state: generation 5340 (cycle)

This commit is contained in:
2026-09-10 20:09:24 +00:00
parent 921890c694
commit 822dbd9d2e
9 changed files with 2060 additions and 2062 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T19:56:52.084081+00:00",
"lastSyncTime": "2026-09-10T19:56:51.309700+00:00",
"generatedAt": "2026-09-10T20:06:20.200156+00:00",
"lastSyncTime": "2026-09-10T20:06:18.925896+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1789,30 +1789,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 76,
"decisionFailureRate": 0.8837,
"decisionSuccessRate": 0.1163,
"decisionTotal": 86,
"attributableFailureCount": 77,
"decisionFailureRate": 0.8851,
"decisionSuccessRate": 0.1149,
"decisionTotal": 87,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 27,
"model_load": 28,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 144,
"failureRate": 0.9351,
"failureCount": 145,
"failureRate": 0.9355,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0649,
"successRate": 0.0645,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 154,
"total": 155,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2290,29 +2290,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 130,
"decisionFailureRate": 0.7303,
"decisionSuccessRate": 0.2697,
"decisionTotal": 178,
"attributableFailureCount": 131,
"decisionFailureRate": 0.7318,
"decisionSuccessRate": 0.2682,
"decisionTotal": 179,
"failureBreakdown": {
"ambiguous_runtime": 124,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 29,
"model_load": 30,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 984,
"failureCount": 985,
"failureRate": 0.9535,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0465,
"total": 1032,
"total": 1033,
"unresolvedFailureCount": 853
},
"vllm": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T19:56:52.079960+00:00",
"generatedAt": "2026-09-10T20:06:20.193221+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2606,27 +2606,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 76,
"decisionFailureRate": 0.8837,
"decisionSuccessRate": 0.1163,
"decisionTotal": 86,
"attributableFailureCount": 77,
"decisionFailureRate": 0.8851,
"decisionSuccessRate": 0.1149,
"decisionTotal": 87,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 27,
"model_load": 28,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 144,
"failureRate": 0.9351,
"failureCount": 145,
"failureRate": 0.9355,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0649,
"total": 154,
"successRate": 0.0645,
"total": 155,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4170,10 +4170,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 1
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4185,8 +4185,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 3
"total": 3,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4268,7 +4268,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 9,
"consecutiveFailures": 10,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
@@ -4283,7 +4283,7 @@
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T19:56:51.309700+00:00",
"lastTerminalAt": "2026-09-10T20:06:18.925896+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4613,9 +4613,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-10T13:06:08.293453+00:00",
@@ -4628,8 +4628,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
@@ -6995,19 +6995,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1630,
"totalRecords": 1717,
"terminalRecords": 1631,
"totalRecords": 1718,
"totals": {
"attributableFailureCount": 425,
"decisionFailureRate": 0.891,
"decisionSuccessRate": 0.109,
"decisionTotal": 477,
"attributableFailureCount": 426,
"decisionFailureRate": 0.8912,
"decisionSuccessRate": 0.1088,
"decisionTotal": 478,
"failureBreakdown": {
"ambiguous_runtime": 378,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 51,
"model_load": 52,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -7015,30 +7015,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1578,
"failureCount": 1579,
"failureRate": 0.9681,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.0319,
"total": 1630,
"total": 1631,
"unresolvedFailureCount": 1149
},
"warnings": [
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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 MetaX_c-500 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 Biren_166m 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 hygon_k100-ai 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 Cambricon_mlu-370-x4 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 Biren_166m 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。",
"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-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 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 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。",
@@ -7053,11 +7054,10 @@
"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 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 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 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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1717,
"summarizedRecords": 1718,
"version": 1
}