state: generation 9888 (cycle)

This commit is contained in:
2026-09-19 16:01:10 +00:00
parent 86d8e85f48
commit 4cc6c43969
9 changed files with 1836 additions and 1790 deletions

View File

@@ -1764,7 +1764,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-19T15:58:40.805914+00:00",
"generatedAt": "2026-09-19T16:01:09.683885+00:00",
"summary": {
"activeBlockCount": 85,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 721,
"listingErrors": 722,
"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": 10,
"nextAccountIndex": 11,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-19T15:58:40.783384+00:00",
"updatedAt": "2026-09-19T16:01:09.658213+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-19T15:57:27.993251+00:00",
"generatedAt": "2026-09-19T15:59:50.434085+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": "2026-09-19T15:51:19.427783+00:00",
"lastSyncTime": "2026-09-19T15:51:19.393846+00:00",
"generatedAt": "2026-09-19T15:59:41.750589+00:00",
"lastSyncTime": "2026-09-19T15:59:41.486250+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2047,25 +2047,25 @@
"unresolvedFailureCount": 79
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 5,
"decisionFailureRate": 0.4167,
"decisionSuccessRate": 0.5833,
"decisionTotal": 12,
"attributableFailureCount": 6,
"decisionFailureRate": 0.4615,
"decisionSuccessRate": 0.5385,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 5
"framework_architecture_unsupported": 6
},
"failureCount": 13,
"failureRate": 0.65,
"failureCount": 14,
"failureRate": 0.6667,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.35,
"successRate": 0.3333,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 20,
"total": 21,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -2889,24 +2889,24 @@
"unresolvedFailureCount": 287
},
"vllm-mlu": {
"attributableFailureCount": 17,
"decisionFailureRate": 0.4857,
"decisionSuccessRate": 0.5143,
"decisionTotal": 35,
"attributableFailureCount": 18,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 36,
"failureBreakdown": {
"ambiguous_runtime": 39,
"framework_architecture_unsupported": 16,
"framework_architecture_unsupported": 17,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 59,
"failureRate": 0.7662,
"failureCount": 60,
"failureRate": 0.7692,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2338,
"total": 77,
"successRate": 0.2308,
"total": 78,
"unresolvedFailureCount": 42
},
"vllm-patch-tokenizer": {
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 21
}
},
"generatedAt": "2026-09-19T15:51:19.422379+00:00",
"generatedAt": "2026-09-19T15:59:41.745316+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3075,26 +3075,26 @@
"unresolvedFailureCount": 60
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.7609,
"decisionSuccessRate": 0.2391,
"decisionTotal": 46,
"attributableFailureCount": 36,
"decisionFailureRate": 0.766,
"decisionSuccessRate": 0.234,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 47,
"framework_architecture_unsupported": 32,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 122,
"failureRate": 0.9173,
"failureCount": 123,
"failureRate": 0.9179,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.0827,
"total": 133,
"successRate": 0.0821,
"total": 134,
"unresolvedFailureCount": 87
},
"Cambricon_mlu-370-x8": {
@@ -4405,6 +4405,29 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -10238,6 +10261,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -15874,17 +15921,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2346,
"totalRecords": 2449,
"terminalRecords": 2347,
"totalRecords": 2450,
"totals": {
"attributableFailureCount": 767,
"decisionFailureRate": 0.8168,
"decisionSuccessRate": 0.1832,
"decisionTotal": 939,
"attributableFailureCount": 768,
"decisionFailureRate": 0.817,
"decisionSuccessRate": 0.183,
"decisionTotal": 940,
"failureBreakdown": {
"ambiguous_runtime": 590,
"backend_operator": 55,
"framework_architecture_unsupported": 515,
"framework_architecture_unsupported": 516,
"memory_capacity": 12,
"model_load": 89,
"platform_infrastructure": 11,
@@ -15894,18 +15941,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2174,
"failureCount": 2175,
"failureRate": 0.9267,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 172,
"successRate": 0.0733,
"total": 2346,
"total": 2347,
"unresolvedFailureCount": 1396
},
"warnings": [
"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 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。",
@@ -15916,7 +15963,7 @@
"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 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。",
"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。",
@@ -15941,6 +15988,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2449,
"summarizedRecords": 2450,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff