state: generation 6563 (cycle)

This commit is contained in:
2026-09-13 06:00:07 +00:00
parent a72eb7f868
commit b595cc889f
9 changed files with 2036 additions and 2037 deletions

View File

@@ -1454,7 +1454,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-13T05:57:34.699990+00:00",
"generatedAt": "2026-09-13T06:00:07.333126+00:00",
"summary": {
"activeBlockCount": 73,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 474,
"listingErrors": 475,
"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": "2026-09-13T05:57:34.675764+00:00",
"updatedAt": "2026-09-13T06:00:07.309326+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T05:55:51.024018+00:00",
"generatedAt": "2026-09-13T05:58:43.364601+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T05:49:53.761779+00:00",
"lastSyncTime": "2026-09-13T05:49:53.509642+00:00",
"generatedAt": "2026-09-13T05:58:35.719154+00:00",
"lastSyncTime": "2026-09-13T05:58:35.516166+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2398,19 +2398,19 @@
"unresolvedFailureCount": 8
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 43,
"attributableFailureCount": 44,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 43,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 32,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 61,
"failureCount": 62,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2420,7 +2420,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 61,
"total": 62,
"unresolvedFailureCount": 18
}
},
@@ -2489,14 +2489,14 @@
"unresolvedFailureCount": 875
},
"vllm": {
"attributableFailureCount": 293,
"attributableFailureCount": 294,
"decisionFailureRate": 0.9899,
"decisionSuccessRate": 0.0101,
"decisionTotal": 296,
"decisionTotal": 297,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 206,
"framework_architecture_unsupported": 207,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2505,14 +2505,14 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 24
},
"failureCount": 519,
"failureCount": 520,
"failureRate": 0.9943,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0057,
"total": 522,
"total": 523,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2617,7 +2617,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T05:49:53.757657+00:00",
"generatedAt": "2026-09-13T05:58:35.713501+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2924,13 +2924,13 @@
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
"attributableFailureCount": 47,
"attributableFailureCount": 48,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 47,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 36,
"framework_architecture_unsupported": 37,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
@@ -2938,14 +2938,14 @@
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 103,
"failureCount": 104,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 103,
"total": 104,
"unresolvedFailureCount": 56
}
},
@@ -5032,15 +5032,15 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|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": 12,
"framework_architecture_unsupported": 5,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 6,
"model_load": 1,
"repository_structure": 1,
"runtime_memory": 1
@@ -5049,7 +5049,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T00:10:37.716599+00:00",
"lastTerminalAt": "2026-09-13T05:58:35.516166+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5058,7 +5058,7 @@
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 12
"unresolvedFailureCount": 11
}
},
"recentProfileCombinationStats": {
@@ -7462,17 +7462,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1766,
"totalRecords": 1853,
"terminalRecords": 1767,
"totalRecords": 1854,
"totals": {
"attributableFailureCount": 512,
"decisionFailureRate": 0.8967,
"decisionSuccessRate": 0.1033,
"decisionTotal": 571,
"attributableFailureCount": 513,
"decisionFailureRate": 0.8969,
"decisionSuccessRate": 0.1031,
"decisionTotal": 572,
"failureBreakdown": {
"ambiguous_runtime": 415,
"backend_operator": 43,
"framework_architecture_unsupported": 321,
"framework_architecture_unsupported": 322,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
@@ -7482,21 +7482,20 @@
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1707,
"failureCount": 1708,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 59,
"successRate": 0.0334,
"total": 1766,
"total": 1767,
"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。",
@@ -7505,6 +7504,7 @@
"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。",
@@ -7527,6 +7527,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1853,
"summarizedRecords": 1854,
"version": 1
}

View File

@@ -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", "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}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T04:23:07.613289+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:17:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4557614", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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}
{"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_mtp"], "framework": "", "lastSyncTime": "2026-09-09T11:01:57.287962+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332978", "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

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "0d7083dc330ed2a62859265c0bf944854024ca2821c976b819b0766126c97a8e",
".modelhub_state/architecture_history_backfill.json": "47d0484d448a251bc84a19a0a9b367efd029cf18b4e8a5aa844ed3bdd648e835",
".modelhub_state/market_intelligence.json": "54abbe417c9fc4253fa2d0dadcdf5e859945d39b0941df263fee313fa60e4f83",
".modelhub_state/official_capabilities.json": "41bbcc847f557142bf346e5d38fbc38e784f38d5a767126786aae7b90836f3c5",
".modelhub_state/outcome_checkpoint.json": "2ee2bb267b7a5bd5e15777478108edfcc5827d167515e82f22278b4803710306",
".modelhub_state/architecture_compatibility_blacklist.json": "38f01cd45b1c06db9ef8e27cef5b864c862f01e9da0f32741eb856eb997d502c",
".modelhub_state/architecture_history_backfill.json": "37a1560a48b15ba63fd7272642a16cda0d31fa34178833feb71b33fdbb7672b2",
".modelhub_state/market_intelligence.json": "c98cc66a49ded610460d3c582cf9c3181e8a104123d6e31eb6e21ed360a9af4a",
".modelhub_state/official_capabilities.json": "8066fd819a4a09625a44526b143794f74b183740002bd446f9227881e94a484b",
".modelhub_state/outcome_checkpoint.json": "c3d55235454323ea1dc5b0fca87fab66ce11f4b3f68611a64a756884ab63e50b",
".modelhub_state/queue_cleanup_latest.json": "51e7d1585319177976584ac9d97c18e02335e06fbd17bfdd6be748f1310ef4da",
".modelhub_state/recent_outcomes.jsonl": "c7fe62e24b287acede3bb2571da03d9fc34f18c85c0a2bf672ad3a61a0406a1e",
".modelhub_state/recovery_active_tasks.jsonl": "d436e0fac208ade3398b93fd1b44a135f81afbbd73293b077a6400060c67247e",
".modelhub_state/recovery_intents.jsonl": "4db58177df85fd0eedd6f4f82a2f6740a3a9447e23a245ab88bf14011f168aba",
".modelhub_state/recent_outcomes.jsonl": "3dc50edc255ec3d55d8f3484144800884371f3bc74293c58f6333aabd08c07c7",
".modelhub_state/recovery_active_tasks.jsonl": "de5af8261745fe56635cbc275792eed85a29bf647fa6322185be92a378dd542d",
".modelhub_state/recovery_intents.jsonl": "8b17ad7fcf866b2acd4713bb5a36c33f57eaa3ff29e6ab4c158ea8de3dfb1899",
".modelhub_state/routing_intelligence.json": "57d494a2e4eddd4b9e9c8d4c863ffdeac993f298b3445c58b1135209d55d3921",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "7f3726876c0c5222a8e1ca3e8ab4528365fd8f89767d375cd6631dd11fa0e740",
"outcomes/submissions.jsonl": "3764c1c7bee1eca08b25d4a461c06c5cd5cd633be686c4c099e76e0fd0e82a2e"
},
"generation": 6562,
"generation": 6563,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-13T05:57:34.790731+00:00",
"updatedAt": "2026-09-13T06:00:07.947548+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}