state: generation 9727 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T09:14:35.206545+00:00",
|
||||
"generatedAt": "2026-09-19T09:18:07.850366+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -75,7 +75,7 @@
|
||||
"7": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 709,
|
||||
"listingErrors": 710,
|
||||
"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": "2026-09-19T09:14:35.182253+00:00",
|
||||
"updatedAt": "2026-09-19T09:18:07.826662+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-19T08:58:08.882691+00:00",
|
||||
"communityAttemptedAt": "2026-09-19T09:15:44.471079+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-19T08:58:08.882691+00:00",
|
||||
"communityUpdatedAt": "2026-09-19T09:15:44.471079+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-19T04:55:42.165883+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T09:12:33.654763+00:00",
|
||||
"generatedAt": "2026-09-19T09:15:44.471079+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-19T09:05:14.627283+00:00",
|
||||
"lastSyncTime": "2026-09-19T09:05:14.592122+00:00",
|
||||
"generatedAt": "2026-09-19T09:15:36.148816+00:00",
|
||||
"lastSyncTime": "2026-09-19T09:15:35.886669+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1922,15 +1922,15 @@
|
||||
"unresolvedFailureCount": 188
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 8,
|
||||
"attributableFailureCount": 9,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 8,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 8
|
||||
"framework_architecture_unsupported": 9
|
||||
},
|
||||
"failureCount": 20,
|
||||
"failureCount": 21,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -1940,7 +1940,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"total": 21,
|
||||
"unresolvedFailureCount": 12
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
@@ -1999,25 +1999,25 @@
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 29,
|
||||
"decisionFailureRate": 0.7436,
|
||||
"decisionSuccessRate": 0.2564,
|
||||
"decisionTotal": 39,
|
||||
"decisionFailureRate": 0.725,
|
||||
"decisionSuccessRate": 0.275,
|
||||
"decisionTotal": 40,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 22,
|
||||
"model_load": 6,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 29,
|
||||
"failureRate": 0.7436,
|
||||
"failureRate": 0.725,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.2564,
|
||||
"successCount": 11,
|
||||
"successRate": 0.275,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 39,
|
||||
"total": 40,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -2863,9 +2863,9 @@
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 423,
|
||||
"decisionFailureRate": 0.8849,
|
||||
"decisionSuccessRate": 0.1151,
|
||||
"decisionTotal": 478,
|
||||
"decisionFailureRate": 0.8831,
|
||||
"decisionSuccessRate": 0.1169,
|
||||
"decisionTotal": 479,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 246,
|
||||
"backend_operator": 40,
|
||||
@@ -2879,13 +2879,13 @@
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 711,
|
||||
"failureRate": 0.9282,
|
||||
"failureRate": 0.927,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 55,
|
||||
"successRate": 0.0718,
|
||||
"total": 766,
|
||||
"successCount": 56,
|
||||
"successRate": 0.073,
|
||||
"total": 767,
|
||||
"unresolvedFailureCount": 286
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2979,26 +2979,26 @@
|
||||
"unresolvedFailureCount": 88
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 20,
|
||||
"decisionFailureRate": 0.9524,
|
||||
"decisionSuccessRate": 0.0476,
|
||||
"decisionTotal": 21,
|
||||
"attributableFailureCount": 21,
|
||||
"decisionFailureRate": 0.9545,
|
||||
"decisionSuccessRate": 0.0455,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 18,
|
||||
"framework_architecture_unsupported": 20
|
||||
"framework_architecture_unsupported": 21
|
||||
},
|
||||
"failureCount": 38,
|
||||
"failureRate": 0.9744,
|
||||
"failureCount": 39,
|
||||
"failureRate": 0.975,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0256,
|
||||
"total": 39,
|
||||
"successRate": 0.025,
|
||||
"total": 40,
|
||||
"unresolvedFailureCount": 18
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T09:05:14.621911+00:00",
|
||||
"generatedAt": "2026-09-19T09:15:36.143651+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 62,
|
||||
@@ -3024,13 +3024,13 @@
|
||||
"unresolvedFailureCount": 76
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 67,
|
||||
"decisionFailureRate": 0.971,
|
||||
"decisionSuccessRate": 0.029,
|
||||
"decisionTotal": 69,
|
||||
"attributableFailureCount": 68,
|
||||
"decisionFailureRate": 0.9714,
|
||||
"decisionSuccessRate": 0.0286,
|
||||
"decisionTotal": 70,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 55,
|
||||
"framework_architecture_unsupported": 62,
|
||||
"framework_architecture_unsupported": 63,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 1,
|
||||
"repository_structure": 1,
|
||||
@@ -3038,21 +3038,21 @@
|
||||
"参数/模板问题": 13,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 310,
|
||||
"failureCount": 311,
|
||||
"failureRate": 0.9936,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0064,
|
||||
"total": 312,
|
||||
"total": 313,
|
||||
"unresolvedFailureCount": 243
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 69,
|
||||
"decisionFailureRate": 0.8519,
|
||||
"decisionSuccessRate": 0.1481,
|
||||
"decisionTotal": 81,
|
||||
"decisionFailureRate": 0.8415,
|
||||
"decisionSuccessRate": 0.1585,
|
||||
"decisionTotal": 82,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 32,
|
||||
"backend_operator": 4,
|
||||
@@ -3065,13 +3065,13 @@
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 129,
|
||||
"failureRate": 0.9149,
|
||||
"failureRate": 0.9085,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 12,
|
||||
"successRate": 0.0851,
|
||||
"total": 141,
|
||||
"successCount": 13,
|
||||
"successRate": 0.0915,
|
||||
"total": 142,
|
||||
"unresolvedFailureCount": 60
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -3745,14 +3745,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "qwen3_5_text",
|
||||
@@ -3764,7 +3764,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|exl3": {
|
||||
@@ -3930,25 +3930,25 @@
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|llama|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 0.5,
|
||||
"decisionSuccessRate": 0.5,
|
||||
"decisionTotal": 2,
|
||||
"decisionFailureRate": 0.3333,
|
||||
"decisionSuccessRate": 0.6667,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 0.5,
|
||||
"failureRate": 0.3333,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 1,
|
||||
"successRate": 0.5,
|
||||
"successCount": 2,
|
||||
"successRate": 0.6667,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|muse_glimmer|none": {
|
||||
@@ -9197,6 +9197,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|34": {
|
||||
"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": 34,
|
||||
"modelType": "qwen3_5_text",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|exl3|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -9441,7 +9465,7 @@
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
@@ -9452,11 +9476,11 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 1,
|
||||
"successCount": 2,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|muse_glimmer|none|34": {
|
||||
@@ -15452,17 +15476,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2314,
|
||||
"totalRecords": 2417,
|
||||
"terminalRecords": 2316,
|
||||
"totalRecords": 2419,
|
||||
"totals": {
|
||||
"attributableFailureCount": 758,
|
||||
"decisionFailureRate": 0.8275,
|
||||
"decisionSuccessRate": 0.1725,
|
||||
"decisionTotal": 916,
|
||||
"attributableFailureCount": 759,
|
||||
"decisionFailureRate": 0.8268,
|
||||
"decisionSuccessRate": 0.1732,
|
||||
"decisionTotal": 918,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 581,
|
||||
"backend_operator": 55,
|
||||
"framework_architecture_unsupported": 508,
|
||||
"framework_architecture_unsupported": 509,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 89,
|
||||
"platform_infrastructure": 11,
|
||||
@@ -15472,18 +15496,18 @@
|
||||
"参数/模板问题": 133,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 2156,
|
||||
"failureRate": 0.9317,
|
||||
"failureCount": 2157,
|
||||
"failureRate": 0.9313,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 11,
|
||||
"successCount": 158,
|
||||
"successRate": 0.0683,
|
||||
"total": 2314,
|
||||
"successCount": 159,
|
||||
"successRate": 0.0687,
|
||||
"total": 2316,
|
||||
"unresolvedFailureCount": 1387
|
||||
},
|
||||
"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。",
|
||||
@@ -15494,7 +15518,7 @@
|
||||
"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。",
|
||||
@@ -15519,6 +15543,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2417,
|
||||
"summarizedRecords": 2419,
|
||||
"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