state: generation 7656 (cycle)

This commit is contained in:
2026-09-15 11:21:23 +00:00
parent b1b2688291
commit a83881a377
9 changed files with 2234 additions and 2233 deletions

View File

@@ -1593,7 +1593,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-15T11:18:28.838995+00:00",
"generatedAt": "2026-09-15T11:21:21.114127+00:00",
"summary": {
"activeBlockCount": 78,
"byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 556,
"listingErrors": 557,
"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": 8,
"nextAccountIndex": 9,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-15T11:18:28.812098+00:00",
"updatedAt": "2026-09-15T11:21:21.088067+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T11:16:42.068462+00:00",
"generatedAt": "2026-09-15T11:19:44.483456+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": "2026-09-15T11:10:08.509995+00:00",
"lastSyncTime": "2026-09-15T11:10:08.437202+00:00",
"generatedAt": "2026-09-15T11:19:29.889956+00:00",
"lastSyncTime": "2026-09-15T11:19:29.645035+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2310,10 +2310,10 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.975,
"decisionSuccessRate": 0.025,
"decisionTotal": 40,
"attributableFailureCount": 40,
"decisionFailureRate": 0.9756,
"decisionSuccessRate": 0.0244,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 42,
"backend_operator": 4,
@@ -2322,19 +2322,20 @@
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 84,
"failureRate": 0.9882,
"failureCount": 85,
"failureRate": 0.9884,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0118,
"successRate": 0.0116,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 85,
"total": 86,
"unresolvedFailureCount": 45
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2636,10 +2637,10 @@
"unresolvedFailureCount": 895
},
"vllm": {
"attributableFailureCount": 341,
"attributableFailureCount": 342,
"decisionFailureRate": 0.9799,
"decisionSuccessRate": 0.0201,
"decisionTotal": 348,
"decisionTotal": 349,
"failureBreakdown": {
"ambiguous_runtime": 218,
"backend_operator": 34,
@@ -2649,17 +2650,17 @@
"platform_infrastructure": 2,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 7,
"tokenizer_compatibility": 8,
"参数/模板问题": 30
},
"failureCount": 591,
"failureCount": 592,
"failureRate": 0.9883,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 7,
"successRate": 0.0117,
"total": 598,
"total": 599,
"unresolvedFailureCount": 248
},
"vllm-mlu": {
@@ -2768,7 +2769,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-15T11:10:08.505046+00:00",
"generatedAt": "2026-09-15T11:19:29.883876+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 40,
@@ -3005,10 +3006,10 @@
"unresolvedFailureCount": 77
},
"Mthreads_s4000": {
"attributableFailureCount": 40,
"decisionFailureRate": 0.9302,
"decisionSuccessRate": 0.0698,
"decisionTotal": 43,
"attributableFailureCount": 41,
"decisionFailureRate": 0.9318,
"decisionSuccessRate": 0.0682,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 42,
"backend_operator": 4,
@@ -3017,17 +3018,18 @@
"model_load": 3,
"repository_structure": 1,
"runtime_memory": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 118,
"failureRate": 0.9752,
"failureCount": 119,
"failureRate": 0.9754,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0248,
"total": 121,
"successRate": 0.0246,
"total": 122,
"unresolvedFailureCount": 78
},
"Sunrise_pt-200-x1": {
@@ -5861,14 +5863,14 @@
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 13,
"backend_operator": 1,
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 6,
"tokenizer_compatibility": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-15T10:50:55.652660+00:00",
"lastTerminalAt": "2026-09-15T11:19:29.645035+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -9462,13 +9464,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1918,
"totalRecords": 2012,
"terminalRecords": 1919,
"totalRecords": 2013,
"totals": {
"attributableFailureCount": 594,
"decisionFailureRate": 0.8973,
"decisionSuccessRate": 0.1027,
"decisionTotal": 662,
"attributableFailureCount": 595,
"decisionFailureRate": 0.8974,
"decisionSuccessRate": 0.1026,
"decisionTotal": 663,
"failureBreakdown": {
"ambiguous_runtime": 460,
"backend_operator": 44,
@@ -9478,18 +9480,18 @@
"platform_infrastructure": 7,
"repository_structure": 8,
"runtime_memory": 9,
"tokenizer_compatibility": 55,
"tokenizer_compatibility": 56,
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1850,
"failureRate": 0.9645,
"failureCount": 1851,
"failureRate": 0.9646,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 68,
"successRate": 0.0355,
"total": 1918,
"successRate": 0.0354,
"total": 1919,
"unresolvedFailureCount": 1249
},
"warnings": [
@@ -9528,6 +9530,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2012,
"summarizedRecords": 2013,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-15T11:19:29.645035+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T11:11:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4590790", "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": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-15T10:50:55.652660+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T10:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609103", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T10:23:01.246264+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T10:15:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590619", "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"], "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938151+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4594446", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T07:04:57.311825+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493601", "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": "2026-09-10T07:04:57.311794+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497056", "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": "2026-09-10T06:56:22.046014+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496936", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:56:22.046035+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477785", "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": "73c7057c8a2ccda5113b28214a842ce4ab143cad90c77370b023b2ecae303e2d",
".modelhub_state/architecture_history_backfill.json": "d9f0df896c9a611f787841dab6e4c6a4c8c3dfe1c71c0b4a3e1b7aeb1e6c1355",
".modelhub_state/market_intelligence.json": "1973fab4193d7c29e72c4b16dea10a71a1ca50591f0786ece47420dc7e3d64ac",
".modelhub_state/official_capabilities.json": "2a740b4dd5589217a58b296b793a713d5854c39a99d9275e3db9b1a5ad654b0e",
".modelhub_state/outcome_checkpoint.json": "94751bb1446c9a3acb1477836913214c5a937d26eb59bd4f2cd1c4b951d0d7cb",
".modelhub_state/architecture_compatibility_blacklist.json": "e7c41b745e4e25f35f7bb97c04ae933b0aaf3dbdae8ac712baf51f62b5582ebf",
".modelhub_state/architecture_history_backfill.json": "1381d764980429696d7a974923872932067345b7593a48c439a34ddd33821ea2",
".modelhub_state/market_intelligence.json": "c07cfe3646de5edeb1c3f42ecda1727758fb37a4f582c42220823c30be6d1347",
".modelhub_state/official_capabilities.json": "cd604f3a2216ec9c96bfe59869bb37977c2acf5912c7ecea4a41bdb338c45f6a",
".modelhub_state/outcome_checkpoint.json": "184b70c2b30804e954bbde239078d0c86cb45a5dd94fc17885c12ee67a9c18e2",
".modelhub_state/queue_cleanup_latest.json": "3e511035a77fe68d9f1adfb35e149ee220beed7c3962d87b7d1892cc816fb69a",
".modelhub_state/recent_outcomes.jsonl": "f66316bd3b5e52cf73f6211e203829454b3a7409d4e47e1dd1ecc67d4e3f1d50",
".modelhub_state/recovery_active_tasks.jsonl": "3961e84707914c4d28487005364a9fb0de2e27cd9a6999c099b59e8bb811ddca",
".modelhub_state/recovery_intents.jsonl": "7c8a32e9609ef9ea8781e3e8ea94bfbcbaa456b89f77460706f377ca61f5fda2",
".modelhub_state/recent_outcomes.jsonl": "e9d75bbd9406aa5dfeed5deb7a54b9084f346ae9a2c50574cfd73045774d0392",
".modelhub_state/recovery_active_tasks.jsonl": "0944f3e961a64959fcf7cce8a7c019d8b2fa207a22a7ae2ceb5fb1c8767a9a7c",
".modelhub_state/recovery_intents.jsonl": "2a0b9ccb81e52252b88e4a50d5924e2b60b64a797f9882a536d64d1ab3fd555c",
".modelhub_state/routing_intelligence.json": "5c8070320d5755aaf914efa600b2d376703dd44fa4a64fb6e2078f23011d8cb3",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "13fdcaaa093a350e18211faadff74ac2fe77d3b0636b1c71c071d0ace828b057",
"outcomes/submissions.jsonl": "f955d3a81ded4eebb56b12ff4444d628a996f63aa9bc8d3493758d203ceb1fe0"
},
"generation": 7655,
"generation": 7656,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-15T11:18:28.934983+00:00",
"updatedAt": "2026-09-15T11:21:23.213121+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
}