state: generation 5152 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T11:57:54.886814+00:00",
|
||||
"lastSyncTime": "2026-09-10T11:57:54.623286+00:00",
|
||||
"generatedAt": "2026-09-10T12:06:09.429869+00:00",
|
||||
"lastSyncTime": "2026-09-10T12:06:09.109223+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1793,29 +1793,29 @@
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 69,
|
||||
"decisionFailureRate": 0.8734,
|
||||
"decisionSuccessRate": 0.1266,
|
||||
"decisionTotal": 79,
|
||||
"attributableFailureCount": 70,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 80,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 46,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 22,
|
||||
"model_load": 23,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 135,
|
||||
"failureRate": 0.931,
|
||||
"failureCount": 136,
|
||||
"failureRate": 0.9315,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.069,
|
||||
"successRate": 0.0685,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 145,
|
||||
"total": 146,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -2075,11 +2075,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2089,8 +2090,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Vastai_va16|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2291,28 +2292,28 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 122,
|
||||
"decisionFailureRate": 0.7176,
|
||||
"decisionSuccessRate": 0.2824,
|
||||
"decisionTotal": 170,
|
||||
"attributableFailureCount": 123,
|
||||
"decisionFailureRate": 0.7193,
|
||||
"decisionSuccessRate": 0.2807,
|
||||
"decisionTotal": 171,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 115,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 87,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 24,
|
||||
"model_load": 25,
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 966,
|
||||
"failureCount": 967,
|
||||
"failureRate": 0.9527,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0473,
|
||||
"total": 1014,
|
||||
"total": 1015,
|
||||
"unresolvedFailureCount": 844
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2321,7 +2322,7 @@
|
||||
"decisionSuccessRate": 0.0042,
|
||||
"decisionTotal": 236,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 166,
|
||||
"ambiguous_runtime": 167,
|
||||
"backend_operator": 29,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 6,
|
||||
@@ -2332,15 +2333,15 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 21
|
||||
},
|
||||
"failureCount": 423,
|
||||
"failureCount": 424,
|
||||
"failureRate": 0.9976,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0024,
|
||||
"total": 424,
|
||||
"unresolvedFailureCount": 187
|
||||
"total": 425,
|
||||
"unresolvedFailureCount": 188
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2443,7 +2444,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T11:57:54.880413+00:00",
|
||||
"generatedAt": "2026-09-10T12:06:09.421970+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2606,26 +2607,26 @@
|
||||
"unresolvedFailureCount": 43
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 69,
|
||||
"decisionFailureRate": 0.8734,
|
||||
"decisionSuccessRate": 0.1266,
|
||||
"decisionTotal": 79,
|
||||
"attributableFailureCount": 70,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 80,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 46,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 22,
|
||||
"model_load": 23,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 135,
|
||||
"failureRate": 0.931,
|
||||
"failureCount": 136,
|
||||
"failureRate": 0.9315,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.069,
|
||||
"total": 145,
|
||||
"successRate": 0.0685,
|
||||
"total": 146,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -2705,21 +2706,22 @@
|
||||
"decisionSuccessRate": 0.0278,
|
||||
"decisionTotal": 36,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"platform_infrastructure": 3,
|
||||
"tokenizer_compatibility": 32,
|
||||
"参数/模板问题": 9,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 79,
|
||||
"failureRate": 0.9875,
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.9877,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0125,
|
||||
"total": 80,
|
||||
"unresolvedFailureCount": 41
|
||||
"successRate": 0.0123,
|
||||
"total": 81,
|
||||
"unresolvedFailureCount": 42
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"attributableFailureCount": 47,
|
||||
@@ -4060,20 +4062,20 @@
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 8,
|
||||
"decisionFailureRate": 0.8571,
|
||||
"decisionSuccessRate": 0.1429,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.9444,
|
||||
"failureCount": 16,
|
||||
"failureRate": 0.9412,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T11:57:54.623286+00:00",
|
||||
@@ -4081,10 +4083,10 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0556,
|
||||
"successRate": 0.0588,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 18,
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -4248,21 +4250,21 @@
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 16,
|
||||
"consecutiveFailures": 2,
|
||||
"consecutiveFailures": 3,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8421,
|
||||
"decisionSuccessRate": 0.1579,
|
||||
"decisionTotal": 19,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 10,
|
||||
"model_load": 6
|
||||
"framework_architecture_unsupported": 9,
|
||||
"model_load": 7
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.85,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T05:18:58.697108+00:00",
|
||||
"lastTerminalAt": "2026-09-10T12:06:09.109223+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4480,18 +4482,19 @@
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
|
||||
"lastTerminalAt": "2026-09-09T17:24:58.529055+00:00",
|
||||
"lastTerminalAt": "2026-09-10T12:06:09.109198+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
@@ -4499,8 +4502,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -7002,19 +7005,19 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1570,
|
||||
"totalRecords": 1657,
|
||||
"terminalRecords": 1572,
|
||||
"totalRecords": 1659,
|
||||
"totals": {
|
||||
"attributableFailureCount": 411,
|
||||
"decisionFailureRate": 0.8896,
|
||||
"decisionSuccessRate": 0.1104,
|
||||
"decisionTotal": 462,
|
||||
"attributableFailureCount": 412,
|
||||
"decisionFailureRate": 0.8898,
|
||||
"decisionSuccessRate": 0.1102,
|
||||
"decisionTotal": 463,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 337,
|
||||
"ambiguous_runtime": 338,
|
||||
"backend_operator": 35,
|
||||
"framework_architecture_unsupported": 271,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 46,
|
||||
"model_load": 47,
|
||||
"platform_infrastructure": 3,
|
||||
"repository_structure": 5,
|
||||
"runtime_memory": 5,
|
||||
@@ -7022,21 +7025,21 @@
|
||||
"参数/模板问题": 95,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1519,
|
||||
"failureRate": 0.9675,
|
||||
"failureCount": 1521,
|
||||
"failureRate": 0.9676,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 51,
|
||||
"successRate": 0.0325,
|
||||
"total": 1570,
|
||||
"unresolvedFailureCount": 1105
|
||||
"successRate": 0.0324,
|
||||
"total": 1572,
|
||||
"unresolvedFailureCount": 1106
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Ascend_910-b3 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。",
|
||||
"GPU Sunrise_pt-200-x1 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 Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -7044,7 +7047,7 @@
|
||||
"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 Mthreads_s4000 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 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|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 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7065,6 +7068,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1657,
|
||||
"summarizedRecords": 1659,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user