state: generation 6654 (cycle)
This commit is contained in:
@@ -1475,7 +1475,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T10:04:36.912244+00:00",
|
||||
"generatedAt": "2026-09-13T10:07:15.822917+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 74,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -35,7 +35,7 @@
|
||||
"2": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 482,
|
||||
"listingErrors": 483,
|
||||
"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": 2,
|
||||
"nextAccountIndex": 3,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-13T10:04:36.888497+00:00",
|
||||
"updatedAt": "2026-09-13T10:07:15.799938+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-13T10:02:39.459481+00:00",
|
||||
"generatedAt": "2026-09-13T10:05:44.730279+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T09:40:23.888574+00:00",
|
||||
"lastSyncTime": "2026-09-13T09:40:23.641563+00:00",
|
||||
"generatedAt": "2026-09-13T10:05:37.934672+00:00",
|
||||
"lastSyncTime": "2026-09-13T10:05:37.717736+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2011,11 +2011,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 36,
|
||||
"ambiguous_runtime": 37,
|
||||
"memory_capacity": 1,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 59,
|
||||
"failureCount": 60,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
@@ -2025,8 +2025,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 59,
|
||||
"unresolvedFailureCount": 58
|
||||
"total": 60,
|
||||
"unresolvedFailureCount": 59
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|visual-multi-modal": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2489,7 +2489,7 @@
|
||||
"decisionSuccessRate": 0.2621,
|
||||
"decisionTotal": 206,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 141,
|
||||
"ambiguous_runtime": 142,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 97,
|
||||
"memory_capacity": 5,
|
||||
@@ -2499,15 +2499,15 @@
|
||||
"参数/模板问题": 61,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1028,
|
||||
"failureCount": 1029,
|
||||
"failureRate": 0.9501,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 54,
|
||||
"successRate": 0.0499,
|
||||
"total": 1082,
|
||||
"unresolvedFailureCount": 875
|
||||
"total": 1083,
|
||||
"unresolvedFailureCount": 876
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 296,
|
||||
@@ -2638,7 +2638,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T09:40:23.884789+00:00",
|
||||
"generatedAt": "2026-09-13T10:05:37.928427+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2831,20 +2831,20 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 71,
|
||||
"ambiguous_runtime": 72,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 96,
|
||||
"failureCount": 97,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 96,
|
||||
"unresolvedFailureCount": 95
|
||||
"total": 97,
|
||||
"unresolvedFailureCount": 96
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 53,
|
||||
@@ -4775,13 +4775,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7
|
||||
"ambiguous_runtime": 8
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-13T04:05:56.910845+00:00",
|
||||
"lastTerminalAt": "2026-09-13T10:05:37.717736+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4789,8 +4789,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7483,15 +7483,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1770,
|
||||
"totalRecords": 1857,
|
||||
"terminalRecords": 1771,
|
||||
"totalRecords": 1858,
|
||||
"totals": {
|
||||
"attributableFailureCount": 516,
|
||||
"decisionFailureRate": 0.8974,
|
||||
"decisionSuccessRate": 0.1026,
|
||||
"decisionTotal": 575,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 415,
|
||||
"ambiguous_runtime": 416,
|
||||
"backend_operator": 43,
|
||||
"framework_architecture_unsupported": 325,
|
||||
"memory_capacity": 11,
|
||||
@@ -7503,21 +7503,20 @@
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1711,
|
||||
"failureCount": 1712,
|
||||
"failureRate": 0.9667,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 59,
|
||||
"successRate": 0.0333,
|
||||
"total": 1770,
|
||||
"unresolvedFailureCount": 1191
|
||||
"total": 1771,
|
||||
"unresolvedFailureCount": 1192
|
||||
},
|
||||
"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。",
|
||||
@@ -7526,6 +7525,7 @@
|
||||
"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。",
|
||||
@@ -7548,6 +7548,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1857,
|
||||
"summarizedRecords": 1858,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"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": "2026-09-13T10:05:37.717736+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:59:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560059", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T09:40:23.641563+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4557415", "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", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-13T08:31:12.943798+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T08:23:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609080", "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", "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}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"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"], "framework": "", "lastSyncTime": "2026-09-09T14:59:28.333331+00:00", "modelId": "ornith-ai/Ornith-1.5-9B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T14:55:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332980", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T16:44:50.902809+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634920, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T12:08:11.431365+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T12:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080603", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"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}
|
||||
|
||||
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": "19e0384e996bce9cefff9ee1a53f21ce6b535d3dd7ad5c14ae73cde18f31d27d",
|
||||
".modelhub_state/architecture_history_backfill.json": "77cae987a225152876c47594ec6d7c13b7343f8ff5c4d9ae81fceb331bf34c1f",
|
||||
".modelhub_state/market_intelligence.json": "afe9e857bbacb95b09539f646162a5b8cc043fcf231227e2e1df07507e34841d",
|
||||
".modelhub_state/official_capabilities.json": "d833015856345e6f34bacdba4e5c277335d81b64079cfee3bf7cf6256791edea",
|
||||
".modelhub_state/outcome_checkpoint.json": "96405d855a2a95a4d84eb43cca03b3e2bea042142ef1c8da6829d6598a85dbe4",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "f53db03745da0b4831a410f9d9f4ae1f838837abfca127fc10681ae928522bd7",
|
||||
".modelhub_state/architecture_history_backfill.json": "d53346f85ed39b0a49c02d18ab830a78e42b4296e27eb3ab7fac57aa961f2277",
|
||||
".modelhub_state/market_intelligence.json": "be4cc8aaa95a3d223cfc94da9fcd4ff00eb4c74ad37a5ac7a9a3888344785d67",
|
||||
".modelhub_state/official_capabilities.json": "422886ab5f074cdfb26d45c493698aba2a4520bac008cab9433ac48b71537f88",
|
||||
".modelhub_state/outcome_checkpoint.json": "2135e096743465f910f31af8814ee60a2f6ef565e52fb0fa86e0d85f4efec7ff",
|
||||
".modelhub_state/queue_cleanup_latest.json": "ead6d4dadaa1cc97a064674e6cd6e82e9bc551fa8eef7e0d699d7fc494f51834",
|
||||
".modelhub_state/recent_outcomes.jsonl": "93e80e0dfefc0d7c521a75d2eae3a6d22cfcb3033462a2e0b28a22629a4be629",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "986a18feb890cbddfd530f54e8883a8d57a39acb937eabf428253a3fbd406f1e",
|
||||
".modelhub_state/recovery_intents.jsonl": "dabf1360ded7dac6380234be3ab3bf3150fee2dfe3f318f7ea50e06b1abcf4e4",
|
||||
".modelhub_state/recent_outcomes.jsonl": "37cdee1c5f1b3c8b6573da6796fd6b89e122be93b75484612709af6cee5c4776",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "211eb29d0c0d7bd2bbcd658d6a883fa820f92ada99a65bf7037551677af9b0a4",
|
||||
".modelhub_state/recovery_intents.jsonl": "562dee796f28785c5fbd151973b42ce595fc20883e46b1e2493a7b2d154d91d2",
|
||||
".modelhub_state/routing_intelligence.json": "25f8e57e8ffc675386079e0278a3edc3292354ffe526675a613f15dbaf877962",
|
||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
|
||||
"ledger/submissions.jsonl": "8bca7d5cce6ea93630ae8fce82a060d0203c390584b3f5cd11e3577c380fcf66",
|
||||
"outcomes/submissions.jsonl": "cca123adc0ce49b2f9782e95a8123824c65d706c415bf53f56a5f2bde32dd9c4"
|
||||
},
|
||||
"generation": 6653,
|
||||
"generation": 6654,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-13T10:04:36.996501+00:00",
|
||||
"updatedAt": "2026-09-13T10:07:17.208931+00:00",
|
||||
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user