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>
215 lines
7.4 KiB
JSON
215 lines
7.4 KiB
JSON
{
|
|
"completed_confirmations": 3,
|
|
"completed_primary_anchors": 21,
|
|
"failures": [
|
|
{
|
|
"failure": "RuntimeError('outside GPU processes detected: [2635013, 2635031, 2635032, 2635034]')",
|
|
"wave": "W1-tp1"
|
|
}
|
|
],
|
|
"gpu_hours_total": 2.2911728494699863,
|
|
"prior_budget_stop": {
|
|
"reason": "superseded by A-P6-1 W1 acceptance",
|
|
"spent_h20_hours": 0.4323110630779864
|
|
},
|
|
"repairs": [
|
|
{
|
|
"at": 1783867821,
|
|
"id": "phase6-owned-pgid-monitor",
|
|
"prior_gpu_hours": 0.13291816790898642,
|
|
"reason": "EngineCore marker unavailable via proc environ; use frozen Phase-3 process-group ownership"
|
|
},
|
|
{
|
|
"at": 1783869388,
|
|
"fallback_cap_activated": false,
|
|
"id": "A-P6-1",
|
|
"reason": "W1 checkpoint sidecars balance; accept eight anchors without rerun"
|
|
}
|
|
],
|
|
"schema": 1,
|
|
"started_at": 1783867644.5549395,
|
|
"status": "budget_projection_stop_before_W4",
|
|
"unconfirmed_triggers": [
|
|
{
|
|
"anchor": 0.033182214016,
|
|
"cell": "tp4_mns16"
|
|
}
|
|
],
|
|
"waves": {
|
|
"W1-tp1": {
|
|
"accounting_mode": "A-P6-1-checkpoint-sidecar",
|
|
"estimate_h20_hours": 0.35,
|
|
"gpu_hours": 0.299392895169,
|
|
"primary_anchors": 8,
|
|
"readjudication_sha256": "4ce0072dc947e492f2c7eb96c9db57c68354c12e96aa4ecb53358b836e71ceb5",
|
|
"status": "complete"
|
|
},
|
|
"W2-tp2": {
|
|
"completed_at": 1783869815.3725514,
|
|
"estimate_h20_hours": 0.65,
|
|
"gpu_hours": 0.9203650120894115,
|
|
"primary_anchors": 8,
|
|
"started_at": 1783869389.3392105,
|
|
"status": "complete",
|
|
"validations": [
|
|
{
|
|
"accounting_mode": "graceful-footer",
|
|
"cell": "tp2_mns8",
|
|
"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": 6687,
|
|
"post_ready_capture_events": [],
|
|
"stream": "/home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp2_mns8/opprof/opprof-v1-dp0-pid2661256-1783869521184806299.jsonl"
|
|
},
|
|
{
|
|
"accounting_mode": "graceful-footer",
|
|
"cell": "tp2_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": 6313,
|
|
"post_ready_capture_events": [],
|
|
"stream": "/home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp2_mns16/opprof/opprof-v1-dp0-pid2661159-1783869522696890561.jsonl"
|
|
},
|
|
{
|
|
"accounting_mode": "graceful-footer",
|
|
"cell": "tp2_mns32",
|
|
"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": 17712,
|
|
"post_ready_capture_events": [],
|
|
"stream": "/home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp2_mns32/opprof/opprof-v1-dp0-pid2661056-1783869524249984543.jsonl"
|
|
},
|
|
{
|
|
"accounting_mode": "graceful-footer",
|
|
"cell": "tp2_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": 4537,
|
|
"post_ready_capture_events": [],
|
|
"stream": "/home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp2_mns64/opprof/opprof-v1-dp0-pid2661205-1783869525995600880.jsonl"
|
|
}
|
|
]
|
|
},
|
|
"W3-tp4-trap": {
|
|
"completed_at": 1783870244.6658168,
|
|
"estimate_h20_hours": 0.85,
|
|
"gpu_hours": 0.9384967743025886,
|
|
"primary_anchors": 5,
|
|
"started_at": 1783869815.6737785,
|
|
"status": "complete",
|
|
"validations": [
|
|
{
|
|
"accounting_mode": "graceful-footer",
|
|
"cell": "tp4_mns8",
|
|
"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": 10954,
|
|
"post_ready_capture_events": [],
|
|
"stream": "/home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp4_mns8/opprof/opprof-v1-dp0-pid2670761-1783869954643149539.jsonl"
|
|
},
|
|
{
|
|
"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": 26137,
|
|
"post_ready_capture_events": [],
|
|
"stream": "/home/admin/cpfs/wjh/opprof-phase6-dash0-20260712/runs/phase6/cells/tp4_mns16/opprof/opprof-v1-dp0-pid2670831-1783869959685052499.jsonl"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"budget_stop": {
|
|
"before_wave": "W4-tp4",
|
|
"spent_h20_hours": 2.2911728494699863,
|
|
"wave_estimate_h20_hours": 0.65,
|
|
"safety_buffer_h20_hours": 0.10,
|
|
"projected_total_h20_hours": 3.0411728494699863,
|
|
"hard_cap_h20_hours": 3.0,
|
|
"excess_h20_hours": 0.04117284946998634,
|
|
"remaining_cells": [
|
|
"tp4_mns32",
|
|
"tp4_mns64"
|
|
],
|
|
"remaining_primary_anchors": 4
|
|
}
|
|
}
|