state: generation 4848 (cycle)

This commit is contained in:
2026-09-10 00:05:29 +00:00
parent 8f5ee0299a
commit 1daca9712a
10 changed files with 1971 additions and 1977 deletions

View File

@@ -1312,7 +1312,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T00:02:39.848956+00:00",
"generatedAt": "2026-09-10T00:05:29.186799+00:00",
"summary": {
"activeBlockCount": 65,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 344,
"listingErrors": 345,
"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": "2026-09-10T00:02:39.826633+00:00",
"updatedAt": "2026-09-10T00:05:29.162194+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T00:01:17.038580+00:00",
"generatedAt": "2026-09-10T00:03:48.111564+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": "2026-09-09T23:55:17.575624+00:00",
"lastSyncTime": "2026-09-09T23:55:17.200912+00:00",
"generatedAt": "2026-09-10T00:03:40.752831+00:00",
"lastSyncTime": "2026-09-10T00:03:40.507646+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1906,19 +1906,19 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 36,
"attributableFailureCount": 37,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 36,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 17,
"backend_operator": 18,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 9
},
"failureCount": 52,
"failureCount": 53,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1928,7 +1928,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 52,
"total": 53,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2315,13 +2315,13 @@
"unresolvedFailureCount": 819
},
"vllm": {
"attributableFailureCount": 225,
"attributableFailureCount": 226,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 225,
"decisionTotal": 226,
"failureBreakdown": {
"ambiguous_runtime": 120,
"backend_operator": 20,
"backend_operator": 21,
"framework_architecture_unsupported": 168,
"memory_capacity": 6,
"model_load": 18,
@@ -2331,14 +2331,14 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 367,
"failureCount": 368,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 367,
"total": 368,
"unresolvedFailureCount": 141
},
"vllm-mlu": {
@@ -2442,7 +2442,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-09T23:55:17.571160+00:00",
"generatedAt": "2026-09-10T00:03:40.748614+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2649,27 +2649,27 @@
"unresolvedFailureCount": 72
},
"MetaX_c-500": {
"attributableFailureCount": 36,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 45,
"attributableFailureCount": 37,
"decisionFailureRate": 0.8043,
"decisionSuccessRate": 0.1957,
"decisionTotal": 46,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 17,
"backend_operator": 18,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 108,
"failureRate": 0.9231,
"failureCount": 109,
"failureRate": 0.9237,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0769,
"total": 117,
"successRate": 0.0763,
"total": 118,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -3614,14 +3614,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 5,
"attributableFailureCount": 6,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"backend_operator": 5
"backend_operator": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "starcoder2",
@@ -3633,7 +3633,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
@@ -6366,14 +6366,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"backend_operator": 1
"backend_operator": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
@@ -6386,7 +6386,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8|30": {
@@ -6678,16 +6678,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1459,
"totalRecords": 1543,
"terminalRecords": 1460,
"totalRecords": 1544,
"totals": {
"attributableFailureCount": 388,
"decisionFailureRate": 0.8899,
"decisionSuccessRate": 0.1101,
"decisionTotal": 436,
"attributableFailureCount": 389,
"decisionFailureRate": 0.8902,
"decisionSuccessRate": 0.1098,
"decisionTotal": 437,
"failureBreakdown": {
"ambiguous_runtime": 254,
"backend_operator": 23,
"backend_operator": 24,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
"model_load": 45,
@@ -6698,21 +6698,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1411,
"failureCount": 1412,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0329,
"total": 1459,
"total": 1460,
"unresolvedFailureCount": 1021
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 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 Iluvatar_bi-150 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 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。",
@@ -6720,7 +6720,7 @@
"GPU hygon_k100-ai 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 Iluvatar_bi-150 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。",
"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。",
"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。",
"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。",
@@ -6741,6 +6741,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1543,
"summarizedRecords": 1544,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff