state: generation 5063 (cycle)

This commit is contained in:
2026-09-10 07:55:17 +00:00
parent b2b7a36ab0
commit 0838dbfe5d
10 changed files with 2437 additions and 2417 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T07:29:03.167497+00:00",
"lastSyncTime": "2026-09-10T07:29:02.941680+00:00",
"generatedAt": "2026-09-10T07:53:10.960863+00:00",
"lastSyncTime": "2026-09-10T07:53:10.699435+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1576,25 +1576,25 @@
"decisionSuccessRate": 0.2222,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 5,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 5,
"验证失败": 22
},
"failureCount": 49,
"failureRate": 0.9608,
"failureCount": 52,
"failureRate": 0.963,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0392,
"successRate": 0.037,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 51,
"unresolvedFailureCount": 42
"total": 54,
"unresolvedFailureCount": 45
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 7,
@@ -1602,11 +1602,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 7,
"参数/模板问题": 3
},
"failureCount": 23,
"failureCount": 24,
"failureRate": 1.0,
"framework": "vllm-mlu",
"pendingCount": 0,
@@ -1616,8 +1616,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 23,
"unresolvedFailureCount": 16
"total": 24,
"unresolvedFailureCount": 17
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -1912,9 +1912,9 @@
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 39,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 39,
"decisionFailureRate": 0.975,
"decisionSuccessRate": 0.025,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 20,
@@ -1924,16 +1924,16 @@
"参数/模板问题": 9
},
"failureCount": 55,
"failureRate": 1.0,
"failureRate": 0.9821,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.0179,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 55,
"total": 56,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2300,7 +2300,7 @@
"decisionSuccessRate": 0.284,
"decisionTotal": 169,
"failureBreakdown": {
"ambiguous_runtime": 109,
"ambiguous_runtime": 112,
"backend_operator": 2,
"framework_architecture_unsupported": 87,
"memory_capacity": 5,
@@ -2309,21 +2309,21 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 959,
"failureRate": 0.9523,
"failureCount": 962,
"failureRate": 0.9525,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0477,
"total": 1007,
"unresolvedFailureCount": 838
"successRate": 0.0475,
"total": 1010,
"unresolvedFailureCount": 841
},
"vllm": {
"attributableFailureCount": 230,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"decisionFailureRate": 0.9957,
"decisionSuccessRate": 0.0043,
"decisionTotal": 231,
"failureBreakdown": {
"ambiguous_runtime": 150,
"backend_operator": 24,
@@ -2337,13 +2337,13 @@
"参数/模板问题": 21
},
"failureCount": 402,
"failureRate": 1.0,
"failureRate": 0.9975,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 402,
"successCount": 1,
"successRate": 0.0025,
"total": 403,
"unresolvedFailureCount": 171
},
"vllm-mlu": {
@@ -2352,19 +2352,19 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 7,
"参数/模板问题": 3
},
"failureCount": 23,
"failureCount": 24,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 23,
"unresolvedFailureCount": 16
"total": 24,
"unresolvedFailureCount": 17
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 3,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T07:29:03.163136+00:00",
"generatedAt": "2026-09-10T07:53:10.956424+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2549,22 +2549,22 @@
"decisionSuccessRate": 0.1053,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 32,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 85,
"failureRate": 0.977,
"failureCount": 89,
"failureRate": 0.978,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.023,
"total": 87,
"unresolvedFailureCount": 68
"successRate": 0.022,
"total": 91,
"unresolvedFailureCount": 72
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -2655,9 +2655,9 @@
},
"MetaX_c-500": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.8125,
"decisionSuccessRate": 0.1875,
"decisionTotal": 48,
"decisionFailureRate": 0.7959,
"decisionSuccessRate": 0.2041,
"decisionTotal": 49,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 20,
@@ -2668,13 +2668,13 @@
"验证失败": 48
},
"failureCount": 111,
"failureRate": 0.925,
"failureRate": 0.9174,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.075,
"total": 120,
"successCount": 10,
"successRate": 0.0826,
"total": 121,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -2865,9 +2865,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "llama",
@@ -2879,8 +2879,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
@@ -3505,25 +3505,25 @@
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 10,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"decisionFailureRate": 0.9091,
"decisionSuccessRate": 0.0909,
"decisionTotal": 11,
"failureBreakdown": {
"backend_operator": 10
},
"failureCount": 10,
"failureRate": 1.0,
"failureRate": 0.9091,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.0909,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 10,
"total": 11,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
@@ -4078,28 +4078,28 @@
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 1,
"tokenizer_compatibility": 1
},
"failureCount": 13,
"failureRate": 0.9286,
"failureCount": 16,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T05:27:18.447582+00:00",
"lastTerminalAt": "2026-09-10T07:53:10.699377+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0714,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 11
"total": 16,
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
@@ -4109,11 +4109,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 4,
"参数/模板问题": 1
},
"failureCount": 15,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4125,8 +4125,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 11
"total": 16,
"unresolvedFailureCount": 12
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4700,9 +4700,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T15:41:33.599000+00:00",
@@ -4715,8 +4715,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
@@ -5296,9 +5296,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
@@ -5311,8 +5311,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt|34": {
"attributableFailureCount": 1,
@@ -6248,6 +6248,28 @@
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|28": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 28,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
@@ -6897,15 +6919,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1528,
"totalRecords": 1615,
"terminalRecords": 1533,
"totalRecords": 1620,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 449,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 450,
"failureBreakdown": {
"ambiguous_runtime": 309,
"ambiguous_runtime": 313,
"backend_operator": 29,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6917,21 +6939,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1479,
"failureRate": 0.9679,
"failureCount": 1483,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0321,
"total": 1528,
"unresolvedFailureCount": 1077
"successCount": 50,
"successRate": 0.0326,
"total": 1533,
"unresolvedFailureCount": 1081
},
"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 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。",
"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。",
@@ -6939,7 +6961,7 @@
"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 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。",
"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。",
@@ -6960,6 +6982,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1615,
"summarizedRecords": 1620,
"version": 1
}