state: generation 6105 (cycle)

This commit is contained in:
2026-09-12 08:04:43 +00:00
parent ea85bf82de
commit 7652510713
10 changed files with 2074 additions and 2054 deletions

View File

@@ -1364,7 +1364,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T08:01:47.522476+00:00",
"generatedAt": "2026-09-12T08:04:43.109788+00:00",
"summary": {
"activeBlockCount": 69,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 438,
"listingErrors": 439,
"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": "2026-09-12T08:01:47.499420+00:00",
"updatedAt": "2026-09-12T08:04:43.082766+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T07:59:30.392606+00:00",
"generatedAt": "2026-09-12T08:03:11.372790+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": "2026-09-12T07:44:41.124320+00:00",
"lastSyncTime": "2026-09-12T07:44:40.913717+00:00",
"generatedAt": "2026-09-12T08:02:48.741178+00:00",
"lastSyncTime": "2026-09-12T08:02:48.507658+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1623,25 +1623,25 @@
"decisionSuccessRate": 0.2222,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 19,
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 5,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 5,
"验证失败": 22
},
"failureCount": 53,
"failureRate": 0.9636,
"failureCount": 54,
"failureRate": 0.9643,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0364,
"successRate": 0.0357,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 55,
"unresolvedFailureCount": 46
"total": 56,
"unresolvedFailureCount": 47
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 7,
@@ -2375,7 +2375,7 @@
"decisionSuccessRate": 0.2629,
"decisionTotal": 194,
"failureBreakdown": {
"ambiguous_runtime": 130,
"ambiguous_runtime": 131,
"backend_operator": 4,
"framework_architecture_unsupported": 91,
"memory_capacity": 5,
@@ -2385,15 +2385,15 @@
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1006,
"failureCount": 1007,
"failureRate": 0.9518,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 51,
"successRate": 0.0482,
"total": 1057,
"unresolvedFailureCount": 862
"total": 1058,
"unresolvedFailureCount": 863
},
"vllm": {
"attributableFailureCount": 260,
@@ -2524,7 +2524,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T07:44:41.120022+00:00",
"generatedAt": "2026-09-12T08:02:48.736149+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2626,22 +2626,22 @@
"decisionSuccessRate": 0.1053,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 38,
"ambiguous_runtime": 39,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 95,
"failureRate": 0.9794,
"failureCount": 96,
"failureRate": 0.9796,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0206,
"total": 97,
"unresolvedFailureCount": 78
"successRate": 0.0204,
"total": 98,
"unresolvedFailureCount": 79
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -4365,14 +4365,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 15,
"tokenizer_compatibility": 1
},
"failureCount": 15,
"failureCount": 16,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T08:19:33.742658+00:00",
"lastTerminalAt": "2026-09-12T08:02:48.507658+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4380,8 +4380,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 14
"total": 16,
"unresolvedFailureCount": 15
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -4771,20 +4771,20 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 2,
"model_load": 1,
"repository_structure": 2,
"runtime_memory": 1
},
"failureCount": 19,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4796,7 +4796,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 19,
"total": 18,
"unresolvedFailureCount": 12
}
},
@@ -7185,15 +7185,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1698,
"totalRecords": 1785,
"terminalRecords": 1699,
"totalRecords": 1786,
"totals": {
"attributableFailureCount": 467,
"decisionFailureRate": 0.8929,
"decisionSuccessRate": 0.1071,
"decisionTotal": 523,
"failureBreakdown": {
"ambiguous_runtime": 397,
"ambiguous_runtime": 398,
"backend_operator": 41,
"framework_architecture_unsupported": 286,
"memory_capacity": 11,
@@ -7205,21 +7205,20 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1642,
"failureCount": 1643,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.033,
"total": 1698,
"unresolvedFailureCount": 1171
"total": 1699,
"unresolvedFailureCount": 1172
},
"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。",
@@ -7228,6 +7227,7 @@
"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。",
@@ -7249,6 +7249,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1785,
"summarizedRecords": 1786,
"version": 1
}

View File

@@ -14,7 +14,7 @@
100
],
"accounts": 12,
"activeScanned": 1050,
"activeScanned": 1048,
"ageCleanupMode": "admission_only",
"agePolicySkipped": {
"cleanupDisabled": true,
@@ -32,6 +32,16 @@
"vllm",
"vllm_tokenizer_patch"
],
"biren_166m|text-generation": [
"vllm",
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"cambricon_mlu-370-x4|text-generation": [
"vllm",
"vllm-customized",
"vllm-mlu"
],
"cambricon_mlu-370-x8|text-generation": [
"vllm",
"vllm-customized",
@@ -50,6 +60,15 @@
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"iluvatar_mrv-100|text-generation": [
"transformers",
"vllm"
],
"kunlunxin_p-800|text-generation": [
"vllm",
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"metax_c-500|text-generation": [
"vllm"
],
@@ -95,13 +114,13 @@
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
},
"architectureModelConfigsComplete": 106,
"architectureOnly": true,
"architectureOnly": false,
"architecturePolicySkipped": {
"frameworkCatalogUnknown": 86,
"frameworkContextUnknown": 323,
"frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 320,
"modelArchitectureUnknown": 150,
"noMatchingBlock": 717,
"partiallyBlockedFrameworkSet": 97,
"noMatchingBlock": 803,
"partiallyBlockedFrameworkSet": 95,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
"submissionContextUnknown": 0
@@ -140,12 +159,14 @@
"policyNoLongerAppliesTasks": [],
"recentModelDays": 7,
"recentModelReserveSlots": 5,
"repositorySizeErrors": {},
"repositorySizesComplete": 0,
"repositorySizeErrors": {
"empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
},
"repositorySizesComplete": 247,
"skipped": {
"fitsKnownCapacity": 0,
"fitsKnownCapacity": 1046,
"gpuCapacityUnknown": 0,
"repositorySizeUnknown": 0
"repositorySizeUnknown": 2
},
"stopErrors": [],
"uniqueModels": 248

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-12T08:02:48.507658+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T07:53:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4549467", "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": "2026-09-12T07:44:40.913717+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T07:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610364", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T07:35:30.412992+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T07:33:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4547660", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T06:59:46.603354+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079259", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-08T17:33:37.506903+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B-IT", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-08T17:33:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4133741", "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": "2026-09-08T17:33:37.506924+00:00", "modelId": "amd/Phi-3.5-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079902", "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": "2026-09-08T17:33:37.506936+00:00", "modelId": "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079101", "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": "2026-09-08T17:15:48.506951+00:00", "modelId": "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080076", "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": "32580b186f2677be574d25aa588f01c6715b0cf207ae6079d7ece4e4b994db52",
".modelhub_state/architecture_history_backfill.json": "a875b7e2bfa4e96c7c8fdf66dd49d3a197a48b83ccbcc0aa3820bb01671e9d05",
".modelhub_state/market_intelligence.json": "a130b8043e39917552faef15d0173cd257a06dc2599c175d784cfcc5011c2eea",
".modelhub_state/official_capabilities.json": "cf41fe068af83c7b62608343f75ed2079fdd6ccaa05ad8a7e764bffb1196889b",
".modelhub_state/outcome_checkpoint.json": "58120d7a2d7f554080f2a652045ef3450521d93c37a5553c8e8a6543a6318680",
".modelhub_state/queue_cleanup_latest.json": "90e4dcfb9592532e113083f4f6101f91569aa480a0f7e2747a042a0aba314e96",
".modelhub_state/recent_outcomes.jsonl": "f3cc5d8f9057e0a9d8465ae9c98a3e559877190100f5af0bb2557b81f37f95fd",
".modelhub_state/recovery_active_tasks.jsonl": "d1d0c450993b482d60c3f9848d47e1bf9c45e67140c5f404c6508740b4d475c9",
".modelhub_state/recovery_intents.jsonl": "4f90c7a83d7aa924394a6b5f72794555bcd1ff2d159b8a135fc85bfe0d7ae79a",
".modelhub_state/architecture_compatibility_blacklist.json": "33a97ae5b47ee83c1dc5ea10528f17c3b001999d42914726aae5dedd4a0a9dc7",
".modelhub_state/architecture_history_backfill.json": "de3672479d0527b445ac83aa9417d4b282139734e43b5a7b3d95fadb62f2a14a",
".modelhub_state/market_intelligence.json": "2fa2cef62ab6ddc117f6ef44f18cdec0b6ba4610e22988fa79a2a3ab2f0f88e7",
".modelhub_state/official_capabilities.json": "a609cdf78e850b88afd6ad40753ff72234145d5591cd785ac9b68e25a1e32c3b",
".modelhub_state/outcome_checkpoint.json": "4f9c7d432ca4e8634c57ba21158551ae31511510888e79e1ca351dfefaec882e",
".modelhub_state/queue_cleanup_latest.json": "6b05059de615759adb561da08f7e955c6aa7fc0a1781227efab19cf90b539800",
".modelhub_state/recent_outcomes.jsonl": "cafdf2ca6da63d9768b0718ec93cfed6bbfae43a32ed15af04f52bf50a9c091a",
".modelhub_state/recovery_active_tasks.jsonl": "c6395f7d9cc2f617f064fa5ed347a42e7ff9029d1f7f4e8cce86c1453cfb4674",
".modelhub_state/recovery_intents.jsonl": "a909c174c14be65d4edac27c8b0babea28920f33afc67e58b3bb283de810e9f6",
".modelhub_state/routing_intelligence.json": "2855b5a64db2097d238c63bc8e3c9527429b37e5743e8c4067b04a47b96bf6d5",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "fce27fb2f360720694402834960f8bd72b07cc9cdb7df41af2ff877c48deb61a",
"outcomes/submissions.jsonl": "c1fb4ffb5f8805609635341d14f8a0d312d7065898c795a6d23cb2b73c0d9814"
},
"generation": 6104,
"generation": 6105,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T08:01:47.614736+00:00",
"updatedAt": "2026-09-12T08:04:43.655235+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}