Files
esh-pfi-infrastructure/services/intern-decision-serve/acceptance/gpu3-2026-09-30/cap9.0/shape.json
T
vh a262477a61 feat(intern-decision): stack, DNS and GPU 3 acceptance for the SemIf replacement
stacks/intern-decision: compose (GPU 1, :8033, hard VRAM cap as the single .env knob,
healthcheck, Homepage group 'AI - Eval & Retrieval'), .env.example and README.
dns: intern-decision.fv.internal -> fv-ml1 (synced to ana/esh/nh3).
acceptance on fv-ml1 GPU 3, 3 fresh processes: bit-identical to the Jev bench's native rows
(pooled 240/259, Wyrd 79/84, 0/560 flips, Δp 0), negative control 10/122/14, 0 flips across
restarts; largest accepted request 200 at a 10,134 MiB card peak under a 9.25 GiB cap; 503 and
recovery proven at a tight cap. GPU 1 deploy held: nvidia-smi Free on GPU 1 is 15,442 MiB.
2026-09-30 09:38:00 -07:00

1 line
2.3 KiB
JSON

{"label": "cap9.0", "backend": "semif", "runs": 1, "per": 5, "max_questions": 10000, "events": [["start", 1790786179.0584767], ["short1:measure", 1790786179.1493392], ["crit21:measure", 1790786179.5161796], ["long1:measure", 1790786186.5989966], ["long16:measure", 1790786194.1815286], ["shapes:done", 1790786195.251973], ["end", 1790786195.251976]], "shapes": {"short1": {"rows": 1, "runs": [{"e2e_ms": [37.941707065328956, 38.23350998573005, 37.37540193833411, 38.53617515414953, 38.11007016338408], "server_ms": [35.29082587920129, 35.39266809821129, 34.68621987849474, 35.76885210350156, 35.205855034291744], "statuses": [200, 200, 200, 200, 200], "tokens": 181, "median_e2e": 38.11007016338408, "median_server": 35.29082587920129}], "tokens": 181, "median_e2e_ms": 38.1, "run_medians_e2e_ms": [38.1], "median_server_ms": 35.3, "non_200": 0}, "crit21": {"rows": 21, "runs": [{"e2e_ms": [86.08735189773142, 85.76549892313778, 85.83429013378918, 85.84657986648381, 85.68961801938713], "server_ms": [79.76265903562307, 79.48806718923151, 79.50853602960706, 79.57211695611477, 79.62968898937106], "statuses": [200, 200, 200, 200, 200], "tokens": null, "median_e2e": 85.83429013378918, "median_server": 79.57211695611477}], "tokens": null, "median_e2e_ms": 85.8, "run_medians_e2e_ms": [85.8], "median_server_ms": 79.6, "non_200": 0}, "long1": {"rows": 1, "runs": [{"e2e_ms": [184.56048821099102, 191.5509181562811, 187.36126995645463, 186.49141117930412, 187.67126300372183], "server_ms": [181.11044797115028, 187.99379700794816, 183.76171891577542, 183.00863006152213, 184.1394929215312], "statuses": [200, 200, 200, 200, 200], "tokens": 4019, "median_e2e": 187.36126995645463, "median_server": 183.76171891577542}], "tokens": 4019, "median_e2e_ms": 187.4, "run_medians_e2e_ms": [187.4], "median_server_ms": 183.8, "non_200": 0}, "long16": {"rows": 16, "runs": [{"e2e_ms": [211.36997686699033, 217.9243720602244, 213.36712990887463, 213.6664930731058, 211.49204880930483], "server_ms": [205.53427003324032, 212.03652513213456, 207.65956514514983, 207.81763619743288, 205.71005111560225], "statuses": [200, 200, 200, 200, 200], "tokens": null, "median_e2e": 213.36712990887463, "median_server": 207.65956514514983}], "tokens": null, "median_e2e_ms": 213.4, "run_medians_e2e_ms": [213.4], "median_server_ms": 207.7, "non_200": 0}}}