gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Record phase-aware telemetry pilot result

Browse Source
This commit is contained in:
Gahow Wang
2026-07-14 19:18:57 +08:00
parent 7fd9563550
commit 26c2cdab2b
6 changed files with 17372 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

342
runs/intervention-response-v2/pilot-controller-state-v3.json Normal file
View File

@@ -0,0 +1,342 @@
{
"completed_at": 1784027453.4005148,
"completed_sessions": 6,
"failures": [],
"gpu_hours_total": 5.092428478929731,
"hard_cap_h20_hours": 6.641945318645901,
"schema": "intervention-response-phase-aware-pilot-state-v3",
"sessions": {
"rep1-mns16": {
"burnin": {
"elapsed_s": 64.194648239,
"feasible": false,
"pass_rate": 0.5235294117647059
},
"completed_at": 1784023620.6911042,
"gpu_hours": 0.856446467505561,
"mns": 16,
"replicate": 1,
"runs": [
{
"early_stopped": false,
"elapsed_s": 301.068878512,
"feasible": true,
"level": "low",
"offered_req_s_per_gpu": 1.5,
"pass_rate": 1.0,
"selected_count": 1800
},
{
"early_stopped": false,
"elapsed_s": 313.268231477,
"feasible": false,
"level": "mid",
"offered_req_s_per_gpu": 2.125,
"pass_rate": 0.5603921568627451,
"selected_count": 2550
}
],
"started_at": 1784022846.257515,
"status": "complete",
"validation": {
"accounting_mode": "graceful-footer",
"cell": "tp4_mns16",
"invariants": {
"anchor_intervals_present": true,
"compile_capture_pre_ready": true,
"encoded_balanced": true,
"footer_sidecar_agrees": true,
"last_step_matches": true,
"layer1_contiguous": true,
"layer1_zero_drops": true,
"one_footer_last": true,
"one_ready_marker": true,
"sidecar_final": true,
"warmup_exact_16": true,
"warmup_long": true,
"written_matches_records": true
},
"layer1_records": 60017,
"post_ready_capture_events": [],
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep1-mns16/opprof/opprof-v1-dp0-pid458427-1784022917661752826.jsonl"
}
},
"rep1-mns64": {
"burnin": {
"elapsed_s": 60.79926316,
"feasible": true,
"pass_rate": 1.0
},
"completed_at": 1784024382.2164423,
"gpu_hours": 0.8415956518385146,
"mns": 64,
"replicate": 1,
"runs": [
{
"early_stopped": false,
"elapsed_s": 301.022700013,
"feasible": true,
"level": "low",
"offered_req_s_per_gpu": 1.5,
"pass_rate": 1.0,
"selected_count": 1800
},
{
"early_stopped": false,
"elapsed_s": 301.100993458,
"feasible": true,
"level": "mid",
"offered_req_s_per_gpu": 2.125,
"pass_rate": 1.0,
"selected_count": 2550
}
],
"started_at": 1784023620.9865165,
"status": "complete",
"validation": {
"accounting_mode": "graceful-footer",
"cell": "tp4_mns64",
"invariants": {
"anchor_intervals_present": true,
"compile_capture_pre_ready": true,
"encoded_balanced": true,
"footer_sidecar_agrees": true,
"last_step_matches": true,
"layer1_contiguous": true,
"layer1_zero_drops": true,
"one_footer_last": true,
"one_ready_marker": true,
"sidecar_final": true,
"warmup_exact_16": true,
"warmup_long": true,
"written_matches_records": true
},
"layer1_records": 62456,
"post_ready_capture_events": [],
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep1-mns64/opprof/opprof-v1-dp0-pid471212-1784023695315485142.jsonl"
}
},
"rep2-mns16": {
"burnin": {
"elapsed_s": 63.518994307,
"feasible": false,
"pass_rate": 0.6647058823529411
},
"completed_at": 1784025910.710227,
"gpu_hours": 0.8481734045346578,
"mns": 16,
"replicate": 2,
"runs": [
{
"early_stopped": false,
"elapsed_s": 315.780805484,
"feasible": false,
"level": "mid",
"offered_req_s_per_gpu": 2.125,
"pass_rate": 0.31450980392156863,
"selected_count": 2550
},
{
"early_stopped": false,
"elapsed_s": 300.346368314,
"feasible": true,
"level": "low",
"offered_req_s_per_gpu": 1.5,
"pass_rate": 1.0,
"selected_count": 1800
}
],
"started_at": 1784025143.731658,
"status": "complete",
"validation": {
"accounting_mode": "graceful-footer",
"cell": "tp4_mns16",
"invariants": {
"anchor_intervals_present": true,
"compile_capture_pre_ready": true,
"encoded_balanced": true,
"footer_sidecar_agrees": true,
"last_step_matches": true,
"layer1_contiguous": true,
"layer1_zero_drops": true,
"one_footer_last": true,
"one_ready_marker": true,
"sidecar_final": true,
"warmup_exact_16": true,
"warmup_long": true,
"written_matches_records": true
},
"layer1_records": 58465,
"post_ready_capture_events": [],
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep2-mns16/opprof/opprof-v1-dp0-pid496100-1784025206790752505.jsonl"
}
},
"rep2-mns64": {
"burnin": {
"elapsed_s": 60.803771161,
"feasible": true,
"pass_rate": 1.0
},
"completed_at": 1784025143.4362338,
"gpu_hours": 0.8412917502721151,
"mns": 64,
"replicate": 2,
"runs": [
{
"early_stopped": false,
"elapsed_s": 300.605515019,
"feasible": true,
"level": "mid",
"offered_req_s_per_gpu": 2.125,
"pass_rate": 1.0,
"selected_count": 2550
},
{
"early_stopped": false,
"elapsed_s": 300.354084826,
"feasible": true,
"level": "low",
"offered_req_s_per_gpu": 1.5,
"pass_rate": 1.0,
"selected_count": 1800
}
],
"started_at": 1784024382.5080929,
"status": "complete",
"validation": {
"accounting_mode": "graceful-footer",
"cell": "tp4_mns64",
"invariants": {
"anchor_intervals_present": true,
"compile_capture_pre_ready": true,
"encoded_balanced": true,
"footer_sidecar_agrees": true,
"last_step_matches": true,
"layer1_contiguous": true,
"layer1_zero_drops": true,
"one_footer_last": true,
"one_ready_marker": true,
"sidecar_final": true,
"warmup_exact_16": true,
"warmup_long": true,
"written_matches_records": true
},
"layer1_records": 61696,
"post_ready_capture_events": [],
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep2-mns64/opprof/opprof-v1-dp0-pid483758-1784024456752184540.jsonl"
}
},
"rep3-mns16": {
"burnin": {
"elapsed_s": 64.324514503,
"feasible": false,
"pass_rate": 0.5588235294117647
},
"completed_at": 1784026691.6293187,
"gpu_hours": 0.8631463612450494,
"mns": 16,
"replicate": 3,
"runs": [
{
"early_stopped": false,
"elapsed_s": 300.711109876,
"feasible": true,
"level": "low",
"offered_req_s_per_gpu": 1.5,
"pass_rate": 1.0,
"selected_count": 1800
},
{
"early_stopped": false,
"elapsed_s": 317.011840655,
"feasible": false,
"level": "mid",
"offered_req_s_per_gpu": 2.125,
"pass_rate": 0.2635294117647059,
"selected_count": 2550
}
],
"started_at": 1784025911.00421,
"status": "complete",
"validation": {
"accounting_mode": "graceful-footer",
"cell": "tp4_mns16",
"invariants": {
"anchor_intervals_present": true,
"compile_capture_pre_ready": true,
"encoded_balanced": true,
"footer_sidecar_agrees": true,
"last_step_matches": true,
"layer1_contiguous": true,
"layer1_zero_drops": true,
"one_footer_last": true,
"one_ready_marker": true,
"sidecar_final": true,
"warmup_exact_16": true,
"warmup_long": true,
"written_matches_records": true
},
"layer1_records": 61438,
"post_ready_capture_events": [],
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep3-mns16/opprof/opprof-v1-dp0-pid508913-1784025983046041167.jsonl"
}
},
"rep3-mns64": {
"burnin": {
"elapsed_s": 60.850091109,
"feasible": true,
"pass_rate": 1.0
},
"completed_at": 1784027453.3790896,
"gpu_hours": 0.8417748435338338,
"mns": 64,
"replicate": 3,
"runs": [
{
"early_stopped": false,
"elapsed_s": 300.710505069,
"feasible": true,
"level": "low",
"offered_req_s_per_gpu": 1.5,
"pass_rate": 1.0,
"selected_count": 1800
},
{
"early_stopped": false,
"elapsed_s": 300.869326418,
"feasible": true,
"level": "mid",
"offered_req_s_per_gpu": 2.125,
"pass_rate": 1.0,
"selected_count": 2550
}
],
"started_at": 1784026691.96421,
"status": "complete",
"validation": {
"accounting_mode": "graceful-footer",
"cell": "tp4_mns64",
"invariants": {
"anchor_intervals_present": true,
"compile_capture_pre_ready": true,
"encoded_balanced": true,
"footer_sidecar_agrees": true,
"last_step_matches": true,
"layer1_contiguous": true,
"layer1_zero_drops": true,
"one_footer_last": true,
"one_ready_marker": true,
"sidecar_final": true,
"warmup_exact_16": true,
"warmup_long": true,
"written_matches_records": true
},
"layer1_records": 64776,
"post_ready_capture_events": [],
"stream": "/home/admin/cpfs/wjh/intervention-response-v3-20260714/runs/pilot/sessions/rep3-mns64/opprof/opprof-v1-dp0-pid521797-1784026767359409666.jsonl"
}
}
},
"started_at": 1784022845.964628,
"status": "complete"
}