Gahow Wang
d5b276180d
Workload-conditioned operator profiling on patched vLLM 0.24.0 + Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64 raggedness, 8-45% token-efficiency loss vs rectangular controls); mechanism decomposition kills the padding narrative and finds the arrival-uniformization artifact (-12.9%); cross-version churn surface shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held. Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer sidecars and metrics are tracked. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
213 lines
5.3 KiB
JSON
213 lines
5.3 KiB
JSON
{
|
|
"clean_window_failures": 0,
|
|
"completed_burnins": 3,
|
|
"completed_measured_runs": 0,
|
|
"controller_pid": 2505724,
|
|
"created_at": 1783858074.2830184,
|
|
"drain_quarantined_runs": 0,
|
|
"fingerprint": {
|
|
"capture_sizes": [
|
|
1,
|
|
2,
|
|
3,
|
|
4,
|
|
5,
|
|
6,
|
|
7,
|
|
8,
|
|
16,
|
|
24,
|
|
32,
|
|
40,
|
|
48,
|
|
56,
|
|
64,
|
|
72,
|
|
80,
|
|
88,
|
|
96,
|
|
104,
|
|
112,
|
|
120,
|
|
128,
|
|
136,
|
|
144,
|
|
152,
|
|
160,
|
|
168,
|
|
176,
|
|
184,
|
|
192,
|
|
200,
|
|
208,
|
|
216,
|
|
224,
|
|
232,
|
|
240,
|
|
248,
|
|
256,
|
|
272,
|
|
288,
|
|
304,
|
|
320,
|
|
336,
|
|
352,
|
|
368,
|
|
384,
|
|
400,
|
|
416,
|
|
432,
|
|
448,
|
|
464,
|
|
480,
|
|
496,
|
|
512
|
|
],
|
|
"client_sha256": "f935486ab2588c1fca514be29b59361f53118eb000ea037863de48ce4fc76b16",
|
|
"controller_sha256": "ea2e2066a8b6d9427c59fe80db44cf87a86776570ca9066bfdff0c0b0e7f4a46",
|
|
"manifests": {
|
|
"A1": {
|
|
"path": "/home/admin/cpfs/wjh/opprof-phase5-private/manifests/P10-A1.jsonl",
|
|
"sha256": "cab8468983fb7397ec88eb5e88a44c8b1b53d8021b7867e7bec6f58d3d903806"
|
|
},
|
|
"A3": {
|
|
"path": "/home/admin/cpfs/wjh/opprof-phase5-private/manifests/P10-A3.jsonl",
|
|
"sha256": "ec5eaa29fcd3ec421e4f68a902c7e7fea9c0bc6b16f1013cef30ccc1f97bae24"
|
|
},
|
|
"base": {
|
|
"path": "/home/admin/cpfs/wjh/opprof-phase5-private/manifests/P10-base.jsonl",
|
|
"sha256": "d3b4f540ddd629dd0e34fff55c3b3837f359bdd6e5947309a1ea2a358f811ffc"
|
|
}
|
|
},
|
|
"p3_client_sha256": "ab937a5f28252559c2fd97e848a500f1094cef232823ce4b90da8c0ece7554a0",
|
|
"p3_matrix_sha256": "6ac565ff35ead305f7b2e39e6a754389d03c27ea6511b2c9e8ebc0c868c9519f",
|
|
"rate": 0.4725,
|
|
"source_commit": "4b253fd8619764b6971a7f2e3a3aa7545f6ace05",
|
|
"source_tree": "a3d536b287a724e60abbec68b45eed7e088a15d1"
|
|
},
|
|
"gpu_hours_this_stage": 0.4224752351972792,
|
|
"gpu_hours_total": 0.6476566231913037,
|
|
"missing_trace_files": 0,
|
|
"schema": 1,
|
|
"stages": {
|
|
"burnins": {
|
|
"assignments": [
|
|
{
|
|
"cell": "burnin-C00-C00",
|
|
"gpus": [
|
|
0
|
|
]
|
|
},
|
|
{
|
|
"cell": "burnin-A2-A2",
|
|
"gpus": [
|
|
1
|
|
]
|
|
},
|
|
{
|
|
"cell": "burnin-A4-A4",
|
|
"gpus": [
|
|
2
|
|
]
|
|
}
|
|
],
|
|
"burnin": true,
|
|
"clients": {},
|
|
"completed_at": 1783858361.2828288,
|
|
"confirmation": false,
|
|
"gpu_hours": 0.22518138799402448,
|
|
"load_point": "saturation",
|
|
"profile": false,
|
|
"servers": {},
|
|
"started_at": 1783858074.4911764,
|
|
"status": "complete"
|
|
},
|
|
"primary-01": {
|
|
"assignments": [
|
|
{
|
|
"cell": "base-r2-C00",
|
|
"gpus": [
|
|
0
|
|
]
|
|
},
|
|
{
|
|
"cell": "A3-r1-C00",
|
|
"gpus": [
|
|
1
|
|
]
|
|
},
|
|
{
|
|
"cell": "A1-r2-C00",
|
|
"gpus": [
|
|
2
|
|
]
|
|
},
|
|
{
|
|
"cell": "A4-r1-A4",
|
|
"gpus": [
|
|
3
|
|
]
|
|
}
|
|
],
|
|
"burnin": false,
|
|
"clients": {
|
|
"A1-r2-C00-moderate": {
|
|
"pgid": 2512122,
|
|
"pid": 2512122
|
|
},
|
|
"A3-r1-C00-moderate": {
|
|
"pgid": 2512121,
|
|
"pid": 2512121
|
|
},
|
|
"A4-r1-A4-moderate": {
|
|
"pgid": 2512123,
|
|
"pid": 2512123
|
|
},
|
|
"base-r2-C00-moderate": {
|
|
"pgid": 2512119,
|
|
"pid": 2512119
|
|
}
|
|
},
|
|
"confirmation": false,
|
|
"failure": "RuntimeError(\"client invariant failure: /home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/runs/phase5/primary/base-r2-C00/moderate: {'client_sanity': True, 'clean_duration': True, 'clean_failures_zero': True, 'failed_records_accounted': True, 'manifest_no_wrap': True, 'warmup_completions': False, 'profile_count': True, 'profile_after_clean': True, 'drain_re_adjudicated': True}; failed=[]; warmup_completions=25; warmup_gate_branch=failed; warmup_stability={'passed': False, 'reason': 'A-P3-6 stabilization criterion not met', 'window_seconds': [45.0, 60.0], 'bin_seconds': 5.0, 'step_counts': [380, 201, 187], 'scheduled_tokens': [26927, 27616, 463], 'scheduled_token_throughput': [5385.4, 5523.2, 92.6], 'mean_scheduled_token_throughput': 3667.066666666666, 'slope_tokens_per_second_squared': -529.28, 'normalized_drift': 2.1650001817983497, 'normalized_drift_limit': 0.1, 'step_indices_continuous': True}\")",
|
|
"gpu_hours": 0.4224752351972792,
|
|
"load_point": "moderate",
|
|
"profile": false,
|
|
"servers": {
|
|
"A1-r2-C00-moderate": {
|
|
"gpus": [
|
|
2
|
|
],
|
|
"pgid": 2510424,
|
|
"pid": 2510424
|
|
},
|
|
"A3-r1-C00-moderate": {
|
|
"gpus": [
|
|
1
|
|
],
|
|
"pgid": 2510423,
|
|
"pid": 2510423
|
|
},
|
|
"A4-r1-A4-moderate": {
|
|
"gpus": [
|
|
3
|
|
],
|
|
"pgid": 2510425,
|
|
"pid": 2510425
|
|
},
|
|
"base-r2-C00-moderate": {
|
|
"gpus": [
|
|
0
|
|
],
|
|
"pgid": 2510422,
|
|
"pid": 2510422
|
|
}
|
|
},
|
|
"started_at": 1783858361.3184204,
|
|
"status": "failed"
|
|
}
|
|
},
|
|
"status": "failed",
|
|
"updated_at": 1783858758.067235
|
|
}
|