state: generation 19240 (cycle_no_slots)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-11-01T21:03:57.528017+00:00",
|
||||
"lastSyncTime": "2026-11-01T21:03:57.238253+00:00",
|
||||
"generatedAt": "2026-11-02T03:10:29.104148+00:00",
|
||||
"lastSyncTime": "2026-11-02T03:10:28.741795+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"agentSummaries": {
|
||||
@@ -24,16 +24,16 @@
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 144,
|
||||
"decisionFailureRate": 0.9474,
|
||||
"decisionSuccessRate": 0.0526,
|
||||
"decisionTotal": 152,
|
||||
"attributableFailureCount": 145,
|
||||
"decisionFailureRate": 0.9477,
|
||||
"decisionSuccessRate": 0.0523,
|
||||
"decisionTotal": 153,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 59,
|
||||
"backend_operator": 5,
|
||||
"configuration_launch": 33,
|
||||
"context_length": 5,
|
||||
"framework_architecture_unsupported": 64,
|
||||
"framework_architecture_unsupported": 65,
|
||||
"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": 464,
|
||||
"failureCount": 465,
|
||||
"failureRate": 0.9831,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 8,
|
||||
"successRate": 0.0169,
|
||||
"total": 472,
|
||||
"total": 473,
|
||||
"unresolvedFailureCount": 319
|
||||
}
|
||||
},
|
||||
@@ -671,6 +671,27 @@
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|architectures:cagliostroforcausallm": {
|
||||
"architectureSignature": "architectures:cagliostroforcausallm",
|
||||
"architectures": [
|
||||
"cagliostroforcausallm"
|
||||
],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-12-02T03:10:28.741795+00:00",
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"latestFailureAt": "2026-11-02T03:10:28.741795+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "architectures",
|
||||
"modelType": null,
|
||||
"sourceModelIds": [
|
||||
"bench-labs/tinctura-v1"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5520202"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|architectures:sophiaforcausallm": {
|
||||
"architectureSignature": "architectures:sophiaforcausallm",
|
||||
"architectures": [
|
||||
@@ -1037,7 +1058,7 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 48,
|
||||
"activeBlockCount": 49,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 8,
|
||||
"Ascend_910-b4|vllm": 8,
|
||||
@@ -1046,7 +1067,7 @@
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 1,
|
||||
"Mthreads_s4000|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm": 8,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 8,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 9,
|
||||
"Vastai_va16|vllm": 2,
|
||||
"hygon_k100-ai|vllm": 2
|
||||
},
|
||||
@@ -2870,14 +2891,14 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 190,
|
||||
"attributableFailureCount": 191,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 190,
|
||||
"decisionTotal": 191,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5,
|
||||
"backend_operator": 12,
|
||||
"framework_architecture_unsupported": 69,
|
||||
"framework_architecture_unsupported": 70,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 2,
|
||||
"platform_storage": 1,
|
||||
@@ -2885,7 +2906,7 @@
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 106
|
||||
},
|
||||
"failureCount": 198,
|
||||
"failureCount": 199,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -2895,7 +2916,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 198,
|
||||
"total": 199,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -3412,14 +3433,14 @@
|
||||
"unresolvedFailureCount": 1595
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 199,
|
||||
"attributableFailureCount": 200,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 199,
|
||||
"decisionTotal": 200,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 56,
|
||||
"backend_operator": 12,
|
||||
"framework_architecture_unsupported": 69,
|
||||
"framework_architecture_unsupported": 70,
|
||||
"memory_capacity": 10,
|
||||
"platform_infrastructure": 2,
|
||||
"platform_storage": 1,
|
||||
@@ -3427,14 +3448,14 @@
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 106
|
||||
},
|
||||
"failureCount": 258,
|
||||
"failureCount": 259,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 258,
|
||||
"total": 259,
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -3457,7 +3478,7 @@
|
||||
"unresolvedFailureCount": 3
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-11-01T21:03:57.523913+00:00",
|
||||
"generatedAt": "2026-11-02T03:10:29.099542+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 139,
|
||||
@@ -3798,16 +3819,16 @@
|
||||
"unresolvedFailureCount": 338
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 1046,
|
||||
"decisionFailureRate": 0.9064,
|
||||
"decisionSuccessRate": 0.0936,
|
||||
"decisionTotal": 1154,
|
||||
"attributableFailureCount": 1047,
|
||||
"decisionFailureRate": 0.9065,
|
||||
"decisionSuccessRate": 0.0935,
|
||||
"decisionTotal": 1155,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 119,
|
||||
"architecture_compatibility": 13,
|
||||
"backend_operator": 45,
|
||||
"context_length": 44,
|
||||
"framework_architecture_unsupported": 391,
|
||||
"framework_architecture_unsupported": 392,
|
||||
"memory_capacity": 114,
|
||||
"platform_infrastructure": 79,
|
||||
"platform_storage": 3,
|
||||
@@ -3817,14 +3838,14 @@
|
||||
"任务失败_原因未确认": 8,
|
||||
"参数/模板问题": 239
|
||||
},
|
||||
"failureCount": 1494,
|
||||
"failureCount": 1495,
|
||||
"failureRate": 0.9326,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 82,
|
||||
"successCount": 108,
|
||||
"successRate": 0.0674,
|
||||
"total": 1602,
|
||||
"total": 1603,
|
||||
"unresolvedFailureCount": 366
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -4388,24 +4409,24 @@
|
||||
"unresolvedFailureCount": 12
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 14,
|
||||
"consecutiveFailures": 14,
|
||||
"attributableFailureCount": 15,
|
||||
"consecutiveFailures": 15,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 14,
|
||||
"decisionTotal": 15,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"framework_architecture_unsupported": 6,
|
||||
"platform_storage": 1,
|
||||
"tokenizer_compatibility": 8
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-10-31T12:05:02.739582+00:00",
|
||||
"lastTerminalAt": "2026-11-01T21:03:57.238253+00:00",
|
||||
"lastTerminalAt": "2026-11-02T03:10:28.741795+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
@@ -4413,7 +4434,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -4522,18 +4543,17 @@
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"model_load": 1
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4545,7 +4565,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 6
|
||||
}
|
||||
},
|
||||
@@ -4624,13 +4644,13 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17620,
|
||||
"totalRecords": 17620,
|
||||
"terminalRecords": 17621,
|
||||
"totalRecords": 17621,
|
||||
"totals": {
|
||||
"attributableFailureCount": 7897,
|
||||
"attributableFailureCount": 7898,
|
||||
"decisionFailureRate": 0.8908,
|
||||
"decisionSuccessRate": 0.1092,
|
||||
"decisionTotal": 8865,
|
||||
"decisionTotal": 8866,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3521,
|
||||
"architecture_compatibility": 62,
|
||||
@@ -4638,7 +4658,7 @@
|
||||
"backend_operator": 136,
|
||||
"configuration_launch": 489,
|
||||
"context_length": 408,
|
||||
"framework_architecture_unsupported": 3155,
|
||||
"framework_architecture_unsupported": 3156,
|
||||
"memory_capacity": 1208,
|
||||
"model_load": 586,
|
||||
"platform_infrastructure": 652,
|
||||
@@ -4652,14 +4672,14 @@
|
||||
"参数/模板问题": 3675,
|
||||
"日志缺失": 719
|
||||
},
|
||||
"failureCount": 16652,
|
||||
"failureCount": 16653,
|
||||
"failureRate": 0.9451,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 694,
|
||||
"successCount": 968,
|
||||
"successRate": 0.0549,
|
||||
"total": 17620,
|
||||
"total": 17621,
|
||||
"unresolvedFailureCount": 8061
|
||||
},
|
||||
"warnings": [
|
||||
@@ -4709,6 +4729,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17620,
|
||||
"summarizedRecords": 17621,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user