state: generation 16751 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-26T18:28:52.859100+00:00",
|
||||
"lastSyncTime": "2026-09-26T18:28:52.569178+00:00",
|
||||
"generatedAt": "2026-09-26T19:06:57.386426+00:00",
|
||||
"lastSyncTime": "2026-09-26T19:06:57.060378+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -5402,18 +5402,18 @@
|
||||
"unresolvedFailureCount": 296
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 112,
|
||||
"attributableFailureCount": 113,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 112,
|
||||
"decisionTotal": 113,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"platform_infrastructure": 20,
|
||||
"tokenizer_compatibility": 89,
|
||||
"tokenizer_compatibility": 90,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 138,
|
||||
"failureCount": 139,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -5423,7 +5423,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 138,
|
||||
"total": 139,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -6080,10 +6080,10 @@
|
||||
"unresolvedFailureCount": 25
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 149,
|
||||
"decisionFailureRate": 0.9675,
|
||||
"decisionSuccessRate": 0.0325,
|
||||
"decisionTotal": 154,
|
||||
"attributableFailureCount": 150,
|
||||
"decisionFailureRate": 0.9677,
|
||||
"decisionSuccessRate": 0.0323,
|
||||
"decisionTotal": 155,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 319,
|
||||
"backend_operator": 9,
|
||||
@@ -6091,17 +6091,17 @@
|
||||
"memory_capacity": 10,
|
||||
"model_load": 9,
|
||||
"platform_infrastructure": 20,
|
||||
"tokenizer_compatibility": 89,
|
||||
"tokenizer_compatibility": 90,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 501,
|
||||
"failureCount": 502,
|
||||
"failureRate": 0.9901,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 20,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0099,
|
||||
"total": 506,
|
||||
"total": 507,
|
||||
"unresolvedFailureCount": 332
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -6133,7 +6133,7 @@
|
||||
"unresolvedFailureCount": 196
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-26T18:28:52.846993+00:00",
|
||||
"generatedAt": "2026-09-26T19:06:57.373871+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6468,10 +6468,10 @@
|
||||
"unresolvedFailureCount": 299
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 746,
|
||||
"decisionFailureRate": 0.8892,
|
||||
"decisionSuccessRate": 0.1108,
|
||||
"decisionTotal": 839,
|
||||
"attributableFailureCount": 747,
|
||||
"decisionFailureRate": 0.8893,
|
||||
"decisionSuccessRate": 0.1107,
|
||||
"decisionTotal": 840,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 162,
|
||||
"architecture_compatibility": 44,
|
||||
@@ -6482,18 +6482,18 @@
|
||||
"platform_infrastructure": 226,
|
||||
"repository_structure": 83,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 271,
|
||||
"tokenizer_compatibility": 272,
|
||||
"参数/模板问题": 228,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1394,
|
||||
"failureCount": 1395,
|
||||
"failureRate": 0.9375,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 226,
|
||||
"successCount": 93,
|
||||
"successRate": 0.0625,
|
||||
"total": 1487,
|
||||
"total": 1488,
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -22796,10 +22796,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"ambiguous_runtime": 9,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -22811,8 +22811,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 10
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -23233,22 +23233,22 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 6,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 5,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 2,
|
||||
"tokenizer_compatibility": 4
|
||||
"tokenizer_compatibility": 5
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-23T02:14:08+00:00",
|
||||
"lastTerminalAt": "2026-09-26T17:57:36.159288+00:00",
|
||||
"lastTerminalAt": "2026-09-26T19:06:57.060378+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
@@ -23256,7 +23256,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -23890,31 +23890,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|phi3|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-26T14:37:53.556324+00:00",
|
||||
"modelType": "phi3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -50955,13 +50930,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17045,
|
||||
"totalRecords": 17266,
|
||||
"terminalRecords": 17046,
|
||||
"totalRecords": 17267,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6113,
|
||||
"decisionFailureRate": 0.8635,
|
||||
"decisionSuccessRate": 0.1365,
|
||||
"decisionTotal": 7079,
|
||||
"attributableFailureCount": 6114,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7080,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4407,
|
||||
"architecture_compatibility": 212,
|
||||
@@ -50974,35 +50949,35 @@
|
||||
"platform_infrastructure": 937,
|
||||
"repository_structure": 742,
|
||||
"runtime_memory": 100,
|
||||
"tokenizer_compatibility": 679,
|
||||
"tokenizer_compatibility": 680,
|
||||
"参数/模板问题": 3227,
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16079,
|
||||
"failureCount": 16080,
|
||||
"failureRate": 0.9433,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 937,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0567,
|
||||
"total": 17045,
|
||||
"total": 17046,
|
||||
"unresolvedFailureCount": 9029
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Biren_166m 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 Iluvatar_bi-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 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 Kunlunxin_p-800 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 Ascend_910-b3 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 hygon_k100-ai 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_bi-150 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 MetaX_c-500 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_bi-150|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -51015,6 +50990,7 @@
|
||||
"组合 Iluvatar_bi-100|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|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-x4|vllm-mlu|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|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 hygon_k100-ai|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 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -51040,11 +51016,10 @@
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 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|llamacpp|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 Cambricon_mlu-370-x8|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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17266,
|
||||
"summarizedRecords": 17267,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user