state: generation 6096 (cycle)

This commit is contained in:
2026-09-12 07:37:34 +00:00
parent 9c61051417
commit 6384d59b9e
9 changed files with 2239 additions and 2239 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T06:59:46.849277+00:00",
"lastSyncTime": "2026-09-12T06:59:46.603354+00:00",
"generatedAt": "2026-09-12T07:35:30.629329+00:00",
"lastSyncTime": "2026-09-12T07:35:30.412992+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -722,17 +722,17 @@
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-04T05:07:21+00:00",
"expiresAt": "2026-10-12T07:33:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-04T05:07:21+00:00",
"latestFailureAt": "2026-09-12T07:33:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "nemotron_h",
"sourceModelIds": [
"nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
"primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8"
],
"sourceTaskIds": [
"4152400"
"4547660"
],
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
@@ -1819,19 +1819,19 @@
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 23,
"attributableFailureCount": 24,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 23,
"decisionTotal": 24,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"framework_architecture_unsupported": 12,
"framework_architecture_unsupported": 13,
"model_load": 6,
"repository_structure": 1,
"runtime_memory": 2
},
"failureCount": 30,
"failureCount": 31,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1841,7 +1841,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 30,
"total": 31,
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -2396,14 +2396,14 @@
"unresolvedFailureCount": 862
},
"vllm": {
"attributableFailureCount": 259,
"decisionFailureRate": 0.9885,
"decisionSuccessRate": 0.0115,
"decisionTotal": 262,
"attributableFailureCount": 260,
"decisionFailureRate": 0.9886,
"decisionSuccessRate": 0.0114,
"decisionTotal": 263,
"failureBreakdown": {
"ambiguous_runtime": 197,
"backend_operator": 33,
"framework_architecture_unsupported": 177,
"framework_architecture_unsupported": 178,
"memory_capacity": 6,
"model_load": 24,
"platform_infrastructure": 1,
@@ -2412,14 +2412,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 481,
"failureCount": 482,
"failureRate": 0.9938,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0062,
"total": 484,
"total": 485,
"unresolvedFailureCount": 221
},
"vllm-mlu": {
@@ -2524,7 +2524,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T06:59:46.845007+00:00",
"generatedAt": "2026-09-12T07:35:30.625131+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2663,28 +2663,28 @@
"unresolvedFailureCount": 28
},
"Iluvatar_bi-150": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.7778,
"decisionSuccessRate": 0.2222,
"decisionTotal": 36,
"attributableFailureCount": 29,
"decisionFailureRate": 0.7838,
"decisionSuccessRate": 0.2162,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 5,
"framework_architecture_unsupported": 13,
"framework_architecture_unsupported": 14,
"model_load": 7,
"repository_structure": 1,
"runtime_memory": 2,
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 72,
"failureRate": 0.9,
"failureCount": 73,
"failureRate": 0.9012,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.1,
"total": 80,
"successRate": 0.0988,
"total": 81,
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
@@ -4312,12 +4312,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 9,
"backend_operator": 4,
"framework_architecture_unsupported": 1,
"model_load": 1
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -4329,8 +4329,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 10
"total": 15,
"unresolvedFailureCount": 9
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4434,24 +4434,24 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 10,
"consecutiveFailures": 10,
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 2,
"backend_operator": 1,
"framework_architecture_unsupported": 5,
"framework_architecture_unsupported": 6,
"model_load": 3,
"repository_structure": 1
},
"failureCount": 12,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T06:25:49.409784+00:00",
"lastTerminalAt": "2026-09-12T07:35:30.412992+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4459,7 +4459,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 12,
"total": 13,
"unresolvedFailureCount": 2
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -7185,17 +7185,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1696,
"totalRecords": 1783,
"terminalRecords": 1697,
"totalRecords": 1784,
"totals": {
"attributableFailureCount": 465,
"decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1075,
"decisionTotal": 521,
"attributableFailureCount": 466,
"decisionFailureRate": 0.8927,
"decisionSuccessRate": 0.1073,
"decisionTotal": 522,
"failureBreakdown": {
"ambiguous_runtime": 397,
"backend_operator": 41,
"framework_architecture_unsupported": 284,
"framework_architecture_unsupported": 285,
"memory_capacity": 11,
"model_load": 68,
"platform_infrastructure": 4,
@@ -7205,21 +7205,20 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1640,
"failureCount": 1641,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.033,
"total": 1696,
"total": 1697,
"unresolvedFailureCount": 1171
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7228,6 +7227,7 @@
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7249,6 +7249,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1783,
"summarizedRecords": 1784,
"version": 1
}