state: generation 5995 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T02:56:54.666019+00:00",
|
||||
"lastSyncTime": "2026-09-12T02:56:54.384007+00:00",
|
||||
"generatedAt": "2026-09-12T03:05:48.188591+00:00",
|
||||
"lastSyncTime": "2026-09-12T03:05:47.937930+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1800,18 +1800,18 @@
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
"attributableFailureCount": 17,
|
||||
"attributableFailureCount": 18,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 17,
|
||||
"decisionTotal": 18,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 9,
|
||||
"model_load": 4,
|
||||
"model_load": 5,
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 24,
|
||||
"failureCount": 25,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -1821,7 +1821,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 24,
|
||||
"total": 25,
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
@@ -2125,18 +2125,18 @@
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
"attributableFailureCount": 4,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 2,
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2146,7 +2146,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Vastai_va16|unknown|text-generation": {
|
||||
@@ -2375,30 +2375,30 @@
|
||||
"unresolvedFailureCount": 862
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 248,
|
||||
"decisionFailureRate": 0.988,
|
||||
"decisionSuccessRate": 0.012,
|
||||
"decisionTotal": 251,
|
||||
"attributableFailureCount": 250,
|
||||
"decisionFailureRate": 0.9881,
|
||||
"decisionSuccessRate": 0.0119,
|
||||
"decisionTotal": 253,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 195,
|
||||
"backend_operator": 33,
|
||||
"framework_architecture_unsupported": 173,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 20,
|
||||
"model_load": 21,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 5,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 5,
|
||||
"tokenizer_compatibility": 6,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 468,
|
||||
"failureRate": 0.9936,
|
||||
"failureCount": 470,
|
||||
"failureRate": 0.9937,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0064,
|
||||
"total": 471,
|
||||
"successRate": 0.0063,
|
||||
"total": 473,
|
||||
"unresolvedFailureCount": 219
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2502,7 +2502,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T02:56:54.660525+00:00",
|
||||
"generatedAt": "2026-09-12T03:05:48.184736+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2641,27 +2641,27 @@
|
||||
"unresolvedFailureCount": 27
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"attributableFailureCount": 22,
|
||||
"decisionFailureRate": 0.7333,
|
||||
"decisionSuccessRate": 0.2667,
|
||||
"decisionTotal": 30,
|
||||
"attributableFailureCount": 23,
|
||||
"decisionFailureRate": 0.7419,
|
||||
"decisionSuccessRate": 0.2581,
|
||||
"decisionTotal": 31,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"backend_operator": 5,
|
||||
"framework_architecture_unsupported": 10,
|
||||
"model_load": 5,
|
||||
"model_load": 6,
|
||||
"runtime_memory": 2,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 66,
|
||||
"failureRate": 0.8919,
|
||||
"failureCount": 67,
|
||||
"failureRate": 0.8933,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 8,
|
||||
"successRate": 0.1081,
|
||||
"total": 74,
|
||||
"successRate": 0.1067,
|
||||
"total": 75,
|
||||
"unresolvedFailureCount": 44
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
@@ -2760,26 +2760,26 @@
|
||||
"unresolvedFailureCount": 77
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 45,
|
||||
"decisionFailureRate": 0.9783,
|
||||
"decisionSuccessRate": 0.0217,
|
||||
"decisionTotal": 46,
|
||||
"attributableFailureCount": 46,
|
||||
"decisionFailureRate": 0.9787,
|
||||
"decisionSuccessRate": 0.0213,
|
||||
"decisionTotal": 47,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"platform_infrastructure": 3,
|
||||
"tokenizer_compatibility": 40,
|
||||
"tokenizer_compatibility": 41,
|
||||
"参数/模板问题": 9,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 90,
|
||||
"failureRate": 0.989,
|
||||
"failureCount": 91,
|
||||
"failureRate": 0.9891,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 1,
|
||||
"successRate": 0.011,
|
||||
"total": 91,
|
||||
"successRate": 0.0109,
|
||||
"total": 92,
|
||||
"unresolvedFailureCount": 42
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -4387,23 +4387,23 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"model_load": 1
|
||||
"model_load": 2
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T02:30:20.417896+00:00",
|
||||
"lastTerminalAt": "2026-09-12T03:05:47.937930+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4411,7 +4411,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
@@ -4593,18 +4593,18 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 17,
|
||||
"consecutiveFailures": 17,
|
||||
"attributableFailureCount": 15,
|
||||
"consecutiveFailures": 15,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 17,
|
||||
"decisionTotal": 15,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 2,
|
||||
"platform_infrastructure": 2,
|
||||
"tokenizer_compatibility": 15
|
||||
"tokenizer_compatibility": 13
|
||||
},
|
||||
"failureCount": 19,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
|
||||
@@ -4616,26 +4616,26 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 19,
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
|
||||
"lastTerminalAt": "2026-09-11T11:19:08.306651+00:00",
|
||||
"lastTerminalAt": "2026-09-12T03:05:47.937901+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
@@ -4643,7 +4643,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -7187,40 +7187,41 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1680,
|
||||
"totalRecords": 1767,
|
||||
"terminalRecords": 1682,
|
||||
"totalRecords": 1769,
|
||||
"totals": {
|
||||
"attributableFailureCount": 452,
|
||||
"decisionFailureRate": 0.8898,
|
||||
"decisionSuccessRate": 0.1102,
|
||||
"decisionTotal": 508,
|
||||
"attributableFailureCount": 454,
|
||||
"decisionFailureRate": 0.8902,
|
||||
"decisionSuccessRate": 0.1098,
|
||||
"decisionTotal": 510,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 394,
|
||||
"backend_operator": 40,
|
||||
"framework_architecture_unsupported": 280,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 64,
|
||||
"model_load": 65,
|
||||
"platform_infrastructure": 4,
|
||||
"repository_structure": 5,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 46,
|
||||
"tokenizer_compatibility": 47,
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1624,
|
||||
"failureCount": 1626,
|
||||
"failureRate": 0.9667,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 56,
|
||||
"successRate": 0.0333,
|
||||
"total": 1680,
|
||||
"total": 1682,
|
||||
"unresolvedFailureCount": 1168
|
||||
},
|
||||
"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。",
|
||||
@@ -7229,7 +7230,6 @@
|
||||
"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。",
|
||||
@@ -7251,6 +7251,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1767,
|
||||
"summarizedRecords": 1769,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user