state: generation 7457 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-15T00:40:40.156505+00:00",
|
||||
"lastSyncTime": "2026-09-15T00:40:39.932460+00:00",
|
||||
"generatedAt": "2026-09-15T00:56:25.975339+00:00",
|
||||
"lastSyncTime": "2026-09-15T00:56:25.725574+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1789,29 +1789,29 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 23,
|
||||
"decisionFailureRate": 0.92,
|
||||
"decisionSuccessRate": 0.08,
|
||||
"decisionTotal": 25,
|
||||
"attributableFailureCount": 24,
|
||||
"decisionFailureRate": 0.9231,
|
||||
"decisionSuccessRate": 0.0769,
|
||||
"decisionTotal": 26,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 36,
|
||||
"framework_architecture_unsupported": 20,
|
||||
"framework_architecture_unsupported": 21,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 99,
|
||||
"failureRate": 0.9802,
|
||||
"failureCount": 100,
|
||||
"failureRate": 0.9804,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0198,
|
||||
"successRate": 0.0196,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 101,
|
||||
"total": 102,
|
||||
"unresolvedFailureCount": 76
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
@@ -2574,14 +2574,14 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 162,
|
||||
"decisionFailureRate": 0.7431,
|
||||
"decisionSuccessRate": 0.2569,
|
||||
"decisionTotal": 218,
|
||||
"attributableFailureCount": 163,
|
||||
"decisionFailureRate": 0.7443,
|
||||
"decisionSuccessRate": 0.2557,
|
||||
"decisionTotal": 219,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 153,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 104,
|
||||
"framework_architecture_unsupported": 105,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 45,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2589,14 +2589,14 @@
|
||||
"参数/模板问题": 66,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1055,
|
||||
"failureCount": 1056,
|
||||
"failureRate": 0.9496,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 56,
|
||||
"successRate": 0.0504,
|
||||
"total": 1111,
|
||||
"total": 1112,
|
||||
"unresolvedFailureCount": 892
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2732,7 +2732,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-15T00:40:40.152205+00:00",
|
||||
"generatedAt": "2026-09-15T00:56:25.968195+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 39,
|
||||
@@ -2808,26 +2808,26 @@
|
||||
"unresolvedFailureCount": 59
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 23,
|
||||
"decisionFailureRate": 0.92,
|
||||
"decisionSuccessRate": 0.08,
|
||||
"decisionTotal": 25,
|
||||
"attributableFailureCount": 24,
|
||||
"decisionFailureRate": 0.9231,
|
||||
"decisionSuccessRate": 0.0769,
|
||||
"decisionTotal": 26,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 36,
|
||||
"framework_architecture_unsupported": 20,
|
||||
"framework_architecture_unsupported": 21,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 99,
|
||||
"failureRate": 0.9802,
|
||||
"failureCount": 100,
|
||||
"failureRate": 0.9804,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0198,
|
||||
"total": 101,
|
||||
"successRate": 0.0196,
|
||||
"total": 102,
|
||||
"unresolvedFailureCount": 76
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
@@ -5399,15 +5399,15 @@
|
||||
"unresolvedFailureCount": 11
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 16,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"ambiguous_runtime": 15,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
@@ -5415,7 +5415,7 @@
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-14T20:39:18.216520+00:00",
|
||||
"lastTerminalAt": "2026-09-15T00:56:25.725574+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -5424,7 +5424,7 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 17
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -9012,17 +9012,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1882,
|
||||
"totalRecords": 1975,
|
||||
"terminalRecords": 1883,
|
||||
"totalRecords": 1976,
|
||||
"totals": {
|
||||
"attributableFailureCount": 571,
|
||||
"decisionFailureRate": 0.9006,
|
||||
"decisionSuccessRate": 0.0994,
|
||||
"decisionTotal": 634,
|
||||
"attributableFailureCount": 572,
|
||||
"decisionFailureRate": 0.9008,
|
||||
"decisionSuccessRate": 0.0992,
|
||||
"decisionTotal": 635,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 453,
|
||||
"backend_operator": 44,
|
||||
"framework_architecture_unsupported": 366,
|
||||
"framework_architecture_unsupported": 367,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 78,
|
||||
"platform_infrastructure": 6,
|
||||
@@ -9032,52 +9032,52 @@
|
||||
"参数/模板问题": 116,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1819,
|
||||
"failureCount": 1820,
|
||||
"failureRate": 0.9665,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 6,
|
||||
"successCount": 63,
|
||||
"successRate": 0.0335,
|
||||
"total": 1882,
|
||||
"total": 1883,
|
||||
"unresolvedFailureCount": 1242
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 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 Vastai_va16 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 MetaX_c-500 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 Cambricon_mlu-370-x8 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。",
|
||||
"GPU hygon_k100-ai 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 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 Ascend_910-b4 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。",
|
||||
"组合 Iluvatar_mrv-100|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|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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Mthreads_s4000|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 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"GPU Cambricon_mlu-370-x4 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 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。",
|
||||
"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 Iluvatar_bi-150|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 Iluvatar_mrv-100|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 Sunrise_pt-200-x1|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。",
|
||||
"组合 Cambricon_mlu-370-x4|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 Ascend_910-b3|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 Vastai_va16|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 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 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 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Vastai_va16|vllm_fix_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 Vastai_va16|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 MetaX_c-500|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。",
|
||||
"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 Cambricon_mlu-370-x8|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 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。",
|
||||
"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 Biren_166m|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-b3|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 Vastai_va16|vllm_fix_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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|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-x4|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-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Mthreads_s4000|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 Sunrise_pt-200-x1|vllm_fix_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 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。"
|
||||
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1975,
|
||||
"summarizedRecords": 1976,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user