state: generation 6534 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T04:31:31.956372+00:00",
|
||||
"lastSyncTime": "2026-09-13T04:31:31.632761+00:00",
|
||||
"generatedAt": "2026-09-13T05:03:24.000102+00:00",
|
||||
"lastSyncTime": "2026-09-13T05:03:23.648984+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1740,11 +1740,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 19,
|
||||
"ambiguous_runtime": 20,
|
||||
"framework_architecture_unsupported": 7,
|
||||
"参数/模板问题": 3
|
||||
},
|
||||
"failureCount": 29,
|
||||
"failureCount": 30,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
@@ -1754,8 +1754,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 29,
|
||||
"unresolvedFailureCount": 22
|
||||
"total": 30,
|
||||
"unresolvedFailureCount": 23
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
@@ -2239,18 +2239,18 @@
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
"attributableFailureCount": 5,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 3,
|
||||
"tokenizer_compatibility": 4,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureCount": 9,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2260,7 +2260,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Vastai_va16|unknown|text-generation": {
|
||||
@@ -2489,10 +2489,10 @@
|
||||
"unresolvedFailureCount": 875
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 292,
|
||||
"decisionFailureRate": 0.9898,
|
||||
"decisionSuccessRate": 0.0102,
|
||||
"decisionTotal": 295,
|
||||
"attributableFailureCount": 293,
|
||||
"decisionFailureRate": 0.9899,
|
||||
"decisionSuccessRate": 0.0101,
|
||||
"decisionTotal": 296,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 201,
|
||||
"backend_operator": 34,
|
||||
@@ -2502,17 +2502,17 @@
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 8,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 6,
|
||||
"tokenizer_compatibility": 7,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 518,
|
||||
"failureRate": 0.9942,
|
||||
"failureCount": 519,
|
||||
"failureRate": 0.9943,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0058,
|
||||
"total": 521,
|
||||
"successRate": 0.0057,
|
||||
"total": 522,
|
||||
"unresolvedFailureCount": 225
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2521,19 +2521,19 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 19,
|
||||
"ambiguous_runtime": 20,
|
||||
"framework_architecture_unsupported": 7,
|
||||
"参数/模板问题": 3
|
||||
},
|
||||
"failureCount": 29,
|
||||
"failureCount": 30,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 29,
|
||||
"unresolvedFailureCount": 22
|
||||
"total": 30,
|
||||
"unresolvedFailureCount": 23
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 4,
|
||||
@@ -2617,7 +2617,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T04:31:31.950508+00:00",
|
||||
"generatedAt": "2026-09-13T05:03:23.994548+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2719,22 +2719,22 @@
|
||||
"decisionSuccessRate": 0.1,
|
||||
"decisionTotal": 20,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 39,
|
||||
"ambiguous_runtime": 40,
|
||||
"framework_architecture_unsupported": 16,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 18,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 97,
|
||||
"failureRate": 0.9798,
|
||||
"failureCount": 98,
|
||||
"failureRate": 0.98,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0202,
|
||||
"total": 99,
|
||||
"unresolvedFailureCount": 79
|
||||
"successRate": 0.02,
|
||||
"total": 100,
|
||||
"unresolvedFailureCount": 80
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2877,27 +2877,27 @@
|
||||
"unresolvedFailureCount": 77
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 50,
|
||||
"decisionFailureRate": 0.9804,
|
||||
"decisionSuccessRate": 0.0196,
|
||||
"decisionTotal": 51,
|
||||
"attributableFailureCount": 51,
|
||||
"decisionFailureRate": 0.9808,
|
||||
"decisionSuccessRate": 0.0192,
|
||||
"decisionTotal": 52,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"platform_infrastructure": 3,
|
||||
"tokenizer_compatibility": 43,
|
||||
"tokenizer_compatibility": 44,
|
||||
"参数/模板问题": 10,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 96,
|
||||
"failureRate": 0.9897,
|
||||
"failureCount": 97,
|
||||
"failureRate": 0.9898,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0103,
|
||||
"total": 97,
|
||||
"successRate": 0.0102,
|
||||
"total": 98,
|
||||
"unresolvedFailureCount": 43
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -3287,6 +3287,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -4906,22 +4929,22 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 2
|
||||
"tokenizer_compatibility": 3
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
|
||||
"lastTerminalAt": "2026-09-12T03:05:47.937901+00:00",
|
||||
"lastTerminalAt": "2026-09-13T05:03:23.648954+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
@@ -4929,7 +4952,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -5572,6 +5595,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none|31": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 31,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|31": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -7415,15 +7462,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1763,
|
||||
"totalRecords": 1850,
|
||||
"terminalRecords": 1765,
|
||||
"totalRecords": 1852,
|
||||
"totals": {
|
||||
"attributableFailureCount": 510,
|
||||
"decisionFailureRate": 0.8963,
|
||||
"decisionSuccessRate": 0.1037,
|
||||
"decisionTotal": 569,
|
||||
"attributableFailureCount": 511,
|
||||
"decisionFailureRate": 0.8965,
|
||||
"decisionSuccessRate": 0.1035,
|
||||
"decisionTotal": 570,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 414,
|
||||
"ambiguous_runtime": 415,
|
||||
"backend_operator": 43,
|
||||
"framework_architecture_unsupported": 320,
|
||||
"memory_capacity": 11,
|
||||
@@ -7431,25 +7478,24 @@
|
||||
"platform_infrastructure": 4,
|
||||
"repository_structure": 8,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 49,
|
||||
"tokenizer_compatibility": 50,
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1704,
|
||||
"failureRate": 0.9665,
|
||||
"failureCount": 1706,
|
||||
"failureRate": 0.9666,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 59,
|
||||
"successRate": 0.0335,
|
||||
"total": 1763,
|
||||
"unresolvedFailureCount": 1190
|
||||
"successRate": 0.0334,
|
||||
"total": 1765,
|
||||
"unresolvedFailureCount": 1191
|
||||
},
|
||||
"warnings": [
|
||||
"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 Mthreads_s4000 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 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 Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -7458,6 +7504,7 @@
|
||||
"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。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"组合 hygon_k100-ai|vllm-patch-tokenizer|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|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7480,6 +7527,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1850,
|
||||
"summarizedRecords": 1852,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user