state: generation 6111 (cycle)

This commit is contained in:
2026-09-12 08:22:31 +00:00
parent 7d97313685
commit 814f9feb12
9 changed files with 2066 additions and 2066 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T08:11:37.726028+00:00",
"lastSyncTime": "2026-09-12T08:11:37.402333+00:00",
"generatedAt": "2026-09-12T08:20:40.395370+00:00",
"lastSyncTime": "2026-09-12T08:20:40.114700+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -539,17 +539,17 @@
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-04T23:17:21+00:00",
"expiresAt": "2026-10-12T08:13:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-04T23:17:21+00:00",
"latestFailureAt": "2026-09-12T08:13:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "nemotron_h",
"sourceModelIds": [
"nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15"
"primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8"
],
"sourceTaskIds": [
"4268240"
"4543517"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -1819,19 +1819,19 @@
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 24,
"attributableFailureCount": 25,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 24,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"backend_operator": 3,
"framework_architecture_unsupported": 13,
"model_load": 6,
"repository_structure": 1,
"runtime_memory": 2
},
"failureCount": 31,
"failureCount": 32,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1841,14 +1841,14 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 31,
"total": 32,
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 88,
"decisionFailureRate": 0.88,
"decisionSuccessRate": 0.12,
"decisionTotal": 100,
"decisionFailureRate": 0.8713,
"decisionSuccessRate": 0.1287,
"decisionTotal": 101,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
@@ -1859,16 +1859,16 @@
"验证失败": 47
},
"failureCount": 157,
"failureRate": 0.929,
"failureRate": 0.9235,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 12,
"successRate": 0.071,
"successCount": 13,
"successRate": 0.0765,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 169,
"total": 170,
"unresolvedFailureCount": 68
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2305,19 +2305,19 @@
"unresolvedFailureCount": 8
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 40,
"attributableFailureCount": 41,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 40,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 29,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 57,
"failureCount": 58,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2327,7 +2327,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 57,
"total": 58,
"unresolvedFailureCount": 17
}
},
@@ -2371,9 +2371,9 @@
},
"unknown": {
"attributableFailureCount": 143,
"decisionFailureRate": 0.7371,
"decisionSuccessRate": 0.2629,
"decisionTotal": 194,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 195,
"failureBreakdown": {
"ambiguous_runtime": 131,
"backend_operator": 4,
@@ -2386,24 +2386,24 @@
"验证失败": 673
},
"failureCount": 1007,
"failureRate": 0.9518,
"failureRate": 0.9509,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 51,
"successRate": 0.0482,
"total": 1058,
"successCount": 52,
"successRate": 0.0491,
"total": 1059,
"unresolvedFailureCount": 863
},
"vllm": {
"attributableFailureCount": 261,
"decisionFailureRate": 0.9886,
"decisionSuccessRate": 0.0114,
"decisionTotal": 264,
"attributableFailureCount": 263,
"decisionFailureRate": 0.9887,
"decisionSuccessRate": 0.0113,
"decisionTotal": 266,
"failureBreakdown": {
"ambiguous_runtime": 198,
"backend_operator": 33,
"framework_architecture_unsupported": 179,
"backend_operator": 34,
"framework_architecture_unsupported": 180,
"memory_capacity": 6,
"model_load": 24,
"platform_infrastructure": 1,
@@ -2412,14 +2412,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 484,
"failureRate": 0.9938,
"failureCount": 486,
"failureRate": 0.9939,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0062,
"total": 487,
"successRate": 0.0061,
"total": 489,
"unresolvedFailureCount": 222
},
"vllm-mlu": {
@@ -2524,7 +2524,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T08:11:37.720275+00:00",
"generatedAt": "2026-09-12T08:20:40.389446+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2663,13 +2663,13 @@
"unresolvedFailureCount": 28
},
"Iluvatar_bi-150": {
"attributableFailureCount": 29,
"decisionFailureRate": 0.7838,
"decisionSuccessRate": 0.2162,
"decisionTotal": 37,
"attributableFailureCount": 30,
"decisionFailureRate": 0.7895,
"decisionSuccessRate": 0.2105,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 5,
"backend_operator": 6,
"framework_architecture_unsupported": 14,
"model_load": 7,
"repository_structure": 1,
@@ -2677,21 +2677,21 @@
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 73,
"failureRate": 0.9012,
"failureCount": 74,
"failureRate": 0.9024,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.0988,
"total": 81,
"successRate": 0.0976,
"total": 82,
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 89,
"decisionFailureRate": 0.8812,
"decisionSuccessRate": 0.1188,
"decisionTotal": 101,
"decisionFailureRate": 0.8725,
"decisionSuccessRate": 0.1275,
"decisionTotal": 102,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
@@ -2702,13 +2702,13 @@
"验证失败": 47
},
"failureCount": 158,
"failureRate": 0.9294,
"failureRate": 0.924,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 12,
"successRate": 0.0706,
"total": 170,
"successCount": 13,
"successRate": 0.076,
"total": 171,
"unresolvedFailureCount": 68
},
"Kunlunxin_p-800": {
@@ -2830,13 +2830,13 @@
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
"attributableFailureCount": 43,
"attributableFailureCount": 44,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 43,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 32,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
@@ -2844,14 +2844,14 @@
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 98,
"failureCount": 99,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 98,
"total": 99,
"unresolvedFailureCount": 55
}
},
@@ -4434,24 +4434,24 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 11,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 2,
"backend_operator": 1,
"backend_operator": 2,
"framework_architecture_unsupported": 6,
"model_load": 3,
"repository_structure": 1
},
"failureCount": 13,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T07:35:30.412992+00:00",
"lastTerminalAt": "2026-09-12T08:20:40.114654+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4459,31 +4459,31 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 13,
"total": 14,
"unresolvedFailureCount": 2
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
"consecutiveFailures": 1,
"attributableFailureCount": 15,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 2,
"model_load": 14
"model_load": 13
},
"failureCount": 18,
"failureRate": 0.9,
"failureCount": 17,
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T01:25:57.322172+00:00",
"lastTerminalAt": "2026-09-12T08:20:40.114700+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1,
"successCount": 3,
"successRate": 0.15,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
@@ -4779,16 +4779,16 @@
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 4,
"model_load": 1,
"repository_structure": 2,
"repository_structure": 1,
"runtime_memory": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T08:11:37.402305+00:00",
"lastTerminalAt": "2026-09-12T08:20:40.114686+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7185,17 +7185,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1701,
"totalRecords": 1788,
"terminalRecords": 1704,
"totalRecords": 1791,
"totals": {
"attributableFailureCount": 468,
"decisionFailureRate": 0.8931,
"decisionSuccessRate": 0.1069,
"decisionTotal": 524,
"attributableFailureCount": 470,
"decisionFailureRate": 0.8918,
"decisionSuccessRate": 0.1082,
"decisionTotal": 527,
"failureBreakdown": {
"ambiguous_runtime": 399,
"backend_operator": 41,
"framework_architecture_unsupported": 287,
"backend_operator": 42,
"framework_architecture_unsupported": 288,
"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": 1645,
"failureRate": 0.9671,
"failureCount": 1647,
"failureRate": 0.9665,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0329,
"total": 1701,
"successCount": 57,
"successRate": 0.0335,
"total": 1704,
"unresolvedFailureCount": 1173
},
"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": 1788,
"summarizedRecords": 1791,
"version": 1
}