": "3.5.0.post5", |
| "source_receipt": "/lustre/fsw/portfolios/nemotron/projects/nemotron_parse_dev/users/rchesler/analysis/general_postprocessor_speed_20261017/accuracy_restored_20261017/full/double/complete.json", |
| "source_receipt_sha256": "2a1fc5d79989a17b6ccf825b8d9d964ae53ce8aedf7f31407c8191c0aa38f533", |
| "concurrency": 256, |
| "schedule": "pipelined", |
| "pages": 2078, |
| "complete_pages": 2043, |
| "inference_seconds": 178.3529313809995, |
| "inference_pages_per_second": 11.651056048868371, |
| "complete_inference_pages_per_second": 11.454815932549607, |
| "original_pipeline_seconds": 178.53091148199746, |
| "requests": { |
| "fullpage": 2078, |
| "detection": 0, |
| "crop": 2339 |
| }, |
| "token_limited_responses": { |
| "fullpage": 26, |
| "crop": 9 |
| }, |
| "completion_tokens": 3800986, |
| "extraction_method": "maximum stage end minus minimum stage start on common clock", |
| "generation_metrics": { |
| "mode": "double", |
| "merge_policy": "alternatives", |
| "schedule": "pipelined", |
| "peak_inflight_requests": 256, |
| "request_service_seconds": { |
| "fullpage": 28709.884806043323, |
| "crop": 13957.128172721918 |
| }, |
| "stage_first_request_seconds": { |
| "fullpage": 0.0035496869968483225, |
| "crop": 8.328730886001722 |
| }, |
| "overlapping_stage_times": true, |
| "pages": 2078, |
| "complete_pages": 2043, |
| "incomplete_pages": 35, |
| "concurrency": 256, |
| "postprocess_workers": 8, |
| "preprocessing_seconds": 9.697014473000308, |
| "pipeline_seconds": 178.53091148199746, |
| "processed_pages_per_second": 11.639440939108965, |
| "complete_pages_per_second": 11.44339645745891, |
| "stage_times": { |
| "fullpage_span_seconds": 175.82064464699943, |
| "crop_span_seconds": 170.02775018199463 |
| }, |
| "requests": { |
| "fullpage": 2078, |
| "detection": 0, |
| "crop": 2339 |
| }, |
| "token_limited_responses": { |
| "fullpage": 26, |
| "crop": 9 |
| }, |
| "completion_tokens": 3800986, |
| "postprocessing": { |
| "infer_headers": true, |
| "render_charts": true, |
| "split_chart_value_percent": true, |
| "relocate_chart_captions": true, |
| "normalize_text": true, |
| "deduplicate": true |
| }, |
| "allow_partial": true, |
| "timing_excludes": [ |
| "initial image preparation", |
| "output serialization", |
| "server startup", |
| "warmup requests" |
| ], |
| "timing_includes": [ |
| "all mode inference stages", |
| "predicted-region crop preparation", |
| "merge and document rendering" |
| ], |
| "keys_sha256": "e2800a56d79085a612e2677e87fabd9735be7d92479cd68ad750ff3b49f67d3a", |
| "input_pages": 2078, |
| "vllm_queue": { |
| "sample_interval_seconds": 0.5, |
| "samples": 352, |
| "peak_running": 192.0, |
| "peak_waiting": 64.0, |
| "fraction_samples_with_waiting": 0.8977272727272727, |
| "mean_running": 175.42613636363637 |
| }, |
| "output_serialization_seconds": 1.6826819609996164, |
| "pipeline_plus_serialization_seconds": 180.21359344299708, |
| "pages_per_second_with_serialization": 11.530761693941178, |
| "complete": true |
| } |
| }, |
| { |
| "mode": "triple", |
| "measured_package": "3.5.0.post5", |
| "source_receipt": "/lustre/fsw/portfolios/nemotron/projects/nemotron_parse_dev/users/rchesler/analysis/general_postprocessor_speed_20261017/accuracy_restored_20261017/full/triple/complete.json", |
| "source_receipt_sha256": "08a8671ae3efd29a34241b32990c4f8d539a6e0c62a1b9b88430433abedd3210", |
| "concurrency": 128, |
| "schedule": "pipelined", |
| "pages": 2078, |
| "complete_pages": 2038, |
| "inference_seconds": 195.69899474299746, |
| "inference_pages_per_second": 10.618347849609256, |
| "complete_inference_pages_per_second": 10.4139523183367, |
| "original_pipeline_seconds": 195.8028804409987, |
| "requests": { |
| "fullpage": 2078, |
| "detection": 2078, |
| "crop": 2609 |
| }, |
| "token_limited_responses": { |
| "crop": 22, |
| "fullpage": 33 |
| }, |
| "completion_tokens": 4238196, |
| "extraction_method": "maximum stage end minus minimum stage start on common clock", |
| "generation_metrics": { |
| "mode": "triple", |
| "merge_policy": "alternatives", |
| "schedule": "pipelined", |
| "peak_inflight_requests": 128, |
| "request_service_seconds": { |
| "detection": 2116.9487077718077, |
| "crop": 7074.808867427841, |
| "fullpage": 14919.450061689073 |
| }, |
| "stage_first_request_seconds": { |
| "detection": 0.0024413679930148646, |
| "crop": 0.3488499709928874, |
| "fullpage": 0.0005174870020709932 |
| }, |
| "overlapping_stage_times": true, |
| "pages": 2078, |
| "complete_pages": 2038, |
| "incomplete_pages": 40, |
| "concurrency": 128, |
| "postprocess_workers": 8, |
| "preprocessing_seconds": 9.697014473000308, |
| "pipeline_seconds": 195.8028804409987, |
| "processed_pages_per_second": 10.612714150679535, |
| "complete_pages_per_second": 10.408427064044702, |
| "stage_times": { |
| "detection_span_seconds": 187.84758807100297, |
| "crop_span_seconds": 195.35066225900664, |
| "fullpage_span_seconds": 195.54977705900092 |
| }, |
| "requests": { |
| "fullpage": 2078, |
| "detection": 2078, |
| "crop": 2609 |
| }, |
| "token_limited_responses": { |
| "crop": 22, |
| "fullpage": 33 |
| }, |
| "completion_tokens": 4238196, |
| "postprocessing": { |
| "infer_headers": true, |
| "render_charts": true, |
| "split_chart_value_percent": true, |
| "relocate_chart_captions": true, |
| "normalize_text": true, |
| "deduplicate": true |
| }, |
| "allow_partial": true, |
| "timing_excludes": [ |
| "initial image preparation", |
| "output serialization", |
| "server startup", |
| "warmup requests" |
| ], |
| "timing_includes": [ |
| "all mode inference stages", |
| "predicted-region crop preparation", |
| "merge and document rendering" |
| ], |
| "keys_sha256": "e2800a56d79085a612e2677e87fabd9735be7d92479cd68ad750ff3b49f67d3a", |
| "input_pages": 2078, |
| "vllm_queue": { |
| "sample_interval_seconds": 0.5, |
| "samples": 385, |
| "peak_running": 128.0, |
| "peak_waiting": 4.0, |
| "fraction_samples_with_waiting": 0.0025974025974025974, |
| "mean_running": 113.85194805194806 |
| }, |
| "output_serialization_seconds": 1.8849293050006963, |
| "pipeline_plus_serialization_seconds": 197.6878097459994, |
| "pages_per_second_with_serialization": 10.511523207576294, |
| "complete": true |
| } |
| } |
| ], |
| "interpretation": [ |
| "Prepared-page batch throughput, not PDF-to-document end-to-end throughput or one-page latency.", |
| "Counts all 2078 processed pages; token-limited pages are incomplete and are separately reported.", |
| "Double/triple use the restored alternatives merge and default chart rules. Single has no crop merge and was measured before that merge-only change.", |
| "Dependent crop selection, encoding, dispatch, queueing, model image encoding and generation remain on the inference critical path.", |
| "Initial preparation, startup, warmup and output serialization excluded. Final rendering tail excluded; concurrent rendering contention remains in observed wall time and is not subtracted.", |
| "Historical fastest observed guarded-merge runs reached 11.8805158572 double and 10.9075689818 triple pages/s. They have lower quality and are not the recommended quality-preserving profiles.", |
| "These are observed configurations, not a hardware ceiling. Nonzero-temperature generation and scheduler batching cause run-to-run variation.", |
| "Single stage timer includes executor overhead; this makes its inferred 15.42 pages/s slightly conservative.", |
| "The post6 change only adds timing counters; no new model generation or fresh score is claimed." |
| ], |
| "quality_receipt": "accuracy_restoration.json", |
| "prior_speed_receipt": "batch_benchmarks.json" |
| } |
|
|
