state: generation 7086 (cycle)

This commit is contained in:
2026-09-14 08:31:47 +00:00
parent a9c3e19946
commit 3e176c67b6
10 changed files with 2331 additions and 2214 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-14T07:52:31.153148+00:00",
"lastSyncTime": "2026-09-14T07:52:30.913060+00:00",
"generatedAt": "2026-09-14T08:29:32.873595+00:00",
"lastSyncTime": "2026-09-14T08:29:32.453371+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1679,31 +1679,31 @@
"unresolvedFailureCount": 35
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 31,
"decisionFailureRate": 0.9688,
"decisionSuccessRate": 0.0312,
"decisionTotal": 32,
"attributableFailureCount": 32,
"decisionFailureRate": 0.9697,
"decisionSuccessRate": 0.0303,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 29,
"ambiguous_runtime": 30,
"backend_operator": 4,
"framework_architecture_unsupported": 23,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"model_load": 2,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 87,
"failureRate": 0.9886,
"failureCount": 89,
"failureRate": 0.9889,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0114,
"successRate": 0.0111,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 88,
"unresolvedFailureCount": 56
"total": 90,
"unresolvedFailureCount": 57
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 4,
@@ -1779,16 +1779,17 @@
"unresolvedFailureCount": 47
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 7,
"attributableFailureCount": 8,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 7,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 30,
"failureCount": 31,
"failureRate": 1.0,
"framework": "vllm-mlu",
"pendingCount": 0,
@@ -1798,7 +1799,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 30,
"total": 31,
"unresolvedFailureCount": 23
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
@@ -1931,28 +1932,28 @@
"unresolvedFailureCount": 32
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 8,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 10,
"attributableFailureCount": 9,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 6,
"backend_operator": 3,
"framework_architecture_unsupported": 3,
"model_load": 1,
"runtime_memory": 1
"runtime_memory": 2
},
"failureCount": 14,
"failureRate": 0.875,
"failureCount": 15,
"failureRate": 0.8824,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.125,
"successRate": 0.1176,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 16,
"total": 17,
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -2080,10 +2081,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 35,
"ambiguous_runtime": 36,
"参数/模板问题": 1
},
"failureCount": 36,
"failureCount": 37,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2093,8 +2094,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 36,
"unresolvedFailureCount": 36
"total": 37,
"unresolvedFailureCount": 37
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2510,14 +2511,14 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 159,
"decisionFailureRate": 0.7465,
"decisionSuccessRate": 0.2535,
"decisionTotal": 213,
"attributableFailureCount": 160,
"decisionFailureRate": 0.7477,
"decisionSuccessRate": 0.2523,
"decisionTotal": 214,
"failureBreakdown": {
"ambiguous_runtime": 147,
"ambiguous_runtime": 148,
"backend_operator": 4,
"framework_architecture_unsupported": 102,
"framework_architecture_unsupported": 103,
"memory_capacity": 5,
"model_load": 45,
"platform_infrastructure": 1,
@@ -2525,15 +2526,15 @@
"参数/模板问题": 61,
"验证失败": 673
},
"failureCount": 1041,
"failureRate": 0.9507,
"failureCount": 1043,
"failureRate": 0.9508,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 54,
"successRate": 0.0493,
"total": 1095,
"unresolvedFailureCount": 881
"successRate": 0.0492,
"total": 1097,
"unresolvedFailureCount": 882
},
"vllm": {
"attributableFailureCount": 310,
@@ -2563,23 +2564,24 @@
"unresolvedFailureCount": 234
},
"vllm-mlu": {
"attributableFailureCount": 7,
"attributableFailureCount": 8,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 7,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 30,
"failureCount": 31,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 30,
"total": 31,
"unresolvedFailureCount": 23
},
"vllm-patch-tokenizer": {
@@ -2602,25 +2604,25 @@
"unresolvedFailureCount": 8
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 8,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 10,
"attributableFailureCount": 9,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 6,
"backend_operator": 3,
"framework_architecture_unsupported": 3,
"model_load": 1,
"runtime_memory": 1
"runtime_memory": 2
},
"failureCount": 14,
"failureRate": 0.875,
"failureCount": 15,
"failureRate": 0.8824,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.125,
"total": 16,
"successRate": 0.1176,
"total": 17,
"unresolvedFailureCount": 6
},
"vllm_fix_tokenizer": {
@@ -2629,7 +2631,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 53,
"failureBreakdown": {
"ambiguous_runtime": 37,
"ambiguous_runtime": 38,
"backend_operator": 2,
"framework_architecture_unsupported": 8,
"model_load": 1,
@@ -2637,15 +2639,15 @@
"tokenizer_compatibility": 42,
"参数/模板问题": 7
},
"failureCount": 101,
"failureCount": 102,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 0,
"successRate": 0.0,
"total": 101,
"unresolvedFailureCount": 44
"total": 102,
"unresolvedFailureCount": 45
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2666,7 +2668,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-14T07:52:31.148510+00:00",
"generatedAt": "2026-09-14T08:29:32.865753+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 33,
@@ -2717,28 +2719,28 @@
"unresolvedFailureCount": 223
},
"Biren_166m": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.9722,
"decisionSuccessRate": 0.0278,
"decisionTotal": 36,
"attributableFailureCount": 36,
"decisionFailureRate": 0.973,
"decisionSuccessRate": 0.027,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 29,
"ambiguous_runtime": 30,
"backend_operator": 4,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 91,
"failureRate": 0.9891,
"failureCount": 93,
"failureRate": 0.9894,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0109,
"total": 92,
"unresolvedFailureCount": 56
"successRate": 0.0106,
"total": 94,
"unresolvedFailureCount": 57
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 22,
@@ -2763,26 +2765,26 @@
"unresolvedFailureCount": 75
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 18,
"decisionFailureRate": 0.9,
"decisionSuccessRate": 0.1,
"decisionTotal": 20,
"attributableFailureCount": 19,
"decisionFailureRate": 0.9048,
"decisionSuccessRate": 0.0952,
"decisionTotal": 21,
"failureBreakdown": {
"ambiguous_runtime": 40,
"framework_architecture_unsupported": 16,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 98,
"failureRate": 0.98,
"failureCount": 99,
"failureRate": 0.9802,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.02,
"total": 100,
"successRate": 0.0198,
"total": 101,
"unresolvedFailureCount": 80
},
"Iluvatar_bi-100": {
@@ -2805,28 +2807,28 @@
"unresolvedFailureCount": 29
},
"Iluvatar_bi-150": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.814,
"decisionSuccessRate": 0.186,
"decisionTotal": 43,
"attributableFailureCount": 36,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 14,
"backend_operator": 6,
"framework_architecture_unsupported": 17,
"model_load": 8,
"repository_structure": 1,
"runtime_memory": 3,
"runtime_memory": 4,
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 81,
"failureRate": 0.9101,
"failureCount": 82,
"failureRate": 0.9111,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.0899,
"total": 89,
"successRate": 0.0889,
"total": 90,
"unresolvedFailureCount": 46
},
"Iluvatar_mrv-100": {
@@ -2859,20 +2861,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 74,
"ambiguous_runtime": 75,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 99,
"failureCount": 100,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 99,
"unresolvedFailureCount": 98
"total": 100,
"unresolvedFailureCount": 99
},
"MetaX_c-500": {
"attributableFailureCount": 55,
@@ -3338,6 +3340,29 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -3566,6 +3591,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|gptq": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -3917,9 +3965,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3",
@@ -3931,8 +3979,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none": {
"attributableFailureCount": 0,
@@ -4865,23 +4913,23 @@
"unresolvedFailureCount": 11
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 9,
"ambiguous_runtime": 10,
"backend_operator": 2,
"framework_architecture_unsupported": 5,
"framework_architecture_unsupported": 6,
"model_load": 1
},
"failureCount": 17,
"failureCount": 19,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T04:51:03.045568+00:00",
"lastTerminalAt": "2026-09-14T08:29:32.453358+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4889,8 +4937,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 9
"total": 19,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 2,
@@ -5850,6 +5898,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none|24": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 24,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6206,6 +6278,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|gptq|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6758,6 +6854,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|24": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 24,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -8029,35 +8149,35 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1817,
"totalRecords": 1910,
"terminalRecords": 1822,
"totalRecords": 1915,
"totals": {
"attributableFailureCount": 544,
"decisionFailureRate": 0.9022,
"decisionSuccessRate": 0.0978,
"decisionTotal": 603,
"attributableFailureCount": 547,
"decisionFailureRate": 0.9026,
"decisionSuccessRate": 0.0974,
"decisionTotal": 606,
"failureBreakdown": {
"ambiguous_runtime": 426,
"ambiguous_runtime": 428,
"backend_operator": 43,
"framework_architecture_unsupported": 346,
"framework_architecture_unsupported": 347,
"memory_capacity": 12,
"model_load": 76,
"platform_infrastructure": 6,
"repository_structure": 8,
"runtime_memory": 7,
"tokenizer_compatibility": 52,
"runtime_memory": 8,
"tokenizer_compatibility": 53,
"参数/模板问题": 109,
"验证失败": 673
},
"failureCount": 1758,
"failureRate": 0.9675,
"failureCount": 1763,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 59,
"successRate": 0.0325,
"total": 1817,
"unresolvedFailureCount": 1208
"successRate": 0.0324,
"total": 1822,
"unresolvedFailureCount": 1210
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -8095,6 +8215,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1910,
"summarizedRecords": 1915,
"version": 1
}