state: generation 9891 (cycle)

This commit is contained in:
2026-09-19 16:09:04 +00:00
parent f7983373cb
commit 135e922133
10 changed files with 1869 additions and 1827 deletions

View File

@@ -1764,7 +1764,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-19T16:06:40.092605+00:00",
"generatedAt": "2026-09-19T16:09:02.767766+00:00",
"summary": {
"activeBlockCount": 85,
"byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 722,
"listingErrors": 723,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 1,
"nextAccountIndex": 2,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-19T16:06:40.066573+00:00",
"updatedAt": "2026-09-19T16:09:02.743322+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-19T16:04:44.749968+00:00",
"generatedAt": "2026-09-19T16:07:50.600543+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T15:59:41.750589+00:00",
"lastSyncTime": "2026-09-19T15:59:41.486250+00:00",
"generatedAt": "2026-09-19T16:07:43.480241+00:00",
"lastSyncTime": "2026-09-19T16:07:43.199639+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2328,26 +2328,26 @@
"unresolvedFailureCount": 74
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 12,
"decisionFailureRate": 0.6316,
"decisionSuccessRate": 0.3684,
"decisionTotal": 19,
"attributableFailureCount": 13,
"decisionFailureRate": 0.65,
"decisionSuccessRate": 0.35,
"decisionTotal": 20,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 11,
"framework_architecture_unsupported": 12,
"model_load": 1
},
"failureCount": 16,
"failureRate": 0.6957,
"failureCount": 17,
"failureRate": 0.7083,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.3043,
"successRate": 0.2917,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 23,
"total": 24,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2400,10 +2400,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 75,
"ambiguous_runtime": 76,
"参数/模板问题": 2
},
"failureCount": 77,
"failureCount": 78,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2413,8 +2413,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 77,
"unresolvedFailureCount": 77
"total": 78,
"unresolvedFailureCount": 78
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2862,14 +2862,14 @@
"unresolvedFailureCount": 910
},
"vllm": {
"attributableFailureCount": 425,
"decisionFailureRate": 0.8656,
"decisionSuccessRate": 0.1344,
"decisionTotal": 491,
"attributableFailureCount": 426,
"decisionFailureRate": 0.8659,
"decisionSuccessRate": 0.1341,
"decisionTotal": 492,
"failureBreakdown": {
"ambiguous_runtime": 247,
"backend_operator": 40,
"framework_architecture_unsupported": 319,
"framework_architecture_unsupported": 320,
"memory_capacity": 7,
"model_load": 33,
"platform_infrastructure": 2,
@@ -2878,14 +2878,14 @@
"tokenizer_compatibility": 12,
"参数/模板问题": 40
},
"failureCount": 714,
"failureRate": 0.9154,
"failureCount": 715,
"failureRate": 0.9155,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 66,
"successRate": 0.0846,
"total": 780,
"successRate": 0.0845,
"total": 781,
"unresolvedFailureCount": 287
},
"vllm-mlu": {
@@ -2960,7 +2960,7 @@
"decisionSuccessRate": 0.0145,
"decisionTotal": 69,
"failureBreakdown": {
"ambiguous_runtime": 83,
"ambiguous_runtime": 84,
"backend_operator": 7,
"framework_architecture_unsupported": 12,
"model_load": 1,
@@ -2968,15 +2968,15 @@
"tokenizer_compatibility": 48,
"参数/模板问题": 8
},
"failureCount": 167,
"failureRate": 0.994,
"failureCount": 168,
"failureRate": 0.9941,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 8,
"successCount": 1,
"successRate": 0.006,
"total": 168,
"unresolvedFailureCount": 91
"successRate": 0.0059,
"total": 169,
"unresolvedFailureCount": 92
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 21,
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 21
}
},
"generatedAt": "2026-09-19T15:59:41.745316+00:00",
"generatedAt": "2026-09-19T16:07:43.474838+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3165,13 +3165,13 @@
"unresolvedFailureCount": 54
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 121,
"decisionFailureRate": 0.8121,
"decisionSuccessRate": 0.1879,
"decisionTotal": 149,
"attributableFailureCount": 122,
"decisionFailureRate": 0.8133,
"decisionSuccessRate": 0.1867,
"decisionTotal": 150,
"failureBreakdown": {
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 75,
"framework_architecture_unsupported": 76,
"memory_capacity": 1,
"model_load": 44,
"platform_infrastructure": 1,
@@ -3179,14 +3179,14 @@
"参数/模板问题": 3,
"验证失败": 47
},
"failureCount": 200,
"failureRate": 0.8772,
"failureCount": 201,
"failureRate": 0.8777,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 28,
"successRate": 0.1228,
"total": 228,
"successRate": 0.1223,
"total": 229,
"unresolvedFailureCount": 78
},
"Kunlunxin_p-800": {
@@ -3195,20 +3195,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 124,
"ambiguous_runtime": 125,
"memory_capacity": 1,
"参数/模板问题": 2,
"验证失败": 23
},
"failureCount": 150,
"failureCount": 151,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 150,
"unresolvedFailureCount": 149
"total": 151,
"unresolvedFailureCount": 150
},
"MetaX_c-500": {
"attributableFailureCount": 64,
@@ -5717,6 +5717,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6022,9 +6045,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -6036,8 +6059,8 @@
"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|muse_glimmer|none": {
"attributableFailureCount": 0,
@@ -12264,6 +12287,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -12798,9 +12845,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
@@ -12813,8 +12860,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 0,
@@ -15921,17 +15968,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2347,
"totalRecords": 2450,
"terminalRecords": 2349,
"totalRecords": 2452,
"totals": {
"attributableFailureCount": 768,
"decisionFailureRate": 0.817,
"decisionSuccessRate": 0.183,
"decisionTotal": 940,
"attributableFailureCount": 769,
"decisionFailureRate": 0.8172,
"decisionSuccessRate": 0.1828,
"decisionTotal": 941,
"failureBreakdown": {
"ambiguous_runtime": 590,
"ambiguous_runtime": 591,
"backend_operator": 55,
"framework_architecture_unsupported": 516,
"framework_architecture_unsupported": 517,
"memory_capacity": 12,
"model_load": 89,
"platform_infrastructure": 11,
@@ -15941,18 +15988,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2175,
"failureRate": 0.9267,
"failureCount": 2177,
"failureRate": 0.9268,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 172,
"successRate": 0.0733,
"total": 2347,
"unresolvedFailureCount": 1396
"successRate": 0.0732,
"total": 2349,
"unresolvedFailureCount": 1397
},
"warnings": [
"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 Ascend_910-b3 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -15963,7 +16010,7 @@
"GPU Sunrise_pt-200-x1 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 MetaX_c-500 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。",
"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_tokenizer_patch|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|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -15988,6 +16035,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2450,
"summarizedRecords": 2452,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff