state: generation 20708 (cycle_no_slots)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-11-03T07:52:18.849554+00:00",
|
||||
"lastSyncTime": "2026-11-03T07:52:18.578279+00:00",
|
||||
"generatedAt": "2026-11-03T08:08:12.101249+00:00",
|
||||
"lastSyncTime": "2026-11-03T08:08:11.857200+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"agentSummaries": {
|
||||
@@ -24,16 +24,16 @@
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 147,
|
||||
"decisionFailureRate": 0.9484,
|
||||
"decisionSuccessRate": 0.0516,
|
||||
"decisionTotal": 155,
|
||||
"attributableFailureCount": 148,
|
||||
"decisionFailureRate": 0.9487,
|
||||
"decisionSuccessRate": 0.0513,
|
||||
"decisionTotal": 156,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 59,
|
||||
"backend_operator": 5,
|
||||
"configuration_launch": 33,
|
||||
"context_length": 5,
|
||||
"framework_architecture_unsupported": 65,
|
||||
"framework_architecture_unsupported": 66,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 17,
|
||||
"platform_storage": 1,
|
||||
@@ -43,14 +43,14 @@
|
||||
"任务失败_原因未确认": 146,
|
||||
"参数/模板问题": 114
|
||||
},
|
||||
"failureCount": 467,
|
||||
"failureCount": 468,
|
||||
"failureRate": 0.9832,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 8,
|
||||
"successRate": 0.0168,
|
||||
"total": 475,
|
||||
"total": 476,
|
||||
"unresolvedFailureCount": 319
|
||||
}
|
||||
},
|
||||
@@ -671,6 +671,27 @@
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|architectures:bananaallforcausallm": {
|
||||
"architectureSignature": "architectures:bananaallforcausallm",
|
||||
"architectures": [
|
||||
"bananaallforcausallm"
|
||||
],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-12-03T08:08:11.857200+00:00",
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"latestFailureAt": "2026-11-03T08:08:11.857200+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "architectures",
|
||||
"modelType": null,
|
||||
"sourceModelIds": [
|
||||
"BananaMind/TernaryBananaMind-10M"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5520161"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|architectures:cagliostroforcausallm": {
|
||||
"architectureSignature": "architectures:cagliostroforcausallm",
|
||||
"architectures": [
|
||||
@@ -1058,7 +1079,7 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 49,
|
||||
"activeBlockCount": 50,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 8,
|
||||
"Ascend_910-b4|vllm": 8,
|
||||
@@ -1067,7 +1088,7 @@
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 1,
|
||||
"Mthreads_s4000|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm": 8,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 9,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 10,
|
||||
"Vastai_va16|vllm": 2,
|
||||
"hygon_k100-ai|vllm": 2
|
||||
},
|
||||
@@ -2891,14 +2912,14 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 191,
|
||||
"attributableFailureCount": 192,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 191,
|
||||
"decisionTotal": 192,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5,
|
||||
"backend_operator": 12,
|
||||
"framework_architecture_unsupported": 70,
|
||||
"framework_architecture_unsupported": 71,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 2,
|
||||
"platform_storage": 1,
|
||||
@@ -2906,7 +2927,7 @@
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 106
|
||||
},
|
||||
"failureCount": 199,
|
||||
"failureCount": 200,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -2916,7 +2937,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 199,
|
||||
"total": 200,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -3433,14 +3454,14 @@
|
||||
"unresolvedFailureCount": 1595
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 200,
|
||||
"attributableFailureCount": 201,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 200,
|
||||
"decisionTotal": 201,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 56,
|
||||
"backend_operator": 12,
|
||||
"framework_architecture_unsupported": 70,
|
||||
"framework_architecture_unsupported": 71,
|
||||
"memory_capacity": 10,
|
||||
"platform_infrastructure": 2,
|
||||
"platform_storage": 1,
|
||||
@@ -3448,14 +3469,14 @@
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 106
|
||||
},
|
||||
"failureCount": 259,
|
||||
"failureCount": 260,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 259,
|
||||
"total": 260,
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -3478,7 +3499,7 @@
|
||||
"unresolvedFailureCount": 3
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-11-03T07:52:18.844962+00:00",
|
||||
"generatedAt": "2026-11-03T08:08:12.096889+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 139,
|
||||
@@ -3819,16 +3840,16 @@
|
||||
"unresolvedFailureCount": 338
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 1049,
|
||||
"attributableFailureCount": 1050,
|
||||
"decisionFailureRate": 0.9067,
|
||||
"decisionSuccessRate": 0.0933,
|
||||
"decisionTotal": 1157,
|
||||
"decisionTotal": 1158,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 119,
|
||||
"architecture_compatibility": 13,
|
||||
"backend_operator": 45,
|
||||
"context_length": 44,
|
||||
"framework_architecture_unsupported": 392,
|
||||
"framework_architecture_unsupported": 393,
|
||||
"memory_capacity": 114,
|
||||
"platform_infrastructure": 79,
|
||||
"platform_storage": 3,
|
||||
@@ -3838,14 +3859,14 @@
|
||||
"任务失败_原因未确认": 8,
|
||||
"参数/模板问题": 239
|
||||
},
|
||||
"failureCount": 1497,
|
||||
"failureRate": 0.9327,
|
||||
"failureCount": 1498,
|
||||
"failureRate": 0.9328,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 82,
|
||||
"successCount": 108,
|
||||
"successRate": 0.0673,
|
||||
"total": 1605,
|
||||
"successRate": 0.0672,
|
||||
"total": 1606,
|
||||
"unresolvedFailureCount": 366
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -4391,10 +4412,10 @@
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"任务失败_原因未确认": 8,
|
||||
"参数/模板问题": 4
|
||||
"参数/模板问题": 3
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureRate": 0.8571,
|
||||
"failureCount": 11,
|
||||
"failureRate": 0.8462,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-10-31T12:08:15.546689+00:00",
|
||||
@@ -4402,31 +4423,31 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1429,
|
||||
"successRate": 0.1538,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 12
|
||||
"total": 13,
|
||||
"unresolvedFailureCount": 11
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 15,
|
||||
"consecutiveFailures": 15,
|
||||
"attributableFailureCount": 16,
|
||||
"consecutiveFailures": 16,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 15,
|
||||
"decisionTotal": 16,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 6,
|
||||
"framework_architecture_unsupported": 7,
|
||||
"platform_storage": 1,
|
||||
"tokenizer_compatibility": 8
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureCount": 18,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-10-31T12:05:02.739582+00:00",
|
||||
"lastTerminalAt": "2026-11-02T03:10:28.741795+00:00",
|
||||
"lastTerminalAt": "2026-11-03T08:08:11.857200+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
@@ -4434,7 +4455,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -4644,13 +4665,13 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17623,
|
||||
"totalRecords": 17623,
|
||||
"terminalRecords": 17624,
|
||||
"totalRecords": 17624,
|
||||
"totals": {
|
||||
"attributableFailureCount": 7900,
|
||||
"decisionFailureRate": 0.8908,
|
||||
"decisionSuccessRate": 0.1092,
|
||||
"decisionTotal": 8868,
|
||||
"attributableFailureCount": 7901,
|
||||
"decisionFailureRate": 0.8909,
|
||||
"decisionSuccessRate": 0.1091,
|
||||
"decisionTotal": 8869,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3521,
|
||||
"architecture_compatibility": 62,
|
||||
@@ -4658,7 +4679,7 @@
|
||||
"backend_operator": 136,
|
||||
"configuration_launch": 489,
|
||||
"context_length": 408,
|
||||
"framework_architecture_unsupported": 3156,
|
||||
"framework_architecture_unsupported": 3157,
|
||||
"memory_capacity": 1208,
|
||||
"model_load": 586,
|
||||
"platform_infrastructure": 652,
|
||||
@@ -4672,14 +4693,14 @@
|
||||
"参数/模板问题": 3675,
|
||||
"日志缺失": 719
|
||||
},
|
||||
"failureCount": 16655,
|
||||
"failureCount": 16656,
|
||||
"failureRate": 0.9451,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 694,
|
||||
"successCount": 968,
|
||||
"successRate": 0.0549,
|
||||
"total": 17623,
|
||||
"total": 17624,
|
||||
"unresolvedFailureCount": 8061
|
||||
},
|
||||
"warnings": [
|
||||
@@ -4729,6 +4750,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17623,
|
||||
"summarizedRecords": 17624,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user