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.
37 lines
661 B
JSON
37 lines
661 B
JSON
[
|
|
{
|
|
"tag": "rest",
|
|
"card_mib": 8822,
|
|
"reserved_mib": 8160,
|
|
"outside_mib": 660,
|
|
"max_reserved_mib": 9074
|
|
},
|
|
{
|
|
"tag": "after concurrent burst 1",
|
|
"card_mib": 8828,
|
|
"reserved_mib": 8166,
|
|
"outside_mib": 660,
|
|
"max_reserved_mib": 9074
|
|
},
|
|
{
|
|
"tag": "after concurrent burst 2",
|
|
"card_mib": 8828,
|
|
"reserved_mib": 8166,
|
|
"outside_mib": 660,
|
|
"max_reserved_mib": 9074
|
|
},
|
|
{
|
|
"tag": "after latency shapes",
|
|
"card_mib": 8824,
|
|
"reserved_mib": 8160,
|
|
"outside_mib": 662,
|
|
"max_reserved_mib": 9074
|
|
},
|
|
{
|
|
"tag": "after largest requests",
|
|
"card_mib": 8830,
|
|
"reserved_mib": 8166,
|
|
"outside_mib": 662,
|
|
"max_reserved_mib": 9760
|
|
}
|
|
] |