state: generation 5096 (cycle)

This commit is contained in:
2026-09-10 09:32:05 +00:00
parent 13f889cb2e
commit 5c10f11bf7
9 changed files with 2129 additions and 2127 deletions

View File

@@ -1317,7 +1317,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T09:28:55.478248+00:00",
"generatedAt": "2026-09-10T09:32:05.329723+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 361,
"listingErrors": 362,
"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": 10,
"nextAccountIndex": 11,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T09:28:55.448562+00:00",
"updatedAt": "2026-09-10T09:32:05.306046+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T09:26:58.124159+00:00",
"generatedAt": "2026-09-10T09:30:08.730108+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": "2026-09-10T09:20:50.642259+00:00",
"lastSyncTime": "2026-09-10T09:20:50.207436+00:00",
"generatedAt": "2026-09-10T09:29:58.731302+00:00",
"lastSyncTime": "2026-09-10T09:29:56.132283+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2001,20 +2001,20 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 31,
"attributableFailureCount": 32,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 31,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 3,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 2
},
"failureCount": 57,
"failureCount": 58,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2024,7 +2024,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 57,
"total": 58,
"unresolvedFailureCount": 26
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2320,13 +2320,13 @@
"unresolvedFailureCount": 844
},
"vllm": {
"attributableFailureCount": 234,
"decisionFailureRate": 0.9957,
"decisionSuccessRate": 0.0043,
"decisionTotal": 235,
"attributableFailureCount": 235,
"decisionFailureRate": 0.9958,
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"failureBreakdown": {
"ambiguous_runtime": 155,
"backend_operator": 28,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
"model_load": 18,
@@ -2336,14 +2336,14 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 411,
"failureCount": 412,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 412,
"total": 413,
"unresolvedFailureCount": 176
},
"vllm-mlu": {
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T09:20:50.635463+00:00",
"generatedAt": "2026-09-10T09:29:58.725727+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2678,13 +2678,13 @@
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
"attributableFailureCount": 32,
"decisionFailureRate": 0.9412,
"decisionSuccessRate": 0.0588,
"decisionTotal": 34,
"attributableFailureCount": 33,
"decisionFailureRate": 0.9429,
"decisionSuccessRate": 0.0571,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 3,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 3,
@@ -2693,14 +2693,14 @@
"参数/模板问题": 7,
"验证失败": 26
},
"failureCount": 91,
"failureRate": 0.9785,
"failureCount": 92,
"failureRate": 0.9787,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0215,
"total": 93,
"successRate": 0.0213,
"total": 94,
"unresolvedFailureCount": 59
},
"Sunrise_pt-200-x1": {
@@ -4257,11 +4257,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 4,
"backend_operator": 2,
"framework_architecture_unsupported": 2
},
"failureCount": 9,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4273,8 +4273,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 5
"total": 8,
"unresolvedFailureCount": 4
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
@@ -4429,24 +4429,24 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"backend_operator": 3,
"framework_architecture_unsupported": 1,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 12,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T08:45:45.454624+00:00",
"lastTerminalAt": "2026-09-10T09:29:56.132283+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4454,7 +4454,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 12,
"total": 13,
"unresolvedFailureCount": 7
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -6986,16 +6986,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1549,
"totalRecords": 1636,
"terminalRecords": 1550,
"totalRecords": 1637,
"totals": {
"attributableFailureCount": 404,
"decisionFailureRate": 0.8879,
"decisionSuccessRate": 0.1121,
"decisionTotal": 455,
"attributableFailureCount": 405,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 456,
"failureBreakdown": {
"ambiguous_runtime": 324,
"backend_operator": 33,
"backend_operator": 34,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
"model_load": 46,
@@ -7006,21 +7006,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1498,
"failureCount": 1499,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0329,
"total": 1549,
"total": 1550,
"unresolvedFailureCount": 1092
},
"warnings": [
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b3 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。",
"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。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7028,7 +7028,7 @@
"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 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 Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|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 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7049,6 +7049,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1636,
"summarizedRecords": 1637,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T09:29:56.132283+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:27:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532020", "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": "2026-09-10T09:20:50.207436+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:19:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505117", "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": "2026-09-10T09:20:50.207399+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610375", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T09:20:50.207423+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610372", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-07T20:39:52.300718+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:35:22+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4461773", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-07T20:39:52.300729+00:00", "modelId": "nightmedia/Gemma3-27B-it-vl-HERETIC-GLM4.7-2200x-cp515-q6-mlx", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-07T20:31:03+00:00", "targetGpu": "Vastai_va16", "taskId": "4079310", "taskType": "text-generation", "verifyResult": null}
{"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": "2026-09-07T20:06:50.393090+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:01:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458360", "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": "2026-09-07T19:45:42.406219+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T19:39:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4498542", "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": "8db8a92838c1c81f2b9c0592e4893178e09a47ee33ca5ddbfeaff0ba117cc627",
".modelhub_state/architecture_history_backfill.json": "9460a4d2a4ebc3911032d3caa02e555cf4b115d5d1abd7a01c2aa6c4376b531e",
".modelhub_state/market_intelligence.json": "05e667e04f42f13fc0f78dba5e265d039128a69713d5ea6b00bea55551cbc9e1",
".modelhub_state/official_capabilities.json": "d48e53dd12eae70dd1e78605f4c7b6cf1f4df42f5d4aee10b26a03712a08fb33",
".modelhub_state/outcome_checkpoint.json": "f315ceac1dbb6b6b923f7e117db4cfe0c30eeddf9fa85adc500a27ffbe283b27",
".modelhub_state/architecture_compatibility_blacklist.json": "6754601a50694430e11deaafa06b7fac0006c7653b2a586c7fa65343936049a0",
".modelhub_state/architecture_history_backfill.json": "b06047ce0d4d8b0ee697f06db88efc4a0bc6bbbed58ec06ef5aa9afee21f0c20",
".modelhub_state/market_intelligence.json": "cfbc4c1213bdf01950190363736a9bbdef638d3ce74dbe5c73720c1588874108",
".modelhub_state/official_capabilities.json": "dffc8ed88035da579394a9f2fd8269d726e1c242a19351e6036ebbe9cbb03489",
".modelhub_state/outcome_checkpoint.json": "8e0c38f4bc8fe459d11ab48dd65ae549aad6ffaefaca6056b84278d689c17930",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "f9963c20000f164f6b98cee10a1e169b3b276dfee771ab2ba1e2665771c04c71",
".modelhub_state/recovery_active_tasks.jsonl": "0c89a9e83990c2315c065c2e621543d52a5e30029f30f52694462765125bd6d4",
".modelhub_state/recovery_intents.jsonl": "980070abd42ebbd8cea9f778cb7a638ee06144b3e4e053e240020e6668cfdf31",
".modelhub_state/recent_outcomes.jsonl": "4615727b40655807f0c0dc71d7cf60aab6e60dddf766340249704ded6e957057",
".modelhub_state/recovery_active_tasks.jsonl": "e07a96d6e5f97e8253977a430357133061b5db0e674ffd5a17ddbe1fbb0384e0",
".modelhub_state/recovery_intents.jsonl": "c5b1f641cf3e47a5deac0436f1e15a755f6e555a949ae1d33940fe60e32ba316",
".modelhub_state/routing_intelligence.json": "8a52419d4402861a79d360da797632830eb2c915c1cd189832eea085096de774",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "1933ad805d1becf435394dbda5110270c499a0bd490635a19dc4240e65cfe8b1",
"outcomes/submissions.jsonl": "91fca38fede4537b5ee54c666edf87dc0a2de6ea7ea5ff03e2f533b115ba412e"
},
"generation": 5095,
"generation": 5096,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T09:28:55.554430+00:00",
"updatedAt": "2026-09-10T09:32:05.809466+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}