state: generation 7318 (cycle)

This commit is contained in:
2026-09-14 18:52:25 +00:00
parent c8fc324ef1
commit 39bbc3ba1f
11 changed files with 2259 additions and 2180 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-14T18:40:17.924377+00:00",
"lastSyncTime": "2026-09-14T18:40:17.699722+00:00",
"generatedAt": "2026-09-14T18:50:27.894446+00:00",
"lastSyncTime": "2026-09-14T18:50:27.851919+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1576,21 +1576,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {
"参数/模板问题": 8,
"参数/模板问题": 9,
"验证失败": 26
},
"failureCount": 34,
"failureRate": 0.9444,
"failureCount": 35,
"failureRate": 0.9459,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0556,
"successRate": 0.0541,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 36,
"unresolvedFailureCount": 34
"total": 37,
"unresolvedFailureCount": 35
},
"Ascend_910-b3|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
@@ -1738,20 +1738,21 @@
"memory_capacity": 1,
"model_load": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 90,
"failureRate": 0.9783,
"failureCount": 91,
"failureRate": 0.9785,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0217,
"successRate": 0.0215,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 92,
"unresolvedFailureCount": 58
"total": 93,
"unresolvedFailureCount": 59
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 5,
@@ -1785,20 +1786,21 @@
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 97,
"failureRate": 0.9798,
"failureCount": 98,
"failureRate": 0.98,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0202,
"successRate": 0.02,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 99,
"unresolvedFailureCount": 75
"total": 100,
"unresolvedFailureCount": 76
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -1989,20 +1991,21 @@
"backend_operator": 4,
"framework_architecture_unsupported": 4,
"model_load": 2,
"runtime_memory": 2
"runtime_memory": 2,
"参数/模板问题": 1
},
"failureCount": 18,
"failureRate": 0.8571,
"failureCount": 19,
"failureRate": 0.8636,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.1429,
"successRate": 0.1364,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 21,
"unresolvedFailureCount": 6
"total": 22,
"unresolvedFailureCount": 7
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 26,
@@ -2041,21 +2044,21 @@
"memory_capacity": 1,
"model_load": 43,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"参数/模板问题": 3,
"验证失败": 47
},
"failureCount": 171,
"failureRate": 0.9194,
"failureCount": 172,
"failureRate": 0.9198,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.0806,
"successRate": 0.0802,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 186,
"unresolvedFailureCount": 72
"total": 187,
"unresolvedFailureCount": 73
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -2130,9 +2133,9 @@
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 39,
"参数/模板问题": 1
"参数/模板问题": 2
},
"failureCount": 40,
"failureCount": 41,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2142,8 +2145,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 40,
"unresolvedFailureCount": 40
"total": 41,
"unresolvedFailureCount": 41
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2365,21 +2368,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 13,
"failureBreakdown": {
"参数/模板问题": 13,
"参数/模板问题": 14,
"验证失败": 130
},
"failureCount": 143,
"failureRate": 0.9167,
"failureCount": 144,
"failureRate": 0.9172,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0833,
"successRate": 0.0828,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 156,
"unresolvedFailureCount": 143
"total": 157,
"unresolvedFailureCount": 144
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 3,
@@ -2571,18 +2574,18 @@
"model_load": 45,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 61,
"参数/模板问题": 66,
"验证失败": 673
},
"failureCount": 1047,
"failureRate": 0.9492,
"failureCount": 1052,
"failureRate": 0.9495,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 56,
"successRate": 0.0508,
"total": 1103,
"unresolvedFailureCount": 885
"successRate": 0.0505,
"total": 1108,
"unresolvedFailureCount": 890
},
"vllm": {
"attributableFailureCount": 320,
@@ -2661,17 +2664,18 @@
"backend_operator": 4,
"framework_architecture_unsupported": 4,
"model_load": 2,
"runtime_memory": 2
"runtime_memory": 2,
"参数/模板问题": 1
},
"failureCount": 18,
"failureRate": 0.8571,
"failureCount": 19,
"failureRate": 0.8636,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.1429,
"total": 21,
"unresolvedFailureCount": 6
"successRate": 0.1364,
"total": 22,
"unresolvedFailureCount": 7
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 53,
@@ -2685,17 +2689,17 @@
"model_load": 1,
"platform_infrastructure": 4,
"tokenizer_compatibility": 42,
"参数/模板问题": 7
"参数/模板问题": 8
},
"failureCount": 105,
"failureCount": 106,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 0,
"successRate": 0.0,
"total": 105,
"unresolvedFailureCount": 48
"total": 106,
"unresolvedFailureCount": 49
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2716,7 +2720,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-14T18:40:17.918373+00:00",
"generatedAt": "2026-09-14T18:50:27.889967+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 36,
@@ -2728,18 +2732,18 @@
"framework_architecture_unsupported": 34,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 101,
"failureRate": 0.9806,
"failureCount": 102,
"failureRate": 0.9808,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0194,
"total": 103,
"unresolvedFailureCount": 65
"successRate": 0.0192,
"total": 104,
"unresolvedFailureCount": 66
},
"Ascend_910-b4": {
"attributableFailureCount": 50,
@@ -2778,17 +2782,18 @@
"memory_capacity": 1,
"model_load": 3,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 95,
"failureRate": 0.9794,
"failureCount": 96,
"failureRate": 0.9796,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0206,
"total": 97,
"unresolvedFailureCount": 58
"successRate": 0.0204,
"total": 98,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 22,
@@ -2800,17 +2805,18 @@
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 97,
"failureRate": 0.9798,
"failureCount": 98,
"failureRate": 0.98,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0202,
"total": 99,
"unresolvedFailureCount": 75
"successRate": 0.02,
"total": 100,
"unresolvedFailureCount": 76
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 19,
@@ -2866,18 +2872,18 @@
"model_load": 9,
"repository_structure": 1,
"runtime_memory": 4,
"参数/模板问题": 2,
"参数/模板问题": 3,
"验证失败": 30
},
"failureCount": 85,
"failureRate": 0.9043,
"failureCount": 86,
"failureRate": 0.9053,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0957,
"total": 94,
"unresolvedFailureCount": 46
"successRate": 0.0947,
"total": 95,
"unresolvedFailureCount": 47
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 101,
@@ -2890,18 +2896,18 @@
"memory_capacity": 1,
"model_load": 44,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"参数/模板问题": 3,
"验证失败": 47
},
"failureCount": 174,
"failureRate": 0.9206,
"failureCount": 175,
"failureRate": 0.9211,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.0794,
"total": 189,
"unresolvedFailureCount": 72
"successRate": 0.0789,
"total": 190,
"unresolvedFailureCount": 73
},
"Kunlunxin_p-800": {
"attributableFailureCount": 1,
@@ -2911,18 +2917,18 @@
"failureBreakdown": {
"ambiguous_runtime": 80,
"memory_capacity": 1,
"参数/模板问题": 1,
"参数/模板问题": 2,
"验证失败": 23
},
"failureCount": 105,
"failureCount": 106,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 105,
"unresolvedFailureCount": 104
"total": 106,
"unresolvedFailureCount": 105
},
"MetaX_c-500": {
"attributableFailureCount": 56,
@@ -3010,18 +3016,18 @@
"framework_architecture_unsupported": 45,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"参数/模板问题": 14,
"验证失败": 130
},
"failureCount": 259,
"failureRate": 0.9522,
"failureCount": 260,
"failureRate": 0.9524,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0478,
"total": 272,
"unresolvedFailureCount": 207
"successRate": 0.0476,
"total": 273,
"unresolvedFailureCount": 208
},
"hygon_k100-ai": {
"attributableFailureCount": 54,
@@ -3822,6 +3828,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 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": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -4196,9 +4225,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 4,
"参数/模板问题": 1
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -4210,8 +4240,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none": {
"attributableFailureCount": 0,
@@ -5186,21 +5216,23 @@
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 0.5,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T17:43:43.208549+00:00",
"lastTerminalAt": "2026-09-14T18:50:27.851864+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 1.0,
"successRate": 0.5,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 10,
@@ -5287,15 +5319,16 @@
"decisionSuccessRate": 0.1111,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 10,
"backend_operator": 2,
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 6,
"参数/模板问题": 1
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T09:58:45.951758+00:00",
"lastTerminalAt": "2026-09-14T18:50:27.851828+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5314,14 +5347,15 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 2
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 2,
"参数/模板问题": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T07:31:50.924213+00:00",
"lastTerminalAt": "2026-09-14T18:50:27.851919+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5437,22 +5471,23 @@
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 12,
"attributableFailureCount": 11,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 16,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 15,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 5,
"model_load": 7
"model_load": 6,
"参数/模板问题": 1
},
"failureCount": 16,
"failureRate": 0.8,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T13:56:20.710643+00:00",
"lastTerminalAt": "2026-09-14T18:50:27.851909+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5461,7 +5496,7 @@
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 4
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -5649,6 +5684,31 @@
"total": 11,
"unresolvedFailureCount": 5
},
"Vastai_va16|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T18:50:27.851900+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
@@ -6782,6 +6842,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 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": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none|24": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7364,9 +7448,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 2,
"参数/模板问题": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -7379,8 +7464,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|24": {
"attributableFailureCount": 0,
@@ -8771,8 +8856,8 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1856,
"totalRecords": 1949,
"terminalRecords": 1863,
"totalRecords": 1956,
"totals": {
"attributableFailureCount": 562,
"decisionFailureRate": 0.8992,
@@ -8788,18 +8873,18 @@
"repository_structure": 8,
"runtime_memory": 8,
"tokenizer_compatibility": 53,
"参数/模板问题": 109,
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1793,
"failureRate": 0.9661,
"failureCount": 1800,
"failureRate": 0.9662,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 63,
"successRate": 0.0339,
"total": 1856,
"unresolvedFailureCount": 1225
"successRate": 0.0338,
"total": 1863,
"unresolvedFailureCount": 1232
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -8810,10 +8895,10 @@
"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 Sunrise_pt-200-x1 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 Ascend_910-b4 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。",
@@ -8837,6 +8922,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1949,
"summarizedRecords": 1956,
"version": 1
}