state: generation 8678 (cycle)
This commit is contained in:
@@ -1741,7 +1741,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-17T10:17:44.235931+00:00",
|
||||
"generatedAt": "2026-09-17T10:19:49.648809+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 84,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -75,7 +75,7 @@
|
||||
"7": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 634,
|
||||
"listingErrors": 635,
|
||||
"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": 7,
|
||||
"nextAccountIndex": 8,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-17T10:17:44.208686+00:00",
|
||||
"updatedAt": "2026-09-17T10:19:49.621680+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-17T10:15:29.300761+00:00",
|
||||
"generatedAt": "2026-09-17T10:17:47.830588+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-17T10:10:02.916569+00:00",
|
||||
"lastSyncTime": "2026-09-17T10:10:02.608119+00:00",
|
||||
"generatedAt": "2026-09-17T10:17:47.784818+00:00",
|
||||
"lastSyncTime": "2026-09-17T10:17:47.519781+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1810,25 +1810,25 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 8,
|
||||
"attributableFailureCount": 9,
|
||||
"decisionFailureRate": 0.9,
|
||||
"decisionSuccessRate": 0.1,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5,
|
||||
"framework_architecture_unsupported": 7
|
||||
"framework_architecture_unsupported": 9
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureRate": 0.9231,
|
||||
"failureCount": 14,
|
||||
"failureRate": 0.9333,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0769,
|
||||
"successRate": 0.0667,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
@@ -2953,48 +2953,48 @@
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 10,
|
||||
"decisionFailureRate": 0.9091,
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 11,
|
||||
"attributableFailureCount": 12,
|
||||
"decisionFailureRate": 0.9231,
|
||||
"decisionSuccessRate": 0.0769,
|
||||
"decisionTotal": 13,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8,
|
||||
"framework_architecture_unsupported": 10
|
||||
"framework_architecture_unsupported": 12
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.9474,
|
||||
"failureCount": 20,
|
||||
"failureRate": 0.9524,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0526,
|
||||
"total": 19,
|
||||
"successRate": 0.0476,
|
||||
"total": 21,
|
||||
"unresolvedFailureCount": 8
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-17T10:10:02.910840+00:00",
|
||||
"generatedAt": "2026-09-17T10:17:47.778110+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 54,
|
||||
"decisionFailureRate": 0.9474,
|
||||
"decisionSuccessRate": 0.0526,
|
||||
"decisionTotal": 57,
|
||||
"attributableFailureCount": 56,
|
||||
"decisionFailureRate": 0.9492,
|
||||
"decisionSuccessRate": 0.0508,
|
||||
"decisionTotal": 59,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 37,
|
||||
"framework_architecture_unsupported": 52,
|
||||
"framework_architecture_unsupported": 54,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 10,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 128,
|
||||
"failureRate": 0.9771,
|
||||
"failureCount": 130,
|
||||
"failureRate": 0.9774,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0229,
|
||||
"total": 131,
|
||||
"successRate": 0.0226,
|
||||
"total": 133,
|
||||
"unresolvedFailureCount": 74
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
@@ -3486,6 +3486,52 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "fp8",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -7767,6 +7813,54 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|12": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 12,
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "fp8",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -12525,17 +12619,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2116,
|
||||
"totalRecords": 2219,
|
||||
"terminalRecords": 2118,
|
||||
"totalRecords": 2221,
|
||||
"totals": {
|
||||
"attributableFailureCount": 690,
|
||||
"decisionFailureRate": 0.8835,
|
||||
"decisionSuccessRate": 0.1165,
|
||||
"decisionTotal": 781,
|
||||
"attributableFailureCount": 692,
|
||||
"decisionFailureRate": 0.8838,
|
||||
"decisionSuccessRate": 0.1162,
|
||||
"decisionTotal": 783,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 519,
|
||||
"backend_operator": 48,
|
||||
"framework_architecture_unsupported": 459,
|
||||
"framework_architecture_unsupported": 461,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 85,
|
||||
"platform_infrastructure": 10,
|
||||
@@ -12545,14 +12639,14 @@
|
||||
"参数/模板问题": 133,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 2025,
|
||||
"failureCount": 2027,
|
||||
"failureRate": 0.957,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 10,
|
||||
"successCount": 91,
|
||||
"successRate": 0.043,
|
||||
"total": 2116,
|
||||
"total": 2118,
|
||||
"unresolvedFailureCount": 1325
|
||||
},
|
||||
"warnings": [
|
||||
@@ -12560,14 +12654,14 @@
|
||||
"GPU Iluvatar_mrv-100 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 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 Iluvatar_bi-150 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 MetaX_c-500 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-b3 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 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。",
|
||||
"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。",
|
||||
"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 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。",
|
||||
@@ -12593,6 +12687,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2219,
|
||||
"summarizedRecords": 2221,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user