state: generation 7698 (cycle)

This commit is contained in:
2026-09-15 13:27:24 +00:00
parent fab0d12e0b
commit 6cbbec9038
9 changed files with 2100 additions and 2054 deletions

View File

@@ -1616,7 +1616,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-15T13:24:06.906072+00:00",
"generatedAt": "2026-09-15T13:27:23.803344+00:00",
"summary": {
"activeBlockCount": 79,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 560,
"listingErrors": 561,
"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": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-15T13:24:06.881749+00:00",
"updatedAt": "2026-09-15T13:27:23.777600+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T13:22:26.580682+00:00",
"generatedAt": "2026-09-15T13:25:18.366368+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": "2026-09-15T13:07:18.884376+00:00",
"lastSyncTime": "2026-09-15T13:07:18.613629+00:00",
"generatedAt": "2026-09-15T13:25:07.892350+00:00",
"lastSyncTime": "2026-09-15T13:25:07.648674+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2080,25 +2080,25 @@
"decisionSuccessRate": 0.1667,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"backend_operator": 4,
"framework_architecture_unsupported": 6,
"model_load": 2,
"runtime_memory": 3,
"参数/模板问题": 1
},
"failureCount": 23,
"failureRate": 0.8846,
"failureCount": 24,
"failureRate": 0.8889,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.1154,
"successRate": 0.1111,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 26,
"unresolvedFailureCount": 8
"total": 27,
"unresolvedFailureCount": 9
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 26,
@@ -2755,22 +2755,22 @@
"decisionSuccessRate": 0.1667,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"backend_operator": 4,
"framework_architecture_unsupported": 6,
"model_load": 2,
"runtime_memory": 3,
"参数/模板问题": 1
},
"failureCount": 23,
"failureRate": 0.8846,
"failureCount": 24,
"failureRate": 0.8889,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.1154,
"total": 26,
"unresolvedFailureCount": 8
"successRate": 0.1111,
"total": 27,
"unresolvedFailureCount": 9
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 53,
@@ -2816,7 +2816,7 @@
"unresolvedFailureCount": 2
}
},
"generatedAt": "2026-09-15T13:07:18.878835+00:00",
"generatedAt": "2026-09-15T13:25:07.882737+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 43,
@@ -2962,7 +2962,7 @@
"decisionSuccessRate": 0.1765,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"backend_operator": 7,
"framework_architecture_unsupported": 20,
"model_load": 9,
@@ -2971,15 +2971,15 @@
"参数/模板问题": 3,
"验证失败": 30
},
"failureCount": 90,
"failureRate": 0.9091,
"failureCount": 91,
"failureRate": 0.91,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0909,
"total": 99,
"unresolvedFailureCount": 48
"successRate": 0.09,
"total": 100,
"unresolvedFailureCount": 49
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 107,
@@ -4015,6 +4015,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5_moe",
"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_5|compressed-tensors": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -7431,6 +7454,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"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_5|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -9776,15 +9823,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1927,
"totalRecords": 2021,
"terminalRecords": 1928,
"totalRecords": 2022,
"totals": {
"attributableFailureCount": 601,
"decisionFailureRate": 0.897,
"decisionSuccessRate": 0.103,
"decisionTotal": 670,
"failureBreakdown": {
"ambiguous_runtime": 461,
"ambiguous_runtime": 462,
"backend_operator": 44,
"framework_architecture_unsupported": 393,
"memory_capacity": 12,
@@ -9796,15 +9843,15 @@
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1858,
"failureCount": 1859,
"failureRate": 0.9642,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 69,
"successRate": 0.0358,
"total": 1927,
"unresolvedFailureCount": 1250
"total": 1928,
"unresolvedFailureCount": 1251
},
"warnings": [
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
@@ -9843,6 +9890,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2021,
"summarizedRecords": 2022,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff