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

Track simulator fidelity experiment artifacts

Browse Source
This commit is contained in:
Gahow Wang
2026-07-19 15:31:09 +08:00
parent e0ea7e9961
commit 4c8d581a5b
115 changed files with 42355 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27855
runs/frontier-multicase-sufficiency-v1/artifacts/frontier-t0-surface-v1/frontier_surface_frozen.json Normal file
View File

File diff suppressed because it is too large Load Diff

61
runs/frontier-multicase-sufficiency-v1/artifacts/t0-real-surface-v1/exclusions.json Normal file
View File

@@ -0,0 +1,61 @@
{
"schema": "qwen235b-t0-real-exclusions-v1",
"policy": "Exclude the complete output directory whenever another process shares any allocated GPU or benchmark endpoint during warmup or a measured anchor.",
"excluded_attempts": [
{
"reason": "Fleet monitor re-probed during model load and oversubscribed both TP4 allocations; the later MNS128 attempts overlapped the MNS64 warmup and start of r0p10.",
"remote_quarantine": "/home/admin/cpfs/wjh/aituner/aituner-fidelity-v1/artifacts/contaminated-queue-race-20260716T045500Z",
"run_ids": [
"qwen235b-t0-real-tp4_mns64_mbt8192-20260716-v1-20260716T045338281933Z",
"qwen235b-t0-real-tp4_mns64_mbt16384-20260716-v1-20260716T045339503446Z",
"qwen235b-t0-real-tp4_mns128_mbt8192-20260716-v1-20260716T045458846499Z",
"qwen235b-t0-real-tp4_mns128_mbt16384-20260716-v1-20260716T045500253803Z"
]
},
{
"reason": "A dispatch command still copying the source was mistakenly resubmitted. The duplicate controllers reused the first pair's open ports and issued concurrent warmup requests, so both the original and duplicate outputs were rejected.",
"remote_quarantine": "/home/admin/cpfs/wjh/aituner/aituner-fidelity-v1/artifacts/contaminated-duplicate-dispatch-20260716T0501Z",
"run_ids": [
"qwen235b-t0-real-tp4_mns64_mbt8192-20260716-v1-20260716T050017477963Z",
"qwen235b-t0-real-tp4_mns64_mbt16384-20260716-v1-20260716T050018748070Z",
"qwen235b-t0-real-tp4_mns64_mbt8192-20260716-v1-20260716T050123485776Z",
"qwen235b-t0-real-tp4_mns64_mbt16384-20260716-v1-20260716T050124800483Z"
]
},
{
"reason": "Clean diagnostic run exposed cross-anchor execution-state leakage: TPOT at 1.60 req/s failed after a sustained 0.10 anchor but passed after a 2.40 anchor. The multi-rate-per-server contract does not match Frontier's independent rate runs, so the complete attempt is diagnostic-only.",
"remote_quarantine": "/home/admin/cpfs/wjh/aituner/aituner-fidelity-v1/artifacts/diagnostic-cross-anchor-state-20260716T0504Z",
"run_ids": [
"qwen235b-t0-real-tp4_mns64_mbt8192-20260716-v1-20260716T050405703312Z",
"qwen235b-t0-real-tp4_mns64_mbt16384-20260716-v1-20260716T050407104293Z"
]
}
],
"accepted_attempts": [
"qwen235b-t0-real-tp4_mns64_mbt8192-20260716-v1-20260716T054640909739Z",
"qwen235b-t0-real-tp4_mns64_mbt16384-20260716-v1-20260716T054642115787Z",
"qwen235b-t0-real-tp4_mns64_mbt8192-expansion-r3p20-20260716-v1-20260716T062904775741Z",
"qwen235b-t0-real-tp4_mns64_mbt16384-expansion-r3p20-20260716-v1-20260716T062906244819Z",
"qwen235b-t0-real-tp4_mns128_mbt8192-20260716-v1-20260716T063826749477Z",
"qwen235b-t0-real-tp4_mns128_mbt16384-20260716-v1-20260716T063827805737Z",
"qwen235b-t0-real-tp4_mns128_mbt8192-expansion-r3p20-20260716-v1-20260716T072121119478Z",
"qwen235b-t0-real-tp4_mns128_mbt16384-expansion-r3p20-20260716-v1-20260716T072122501851Z",
"qwen235b-t0-real-tp8_mns64_mbt8192-20260716-v1-20260716T073151443129Z",
"qwen235b-t0-real-tp8_mns64_mbt8192-expansion-r2p40-20260716-v1-20260716T081536141326Z",
"qwen235b-t0-real-tp8_mns64_mbt8192-expansion-r3p20-20260716-v1-20260716T082603837807Z",
"qwen235b-t0-real-tp8_mns64_mbt16384-20260716-v1-20260716T083632620015Z",
"qwen235b-t0-real-tp8_mns64_mbt16384-expansion-r2p40-20260716-v1-20260716T092040851202Z",
"qwen235b-t0-real-tp8_mns128_mbt8192-20260716-v1-20260716T093245831612Z",
"qwen235b-t0-real-tp8_mns128_mbt8192-expansion-r2p40-20260716-v1-20260716T101734683241Z",
"qwen235b-t0-real-tp8_mns128_mbt16384-20260716-v1-20260716T102855604708Z",
"qwen235b-t0-real-tp8_mns128_mbt16384-expansion-r2p40-20260716-v1-20260716T111437770615Z",
"qwen235b-t0-real-tp8_mns128_mbt16384-expansion-r3p20-20260716-v1-20260716T112608807037Z"
],
"accepted_warnings": [
{
"run_id": "qwen235b-t0-real-tp8_mns64_mbt8192-20260716-v1-20260716T073151443129Z",
"anchor": "round1/r1p20",
"reason": "One rank-7 TCPStore heartbeat warning occurred 1.1 s after the complete 64-request result was written, while all eight workers were terminating after the runner intentionally stopped the fresh server. The application then shut down normally; no request, engine, OOM, or in-window NCCL failure occurred."
}
]
}

299
runs/frontier-multicase-sufficiency-v1/artifacts/t0-real-surface-v1/real-plan-executed.json Normal file
View File

@@ -0,0 +1,299 @@
{
"cells": [
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 8192,
"mns": 64,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns64_mbt8192",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 3.284259259259259,
"expected_wall_seconds": 2955.833333333333,
"preregistered_rates": [
0.1,
1.6,
2.4
],
"rates": [
0.1,
1.6,
2.4,
3.2
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.60": 32,
"2.40": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 16384,
"mns": 64,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns64_mbt16384",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 3.284259259259259,
"expected_wall_seconds": 2955.833333333333,
"preregistered_rates": [
0.1,
1.6,
2.4
],
"rates": [
0.1,
1.6,
2.4,
3.2
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.60": 32,
"2.40": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 8192,
"mns": 128,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns128_mbt8192",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 3.284259259259259,
"expected_wall_seconds": 2955.833333333333,
"preregistered_rates": [
0.1,
1.6,
2.4
],
"rates": [
0.1,
1.6,
2.4,
3.2
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.60": 32,
"2.40": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 16384,
"mns": 128,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns128_mbt16384",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 3.284259259259259,
"expected_wall_seconds": 2955.833333333333,
"preregistered_rates": [
0.1,
1.6,
2.4
],
"rates": [
0.1,
1.6,
2.4,
3.2
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.60": 32,
"2.40": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 8192,
"mns": 64,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns64_mbt8192",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 6.712962962962962,
"expected_wall_seconds": 3020.833333333333,
"preregistered_rates": [
0.1,
1.2,
1.6
],
"rates": [
0.1,
1.2,
1.6,
2.4,
3.2
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.20": 24,
"1.60": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 16384,
"mns": 64,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns64_mbt16384",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 6.712962962962962,
"expected_wall_seconds": 3020.833333333333,
"preregistered_rates": [
0.1,
1.2,
1.6
],
"rates": [
0.1,
1.2,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.20": 24,
"1.60": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 8192,
"mns": 128,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns128_mbt8192",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 6.712962962962962,
"expected_wall_seconds": 3020.833333333333,
"preregistered_rates": [
0.1,
1.2,
1.6
],
"rates": [
0.1,
1.2,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.20": 24,
"1.60": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 16384,
"mns": 128,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns128_mbt16384",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 6.712962962962962,
"expected_wall_seconds": 3020.833333333333,
"preregistered_rates": [
0.1,
1.2,
1.6
],
"rates": [
0.1,
1.2,
1.6,
2.4,
3.2
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.20": 24,
"1.60": 32
}
}
],
"execution_protocol_amendment": {
"contract": "fresh server and target-rate warmup for every config-rate-round",
"reason": "observed cross-anchor GPU/kernel/batch warm-state leakage",
"timing": "after excluded multi-rate-per-server diagnostic and before any accepted real surface cell"
},
"expansion_artifact_roots": [
"artifacts/t0-real-expansion-r2p40-v1",
"artifacts/t0-real-expansion-r3p20-v1"
],
"expected_total_h20_gpu_hours": 39.98888888888888,
"frontier_freeze": {
"path": "/home/gahow/phd/aituner/runs/frontier-multicase-sufficiency-v1/artifacts/frontier-t0-surface-v1/frontier_surface_frozen.json",
"sha256": "801aa36451c8647f71cc87011144622d2203786e82f189ed1375d964399b106a"
},
"hard_timeout_hours_per_cell": 2.0,
"post_pilot_sensitivities": [
"tpot_120ms",
"tpot_150ms",
"tpot_180ms"
],
"preregistered_plan": {
"path": "/home/gahow/phd/aituner/runs/frontier-multicase-sufficiency-v1/artifacts/t0-real-surface-v1/real-plan.json",
"sha256": "f7acb45d1183a6026dba4bbf9bc2d7578452b815b8de0035ca732512f3d9d47a"
},
"schema": "qwen235b-t0-real-executed-plan-v1",
"selection_slo": "tpot_150ms",
"selection_timing": "rate anchors frozen after complete simulator surface and before any accepted real surface cell",
"status": "complete",
"strict_preregistered_slo": "tpot_40ms"
}

187
runs/frontier-multicase-sufficiency-v1/artifacts/t0-real-surface-v1/real-plan-pre-anchor-isolation-amendment.json Normal file
View File

@@ -0,0 +1,187 @@
{
"cells": [
{
"config": {
"mbt": 8192,
"mns": 64,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns64_mbt8192",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 2.2125,
"expected_wall_seconds": 1991.25,
"rates": [
0.1,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2
},
{
"config": {
"mbt": 16384,
"mns": 64,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns64_mbt16384",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 2.2125,
"expected_wall_seconds": 1991.25,
"rates": [
0.1,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2
},
{
"config": {
"mbt": 8192,
"mns": 128,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns128_mbt8192",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 2.2125,
"expected_wall_seconds": 1991.25,
"rates": [
0.1,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2
},
{
"config": {
"mbt": 16384,
"mns": 128,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns128_mbt16384",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 2.2125,
"expected_wall_seconds": 1991.25,
"rates": [
0.1,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2
},
{
"config": {
"mbt": 8192,
"mns": 64,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns64_mbt8192",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 4.541666666666667,
"expected_wall_seconds": 2043.75,
"rates": [
0.1,
1.2,
1.6
],
"requests_per_anchor": 64,
"rounds": 2
},
{
"config": {
"mbt": 16384,
"mns": 64,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns64_mbt16384",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 4.541666666666667,
"expected_wall_seconds": 2043.75,
"rates": [
0.1,
1.2,
1.6
],
"requests_per_anchor": 64,
"rounds": 2
},
{
"config": {
"mbt": 8192,
"mns": 128,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns128_mbt8192",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 4.541666666666667,
"expected_wall_seconds": 2043.75,
"rates": [
0.1,
1.2,
1.6
],
"requests_per_anchor": 64,
"rounds": 2
},
{
"config": {
"mbt": 16384,
"mns": 128,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns128_mbt16384",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 4.541666666666667,
"expected_wall_seconds": 2043.75,
"rates": [
0.1,
1.2,
1.6
],
"requests_per_anchor": 64,
"rounds": 2
}
],
"expected_total_h20_gpu_hours": 27.016666666666666,
"frontier_freeze": {
"path": "/home/gahow/phd/aituner/runs/frontier-multicase-sufficiency-v1/artifacts/frontier-t0-surface-v1/frontier_surface_frozen.json",
"sha256": "801aa36451c8647f71cc87011144622d2203786e82f189ed1375d964399b106a"
},
"hard_timeout_hours_per_cell": 2.0,
"post_pilot_sensitivities": [
"tpot_120ms",
"tpot_150ms",
"tpot_180ms"
],
"schema": "qwen235b-t0-real-plan-v1",
"selection_slo": "tpot_150ms",
"selection_timing": "after_complete_simulator_freeze_before_any_real_surface_cell",
"strict_preregistered_slo": "tpot_40ms"
}

240
runs/frontier-multicase-sufficiency-v1/artifacts/t0-real-surface-v1/real-plan.json Normal file
View File

@@ -0,0 +1,240 @@
{
"cells": [
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 8192,
"mns": 64,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns64_mbt8192",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 3.284259259259259,
"expected_wall_seconds": 2955.833333333333,
"rates": [
0.1,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.60": 32,
"2.40": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 16384,
"mns": 64,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns64_mbt16384",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 3.284259259259259,
"expected_wall_seconds": 2955.833333333333,
"rates": [
0.1,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.60": 32,
"2.40": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 8192,
"mns": 128,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns128_mbt8192",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 3.284259259259259,
"expected_wall_seconds": 2955.833333333333,
"rates": [
0.1,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.60": 32,
"2.40": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 16384,
"mns": 128,
"moe_ep": 1,
"moe_tp": 4,
"name": "tp4_mns128_mbt16384",
"num_gpu_blocks": 26101,
"tp": 4
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 3.284259259259259,
"expected_wall_seconds": 2955.833333333333,
"rates": [
0.1,
1.6,
2.4
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.60": 32,
"2.40": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 8192,
"mns": 64,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns64_mbt8192",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 6.712962962962962,
"expected_wall_seconds": 3020.833333333333,
"rates": [
0.1,
1.2,
1.6
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.20": 24,
"1.60": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 16384,
"mns": 64,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns64_mbt16384",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 6.712962962962962,
"expected_wall_seconds": 3020.833333333333,
"rates": [
0.1,
1.2,
1.6
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.20": 24,
"1.60": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 8192,
"mns": 128,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns128_mbt8192",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 6.712962962962962,
"expected_wall_seconds": 3020.833333333333,
"rates": [
0.1,
1.2,
1.6
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.20": 24,
"1.60": 32
}
},
{
"anchor_isolation": "fresh_server_per_rate_per_round",
"config": {
"mbt": 16384,
"mns": 128,
"moe_ep": 8,
"moe_tp": 1,
"name": "tp8_mns128_mbt16384",
"num_gpu_blocks": 62351,
"tp": 8
},
"expansion_rule": "if real labels do not bracket a transition, expand to the next frozen lattice anchor and repeat both directions",
"expected_h20_gpu_hours": 6.712962962962962,
"expected_wall_seconds": 3020.833333333333,
"rates": [
0.1,
1.2,
1.6
],
"requests_per_anchor": 64,
"rounds": 2,
"target_rate_warmup_requests": {
"0.10": 4,
"1.20": 24,
"1.60": 32
}
}
],
"execution_protocol_amendment": {
"contract": "fresh server and target-rate warmup for every config-rate-round",
"reason": "observed cross-anchor GPU/kernel/batch warm-state leakage",
"timing": "after excluded multi-rate-per-server diagnostic and before any accepted real surface cell"
},
"expected_total_h20_gpu_hours": 39.98888888888888,
"frontier_freeze": {
"path": "/home/gahow/phd/aituner/runs/frontier-multicase-sufficiency-v1/artifacts/frontier-t0-surface-v1/frontier_surface_frozen.json",
"sha256": "801aa36451c8647f71cc87011144622d2203786e82f189ed1375d964399b106a"
},
"hard_timeout_hours_per_cell": 2.0,
"post_pilot_sensitivities": [
"tpot_120ms",
"tpot_150ms",
"tpot_180ms"
],
"schema": "qwen235b-t0-real-plan-v1",
"selection_slo": "tpot_150ms",
"selection_timing": "rate anchors frozen after complete simulator surface and before any accepted real surface cell",
"strict_preregistered_slo": "tpot_40ms"
}