state: generation 11111 (cycle)
This commit is contained in:
@@ -2416,7 +2416,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T02:45:51.661216+00:00",
|
||||
"generatedAt": "2026-09-21T02:49:19.928553+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 119,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -425,7 +425,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T02:48:17.967660+00:00",
|
||||
"generatedAt": "2026-09-21T02:49:29.685888+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-21T02:48:17.967660+00:00",
|
||||
"catalogUpdatedAt": "2026-09-21T02:49:29.685888+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-21T02:48:17.967660+00:00",
|
||||
"generatedAt": "2026-09-21T02:49:29.685888+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6336,6 +6336,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-21T02:48:17.967660+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-21T02:49:29.685888+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T02:42:24.603008+00:00",
|
||||
"lastSyncTime": "2026-09-21T02:42:24.494044+00:00",
|
||||
"generatedAt": "2026-09-21T02:49:19.865534+00:00",
|
||||
"lastSyncTime": "2026-09-21T02:49:19.765032+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4456,9 +4456,9 @@
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||
"attributableFailureCount": 13,
|
||||
"decisionFailureRate": 0.1313,
|
||||
"decisionSuccessRate": 0.8687,
|
||||
"decisionTotal": 99,
|
||||
"decisionFailureRate": 0.13,
|
||||
"decisionSuccessRate": 0.87,
|
||||
"decisionTotal": 100,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 52,
|
||||
"context_length": 5,
|
||||
@@ -4467,16 +4467,16 @@
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 309,
|
||||
"failureRate": 0.7823,
|
||||
"failureRate": 0.7803,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 86,
|
||||
"successRate": 0.2177,
|
||||
"successCount": 87,
|
||||
"successRate": 0.2197,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 395,
|
||||
"total": 396,
|
||||
"unresolvedFailureCount": 296
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -5001,9 +5001,9 @@
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 1858,
|
||||
"decisionFailureRate": 0.6972,
|
||||
"decisionSuccessRate": 0.3028,
|
||||
"decisionTotal": 2665,
|
||||
"decisionFailureRate": 0.6969,
|
||||
"decisionSuccessRate": 0.3031,
|
||||
"decisionTotal": 2666,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1964,
|
||||
"architecture_compatibility": 100,
|
||||
@@ -5021,13 +5021,13 @@
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 8306,
|
||||
"failureRate": 0.9114,
|
||||
"failureRate": 0.9113,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 42,
|
||||
"successCount": 807,
|
||||
"successRate": 0.0886,
|
||||
"total": 9113,
|
||||
"successCount": 808,
|
||||
"successRate": 0.0887,
|
||||
"total": 9114,
|
||||
"unresolvedFailureCount": 6406
|
||||
},
|
||||
"vllm": {
|
||||
@@ -5196,7 +5196,7 @@
|
||||
"unresolvedFailureCount": 58
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T02:42:24.558323+00:00",
|
||||
"generatedAt": "2026-09-21T02:49:19.855910+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 90,
|
||||
@@ -5522,9 +5522,9 @@
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 732,
|
||||
"decisionFailureRate": 0.8949,
|
||||
"decisionSuccessRate": 0.1051,
|
||||
"decisionTotal": 818,
|
||||
"decisionFailureRate": 0.8938,
|
||||
"decisionSuccessRate": 0.1062,
|
||||
"decisionTotal": 819,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 162,
|
||||
"architecture_compatibility": 44,
|
||||
@@ -5540,13 +5540,13 @@
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1372,
|
||||
"failureRate": 0.941,
|
||||
"failureRate": 0.9404,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 218,
|
||||
"successCount": 86,
|
||||
"successRate": 0.059,
|
||||
"total": 1458,
|
||||
"successCount": 87,
|
||||
"successRate": 0.0596,
|
||||
"total": 1459,
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -14391,21 +14391,21 @@
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-21T02:15:17.867390+00:00",
|
||||
"lastTerminalAt": "2026-09-21T02:49:19.765032+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successCount": 3,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -14439,7 +14439,7 @@
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
@@ -14449,11 +14449,11 @@
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 4,
|
||||
"successCount": 3,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -29910,13 +29910,13 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16047,
|
||||
"totalRecords": 16214,
|
||||
"terminalRecords": 16048,
|
||||
"totalRecords": 16215,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5830,
|
||||
"decisionFailureRate": 0.8618,
|
||||
"decisionSuccessRate": 0.1382,
|
||||
"decisionTotal": 6765,
|
||||
"decisionFailureRate": 0.8617,
|
||||
"decisionSuccessRate": 0.1383,
|
||||
"decisionTotal": 6766,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3836,
|
||||
"architecture_compatibility": 212,
|
||||
@@ -29939,9 +29939,9 @@
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 935,
|
||||
"successCount": 936,
|
||||
"successRate": 0.0583,
|
||||
"total": 16047,
|
||||
"total": 16048,
|
||||
"unresolvedFailureCount": 8360
|
||||
},
|
||||
"warnings": [
|
||||
@@ -29989,12 +29989,12 @@
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 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。",
|
||||
"组合 Iluvatar_bi-150|transformers|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 Cambricon_mlu-370-x8|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 Ascend_910-b3|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 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 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16214,
|
||||
"summarizedRecords": 16215,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:49:19.765032+00:00", "modelId": "BAAI/Aerospace-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:47:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457982", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-21T02:38:57.372787+00:00", "modelId": "nv-community/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079201", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:15:17.867390+00:00", "modelId": "BAAI/Automobile-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457986", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-21T01:35:45.556193+00:00", "modelId": "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T01:23:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079972", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-17T00:35:45.048497+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T00:27:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610389", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-16T22:43:36.337604+00:00", "modelId": "BAAI/Automobile-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-16T22:43:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4471936", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-16T22:18:05.914670+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-rl", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-16T22:17:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471939", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-16T21:51:28.830496+00:00", "modelId": "BAAI/Hospitality-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-16T21:43:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4471934", "taskType": "text-generation", "verifyResult": 1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user