state: generation 6153 (cycle)

This commit is contained in:
2026-09-12 10:32:23 +00:00
parent 784f8429c1
commit 30cfe60018
9 changed files with 2145 additions and 2144 deletions

View File

@@ -1362,7 +1362,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T10:29:25.947320+00:00",
"generatedAt": "2026-09-12T10:32:22.071812+00:00",
"summary": {
"activeBlockCount": 69,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 442,
"listingErrors": 443,
"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": "2026-09-12T10:29:25.922832+00:00",
"updatedAt": "2026-09-12T10:32:22.047481+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T10:27:20.381757+00:00",
"generatedAt": "2026-09-12T10:30:34.087149+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": "2026-09-12T10:03:18.715055+00:00",
"lastSyncTime": "2026-09-12T10:03:18.508491+00:00",
"generatedAt": "2026-09-12T10:30:27.281504+00:00",
"lastSyncTime": "2026-09-12T10:30:27.007152+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1543,30 +1543,30 @@
"unresolvedFailureCount": 35
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 27,
"decisionFailureRate": 0.9643,
"decisionSuccessRate": 0.0357,
"decisionTotal": 28,
"attributableFailureCount": 28,
"decisionFailureRate": 0.9655,
"decisionSuccessRate": 0.0345,
"decisionTotal": 29,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 4,
"framework_architecture_unsupported": 19,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"model_load": 2,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 80,
"failureRate": 0.9877,
"failureCount": 81,
"failureRate": 0.9878,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0123,
"successRate": 0.0122,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 81,
"total": 82,
"unresolvedFailureCount": 53
},
"Biren_166m|vllm|text-generation": {
@@ -2369,14 +2369,14 @@
"unresolvedFailureCount": 7
},
"unknown": {
"attributableFailureCount": 145,
"decisionFailureRate": 0.736,
"decisionSuccessRate": 0.264,
"decisionTotal": 197,
"attributableFailureCount": 146,
"decisionFailureRate": 0.7374,
"decisionSuccessRate": 0.2626,
"decisionTotal": 198,
"failureBreakdown": {
"ambiguous_runtime": 133,
"backend_operator": 4,
"framework_architecture_unsupported": 91,
"framework_architecture_unsupported": 92,
"memory_capacity": 5,
"model_load": 42,
"platform_infrastructure": 1,
@@ -2384,14 +2384,14 @@
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1011,
"failureCount": 1012,
"failureRate": 0.9511,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 52,
"successRate": 0.0489,
"total": 1063,
"total": 1064,
"unresolvedFailureCount": 865
},
"vllm": {
@@ -2523,7 +2523,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T10:03:18.711009+00:00",
"generatedAt": "2026-09-12T10:30:27.276834+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2574,27 +2574,27 @@
"unresolvedFailureCount": 223
},
"Biren_166m": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.9655,
"decisionSuccessRate": 0.0345,
"decisionTotal": 29,
"attributableFailureCount": 29,
"decisionFailureRate": 0.9667,
"decisionSuccessRate": 0.0333,
"decisionTotal": 30,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 4,
"framework_architecture_unsupported": 19,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"model_load": 3,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 81,
"failureRate": 0.9878,
"failureCount": 82,
"failureRate": 0.988,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0122,
"total": 82,
"successRate": 0.012,
"total": 83,
"unresolvedFailureCount": 53
},
"Cambricon_mlu-370-x4": {
@@ -4305,23 +4305,23 @@
"unresolvedFailureCount": 17
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 9,
"backend_operator": 4,
"framework_architecture_unsupported": 2,
"framework_architecture_unsupported": 3,
"model_load": 1
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T07:44:40.913717+00:00",
"lastTerminalAt": "2026-09-12T10:30:27.007152+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4329,7 +4329,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 16,
"total": 17,
"unresolvedFailureCount": 9
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -7187,17 +7187,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1713,
"totalRecords": 1800,
"terminalRecords": 1714,
"totalRecords": 1801,
"totals": {
"attributableFailureCount": 476,
"decisionFailureRate": 0.8931,
"decisionSuccessRate": 0.1069,
"decisionTotal": 533,
"attributableFailureCount": 477,
"decisionFailureRate": 0.8933,
"decisionSuccessRate": 0.1067,
"decisionTotal": 534,
"failureBreakdown": {
"ambiguous_runtime": 402,
"backend_operator": 42,
"framework_architecture_unsupported": 291,
"framework_architecture_unsupported": 292,
"memory_capacity": 11,
"model_load": 70,
"platform_infrastructure": 4,
@@ -7207,20 +7207,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1656,
"failureCount": 1657,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0333,
"total": 1713,
"total": 1714,
"unresolvedFailureCount": 1176
},
"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。",
@@ -7229,7 +7230,6 @@
"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。",
@@ -7251,6 +7251,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1800,
"summarizedRecords": 1801,
"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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-12T10:30:27.007152+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T10:25:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610388", "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": "2026-09-12T10:03:18.508491+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T10:01:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4543481", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T09:54:24.312986+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T09:53:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505132", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-12T09:44:49.014208+00:00", "modelId": "AI-ModelScope/bitnet-b1.58-2B-4T-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T09:43:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079172", "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": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T20:58:55.412694+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T20:51:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610344", "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": "2026-09-08T20:08:17.704972+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T20:01:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079396", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-08T19:31:22.799826+00:00", "modelId": "RWKV/rwkv-5-world-1b5", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T19:23:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4107006", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T19:23:02.305839+00:00", "modelId": "zenlm/zen-guard-gen", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T19:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080142", "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": "864e1cc32103a7821d37797ebbec072d45fe9f1f673f5bbf5108a638a608c456",
".modelhub_state/architecture_history_backfill.json": "01e7fcefd17c1d726188ebaecf1eb46fcda29c3a01208a293e49795b1e30a3f0",
".modelhub_state/market_intelligence.json": "c38189309b047936da0e912a771f3506d423ecd835e3c468014d66b1acec0895",
".modelhub_state/official_capabilities.json": "13b721cd28494a656e981f7178093deb75d2317889972ef8ea60160f8d8caeba",
".modelhub_state/outcome_checkpoint.json": "b124ea72f5dfff8e43fbd02aa9d1f3122110cac5cdfd12ed133414e1cb35ca76",
".modelhub_state/architecture_compatibility_blacklist.json": "34e6cdf1d5d3ef8e9cd788ea2356de5279a65a04bfb178497856280263c78621",
".modelhub_state/architecture_history_backfill.json": "cc36568816e50e2bc39df7dd80f2dddaecdaddca188726c9fe293e2965d2a5ad",
".modelhub_state/market_intelligence.json": "fccd4dcc8f5f07828e7ef3691666092e37757579583aea17e5e13ec5e8b02e75",
".modelhub_state/official_capabilities.json": "09398826e08edda78451fbf14fb762eb202b4f2ea12ea908238cc9916091f7e9",
".modelhub_state/outcome_checkpoint.json": "9e8e18dfc7e113ed852865d432b1a04a168a77d030aa4a50d387ce0bb00c3b41",
".modelhub_state/queue_cleanup_latest.json": "6b05059de615759adb561da08f7e955c6aa7fc0a1781227efab19cf90b539800",
".modelhub_state/recent_outcomes.jsonl": "dd88a8bc4c0106712997be0a10b3e00a0dee335d9295bc8bd74503ad76f8028f",
".modelhub_state/recovery_active_tasks.jsonl": "14263bf22cee2905472f8e93257747cd0de8330d16e28763b6741a273bbf7fc8",
".modelhub_state/recovery_intents.jsonl": "23deea019b240d587a104780ee7d3b1fd2340061de7da894cdf760492e450b42",
".modelhub_state/recent_outcomes.jsonl": "15cef55624658da5c4609eb92ff9728dbd9dc5fbd13096fd23cb98a864940163",
".modelhub_state/recovery_active_tasks.jsonl": "e466c03cbe81c7bf2ac8525ee07c1780ddfd122d2534ec3fa78caad175cef455",
".modelhub_state/recovery_intents.jsonl": "0a05e0cca9318b8a18f852b05ccf8bd32acfe6a44cd7a18d312d0009e1f35072",
".modelhub_state/routing_intelligence.json": "2855b5a64db2097d238c63bc8e3c9527429b37e5743e8c4067b04a47b96bf6d5",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "df27564b0b2b4c4fa44eda1b2baff32c06f3dd25b37d584a26ab3a3bc0ba376d",
"outcomes/submissions.jsonl": "892192d739c93273dcd9bffabf99eb294c894fbe85a73a14b6767503e7de4cdc"
},
"generation": 6152,
"generation": 6153,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T10:29:26.034213+00:00",
"updatedAt": "2026-09-12T10:32:23.572010+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}