state: generation 6577 (cycle)
This commit is contained in:
@@ -1454,7 +1454,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T06:30:12.333577+00:00",
|
||||
"generatedAt": "2026-09-13T06:32:45.113193+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 73,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
"11": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 475,
|
||||
"listingErrors": 476,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 11,
|
||||
"nextAccountIndex": 0,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-13T06:30:12.308918+00:00",
|
||||
"updatedAt": "2026-09-13T06:32:45.085731+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-13T06:28:37.510741+00:00",
|
||||
"generatedAt": "2026-09-13T06:31:20.655412+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T05:58:35.719154+00:00",
|
||||
"lastSyncTime": "2026-09-13T05:58:35.516166+00:00",
|
||||
"generatedAt": "2026-09-13T06:31:13.409841+00:00",
|
||||
"lastSyncTime": "2026-09-13T06:31:13.105179+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1635,30 +1635,30 @@
|
||||
"unresolvedFailureCount": 35
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 28,
|
||||
"decisionFailureRate": 0.9655,
|
||||
"decisionSuccessRate": 0.0345,
|
||||
"decisionTotal": 29,
|
||||
"attributableFailureCount": 29,
|
||||
"decisionFailureRate": 0.9667,
|
||||
"decisionSuccessRate": 0.0333,
|
||||
"decisionTotal": 30,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 28,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 20,
|
||||
"framework_architecture_unsupported": 21,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 83,
|
||||
"failureRate": 0.9881,
|
||||
"failureCount": 84,
|
||||
"failureRate": 0.9882,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0119,
|
||||
"successRate": 0.0118,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 84,
|
||||
"total": 85,
|
||||
"unresolvedFailureCount": 55
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
@@ -2463,14 +2463,14 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 151,
|
||||
"decisionFailureRate": 0.7366,
|
||||
"decisionSuccessRate": 0.2634,
|
||||
"decisionTotal": 205,
|
||||
"attributableFailureCount": 152,
|
||||
"decisionFailureRate": 0.7379,
|
||||
"decisionSuccessRate": 0.2621,
|
||||
"decisionTotal": 206,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 141,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 96,
|
||||
"framework_architecture_unsupported": 97,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 43,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2478,14 +2478,14 @@
|
||||
"参数/模板问题": 61,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1027,
|
||||
"failureRate": 0.95,
|
||||
"failureCount": 1028,
|
||||
"failureRate": 0.9501,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 54,
|
||||
"successRate": 0.05,
|
||||
"total": 1081,
|
||||
"successRate": 0.0499,
|
||||
"total": 1082,
|
||||
"unresolvedFailureCount": 875
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2617,7 +2617,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T05:58:35.713501+00:00",
|
||||
"generatedAt": "2026-09-13T06:31:13.405630+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2668,27 +2668,27 @@
|
||||
"unresolvedFailureCount": 223
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 31,
|
||||
"decisionFailureRate": 0.9688,
|
||||
"decisionSuccessRate": 0.0312,
|
||||
"decisionTotal": 32,
|
||||
"attributableFailureCount": 32,
|
||||
"decisionFailureRate": 0.9697,
|
||||
"decisionSuccessRate": 0.0303,
|
||||
"decisionTotal": 33,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 28,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 86,
|
||||
"failureRate": 0.9885,
|
||||
"failureCount": 87,
|
||||
"failureRate": 0.9886,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0115,
|
||||
"total": 87,
|
||||
"successRate": 0.0114,
|
||||
"total": 88,
|
||||
"unresolvedFailureCount": 55
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -4561,23 +4561,23 @@
|
||||
"unresolvedFailureCount": 12
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 8,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureCount": 19,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T23:26:15.638629+00:00",
|
||||
"lastTerminalAt": "2026-09-13T06:31:13.105179+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4585,7 +4585,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 18,
|
||||
"total": 19,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -7462,17 +7462,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1767,
|
||||
"totalRecords": 1854,
|
||||
"terminalRecords": 1768,
|
||||
"totalRecords": 1855,
|
||||
"totals": {
|
||||
"attributableFailureCount": 513,
|
||||
"decisionFailureRate": 0.8969,
|
||||
"decisionSuccessRate": 0.1031,
|
||||
"decisionTotal": 572,
|
||||
"attributableFailureCount": 514,
|
||||
"decisionFailureRate": 0.897,
|
||||
"decisionSuccessRate": 0.103,
|
||||
"decisionTotal": 573,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 415,
|
||||
"backend_operator": 43,
|
||||
"framework_architecture_unsupported": 322,
|
||||
"framework_architecture_unsupported": 323,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 73,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -7482,20 +7482,21 @@
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1708,
|
||||
"failureCount": 1709,
|
||||
"failureRate": 0.9666,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 59,
|
||||
"successRate": 0.0334,
|
||||
"total": 1767,
|
||||
"total": 1768,
|
||||
"unresolvedFailureCount": 1191
|
||||
},
|
||||
"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。",
|
||||
@@ -7504,7 +7505,6 @@
|
||||
"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。",
|
||||
@@ -7527,6 +7527,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1854,
|
||||
"summarizedRecords": 1855,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "", "lastSyncTime": "2026-09-13T06:31:13.105179+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T06:27:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610370", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T05:58:35.516166+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T05:53:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4558021", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-13T05:49:53.509642+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T05:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549640", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T05:03:23.648954+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4585193", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-09T11:43:37.216601+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-09T11:43:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460828", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-09T11:43:37.216624+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-09T11:41:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460430", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"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": "2026-09-09T11:08:33.010362+00:00", "modelId": "modelyoungyyds/SuperAI-v1-Mini", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:07:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332981", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-09T11:08:33.010387+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460755", "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
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "fd57e88cf3292a00ab3ddb86055eb675a4568613743f1fc57cf0807b9f151fde",
|
||||
".modelhub_state/architecture_history_backfill.json": "d80c188139abe4e3c328ce1123629bf235d403052cf071a62eabee5e02038dc8",
|
||||
".modelhub_state/market_intelligence.json": "b00e6a15c27fa7aec02421e13d2c1b1df93d271a2a69e144ca5cb94a075be8c1",
|
||||
".modelhub_state/official_capabilities.json": "22d6e8f45f16df115f17cfd7dbbfe9d62899e990cdc423bdd714629254dd6e62",
|
||||
".modelhub_state/outcome_checkpoint.json": "c3d55235454323ea1dc5b0fca87fab66ce11f4b3f68611a64a756884ab63e50b",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "3c5ae1ebeb46840d0e100aa03ae4cedf02e4031a75d5f1ee282e476de4f1e15f",
|
||||
".modelhub_state/architecture_history_backfill.json": "682ae7a859a1eff372a029b3d58cd6e1d86f61709d0ab30017d69edbaf8f8e7c",
|
||||
".modelhub_state/market_intelligence.json": "a8887bd9e9f38ff9879efb23af0b00038f2acab2752ddb4c9f811fee533bf8ae",
|
||||
".modelhub_state/official_capabilities.json": "dd069af698e068c825e8109dfd6ba838cafb84df0a471e701fa6e4929cf2a6fc",
|
||||
".modelhub_state/outcome_checkpoint.json": "5b5798d7d50f69dba1def499fa280c448e307f1e5ce5166cf61b58ac5a11d985",
|
||||
".modelhub_state/queue_cleanup_latest.json": "51e7d1585319177976584ac9d97c18e02335e06fbd17bfdd6be748f1310ef4da",
|
||||
".modelhub_state/recent_outcomes.jsonl": "3dc50edc255ec3d55d8f3484144800884371f3bc74293c58f6333aabd08c07c7",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "6829540e6502711acc7845bb64cec4b19191b08aec77cc3f36a59cc807c36fa7",
|
||||
".modelhub_state/recovery_intents.jsonl": "eec3192faaec019420f9a6f583728d35dfc1accb4b52a2a3438a1f1204407522",
|
||||
".modelhub_state/recent_outcomes.jsonl": "e16dc3fdd8bf32788910f9847022c45fe2762b5047858f69c2bba03aba30922f",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "38561e8cf6f71562dfa1a82093ad0d69ca5ddd4e94675caea54e9b892021c356",
|
||||
".modelhub_state/recovery_intents.jsonl": "68f7536b3149858ef9d68b94a82f2c997fd0bf99c9289b93fbb5f1aa22fe6a63",
|
||||
".modelhub_state/routing_intelligence.json": "8bbc9c8a0b34a70e0b79e5c4089e16cf94def46a7292fb8d7d5c9890b2433a99",
|
||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
|
||||
"ledger/submissions.jsonl": "1a43aba60f5a20c4003652cc68d94d682c68a27eb62b4140cbdbf822a121d016",
|
||||
"outcomes/submissions.jsonl": "b41282e90b445956e11184fac94c9cc3e805749e8e9eb05ae4ff79d53e15a030"
|
||||
},
|
||||
"generation": 6576,
|
||||
"generation": 6577,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-13T06:30:12.410957+00:00",
|
||||
"updatedAt": "2026-09-13T06:32:46.081368+00:00",
|
||||
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user