state: generation 5084 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T08:45:45.905614+00:00",
|
||||
"lastSyncTime": "2026-09-10T08:45:45.454674+00:00",
|
||||
"generatedAt": "2026-09-10T08:54:23.705220+00:00",
|
||||
"lastSyncTime": "2026-09-10T08:54:23.346315+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1478,13 +1478,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 37,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 27,
|
||||
"ambiguous_runtime": 28,
|
||||
"framework_architecture_unsupported": 33,
|
||||
"memory_capacity": 1,
|
||||
"repository_structure": 1,
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 64,
|
||||
"failureCount": 65,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -1494,8 +1494,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 64,
|
||||
"unresolvedFailureCount": 27
|
||||
"total": 65,
|
||||
"unresolvedFailureCount": 28
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 24,
|
||||
@@ -1911,29 +1911,29 @@
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 41,
|
||||
"decisionFailureRate": 0.9762,
|
||||
"decisionSuccessRate": 0.0238,
|
||||
"decisionTotal": 42,
|
||||
"attributableFailureCount": 42,
|
||||
"decisionFailureRate": 0.9767,
|
||||
"decisionSuccessRate": 0.0233,
|
||||
"decisionTotal": 43,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 22,
|
||||
"backend_operator": 23,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 4,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 57,
|
||||
"failureRate": 0.9828,
|
||||
"failureCount": 58,
|
||||
"failureRate": 0.9831,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0172,
|
||||
"successRate": 0.0169,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 58,
|
||||
"total": 59,
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
@@ -2320,13 +2320,13 @@
|
||||
"unresolvedFailureCount": 842
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 233,
|
||||
"attributableFailureCount": 234,
|
||||
"decisionFailureRate": 0.9957,
|
||||
"decisionSuccessRate": 0.0043,
|
||||
"decisionTotal": 234,
|
||||
"decisionTotal": 235,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 153,
|
||||
"backend_operator": 27,
|
||||
"ambiguous_runtime": 154,
|
||||
"backend_operator": 28,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 18,
|
||||
@@ -2336,15 +2336,15 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 21
|
||||
},
|
||||
"failureCount": 408,
|
||||
"failureCount": 410,
|
||||
"failureRate": 0.9976,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0024,
|
||||
"total": 409,
|
||||
"unresolvedFailureCount": 174
|
||||
"total": 411,
|
||||
"unresolvedFailureCount": 175
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2447,7 +2447,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T08:45:45.900554+00:00",
|
||||
"generatedAt": "2026-09-10T08:54:23.700725+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2478,7 +2478,7 @@
|
||||
"decisionSuccessRate": 0.05,
|
||||
"decisionTotal": 40,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 28,
|
||||
"ambiguous_runtime": 29,
|
||||
"framework_architecture_unsupported": 33,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 1,
|
||||
@@ -2487,15 +2487,15 @@
|
||||
"参数/模板问题": 11,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 252,
|
||||
"failureRate": 0.9921,
|
||||
"failureCount": 253,
|
||||
"failureRate": 0.9922,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0079,
|
||||
"total": 254,
|
||||
"unresolvedFailureCount": 214
|
||||
"successRate": 0.0078,
|
||||
"total": 255,
|
||||
"unresolvedFailureCount": 215
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 25,
|
||||
@@ -2654,27 +2654,27 @@
|
||||
"unresolvedFailureCount": 83
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 41,
|
||||
"decisionFailureRate": 0.8039,
|
||||
"decisionSuccessRate": 0.1961,
|
||||
"decisionTotal": 51,
|
||||
"attributableFailureCount": 42,
|
||||
"decisionFailureRate": 0.8077,
|
||||
"decisionSuccessRate": 0.1923,
|
||||
"decisionTotal": 52,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 22,
|
||||
"backend_operator": 23,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 4,
|
||||
"参数/模板问题": 17,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 113,
|
||||
"failureRate": 0.9187,
|
||||
"failureCount": 114,
|
||||
"failureRate": 0.9194,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0813,
|
||||
"total": 123,
|
||||
"successRate": 0.0806,
|
||||
"total": 124,
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -3525,15 +3525,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 12,
|
||||
"decisionFailureRate": 0.9231,
|
||||
"decisionSuccessRate": 0.0769,
|
||||
"decisionTotal": 13,
|
||||
"attributableFailureCount": 13,
|
||||
"decisionFailureRate": 0.9286,
|
||||
"decisionSuccessRate": 0.0714,
|
||||
"decisionTotal": 14,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 12
|
||||
"backend_operator": 13
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureRate": 0.9231,
|
||||
"failureCount": 13,
|
||||
"failureRate": 0.9286,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
@@ -3541,10 +3541,10 @@
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 1,
|
||||
"successRate": 0.0769,
|
||||
"successRate": 0.0714,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
|
||||
@@ -4015,21 +4015,21 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 6,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 7,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 13,
|
||||
"framework_architecture_unsupported": 7
|
||||
"ambiguous_runtime": 14,
|
||||
"framework_architecture_unsupported": 6
|
||||
},
|
||||
"failureCount": 20,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T05:49:48.500487+00:00",
|
||||
"lastTerminalAt": "2026-09-10T08:54:23.346315+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4038,23 +4038,23 @@
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 13
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 8,
|
||||
"decisionFailureRate": 0.8571,
|
||||
"decisionSuccessRate": 0.1429,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureRate": 0.9375,
|
||||
"failureCount": 14,
|
||||
"failureRate": 0.9333,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T06:11:26.144205+00:00",
|
||||
@@ -4062,10 +4062,10 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0625,
|
||||
"successRate": 0.0667,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -6386,14 +6386,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|32": {
|
||||
"attributableFailureCount": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2
|
||||
"backend_operator": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -6406,7 +6406,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
|
||||
@@ -6986,16 +6986,16 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1544,
|
||||
"totalRecords": 1631,
|
||||
"terminalRecords": 1546,
|
||||
"totalRecords": 1633,
|
||||
"totals": {
|
||||
"attributableFailureCount": 403,
|
||||
"decisionFailureRate": 0.8877,
|
||||
"decisionSuccessRate": 0.1123,
|
||||
"decisionTotal": 454,
|
||||
"attributableFailureCount": 404,
|
||||
"decisionFailureRate": 0.8879,
|
||||
"decisionSuccessRate": 0.1121,
|
||||
"decisionTotal": 455,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 320,
|
||||
"backend_operator": 32,
|
||||
"ambiguous_runtime": 321,
|
||||
"backend_operator": 33,
|
||||
"framework_architecture_unsupported": 271,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 46,
|
||||
@@ -7006,21 +7006,21 @@
|
||||
"参数/模板问题": 95,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1493,
|
||||
"failureCount": 1495,
|
||||
"failureRate": 0.967,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 51,
|
||||
"successRate": 0.033,
|
||||
"total": 1544,
|
||||
"unresolvedFailureCount": 1088
|
||||
"total": 1546,
|
||||
"unresolvedFailureCount": 1089
|
||||
},
|
||||
"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 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。",
|
||||
"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。",
|
||||
@@ -7028,7 +7028,7 @@
|
||||
"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 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。",
|
||||
"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。",
|
||||
@@ -7049,6 +7049,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1631,
|
||||
"summarizedRecords": 1633,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user