state: generation 4824 (cycle)

This commit is contained in:
2026-09-09 22:59:26 +00:00
parent 612ba7f8e7
commit 16f8a15fb6
9 changed files with 2169 additions and 2172 deletions

View File

@@ -1312,7 +1312,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-09T22:56:38.022432+00:00",
"generatedAt": "2026-09-09T22:59:25.624874+00:00",
"summary": {
"activeBlockCount": 65,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 342,
"listingErrors": 343,
"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": "2026-09-09T22:56:37.999237+00:00",
"updatedAt": "2026-09-09T22:59:25.602380+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-09T22:55:11.835101+00:00",
"generatedAt": "2026-09-09T22:57:45.114310+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": "2026-09-09T22:49:15.615221+00:00",
"lastSyncTime": "2026-09-09T22:49:15.213972+00:00",
"generatedAt": "2026-09-09T22:57:39.050446+00:00",
"lastSyncTime": "2026-09-09T22:57:38.803923+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1473,13 +1473,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 20,
"ambiguous_runtime": 21,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 57,
"failureCount": 58,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1489,8 +1489,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 57,
"unresolvedFailureCount": 20
"total": 58,
"unresolvedFailureCount": 21
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 24,
@@ -2320,7 +2320,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 225,
"failureBreakdown": {
"ambiguous_runtime": 118,
"ambiguous_runtime": 119,
"backend_operator": 20,
"framework_architecture_unsupported": 168,
"memory_capacity": 6,
@@ -2331,15 +2331,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 365,
"failureCount": 366,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 365,
"unresolvedFailureCount": 139
"total": 366,
"unresolvedFailureCount": 140
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2442,7 +2442,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-09T22:49:15.610998+00:00",
"generatedAt": "2026-09-09T22:57:39.045225+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2473,7 +2473,7 @@
"decisionSuccessRate": 0.05,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 21,
"ambiguous_runtime": 22,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 1,
@@ -2482,15 +2482,15 @@
"参数/模板问题": 11,
"验证失败": 175
},
"failureCount": 245,
"failureCount": 246,
"failureRate": 0.9919,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0081,
"total": 247,
"unresolvedFailureCount": 207
"total": 248,
"unresolvedFailureCount": 208
},
"Biren_166m": {
"attributableFailureCount": 25,
@@ -3966,21 +3966,21 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 12
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 11
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T22:49:15.213951+00:00",
"lastTerminalAt": "2026-09-09T22:57:38.803923+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -3989,7 +3989,7 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 8
"unresolvedFailureCount": 9
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -4432,18 +4432,18 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"attributableFailureCount": 10,
"consecutiveFailures": 10,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 11,
"decisionTotal": 10,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 10
"tokenizer_compatibility": 9
},
"failureCount": 12,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
@@ -4455,7 +4455,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 12,
"total": 11,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -6678,15 +6678,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1456,
"totalRecords": 1540,
"terminalRecords": 1457,
"totalRecords": 1541,
"totals": {
"attributableFailureCount": 388,
"decisionFailureRate": 0.8899,
"decisionSuccessRate": 0.1101,
"decisionTotal": 436,
"failureBreakdown": {
"ambiguous_runtime": 251,
"ambiguous_runtime": 252,
"backend_operator": 23,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
@@ -6698,21 +6698,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1408,
"failureRate": 0.967,
"failureCount": 1409,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.033,
"total": 1456,
"unresolvedFailureCount": 1018
"successRate": 0.0329,
"total": 1457,
"unresolvedFailureCount": 1019
},
"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。",
@@ -6720,7 +6720,7 @@
"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。",
@@ -6741,6 +6741,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1540,
"summarizedRecords": 1541,
"version": 1
}

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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T22:57:38.803923+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:49:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471911", "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": "2026-09-09T22:49:15.213951+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:47:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471912", "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": "2026-09-09T22:49:15.213972+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:47:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471906", "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": "2026-09-09T22:06:26.296264+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:01:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493490", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T04:58:15.193678+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-bf16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-06T20:59:59.616196+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678098", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-06T20:32:42.310571+00:00", "modelId": "RedHatAI/Llama-3.2-1B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-06T20:29:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609073", "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_mtp"], "framework": "vllm", "lastSyncTime": "2026-09-06T17:05:15.231365+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-06T17:03:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609075", "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_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T16:39:46.911859+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Qwen-1.5B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-06T16:37:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107037", "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": "e3713c18cc36a151978e7676953ae6026600f8a0e1f3e153590d061030e62adc",
".modelhub_state/architecture_history_backfill.json": "6cb762bb82879716bd56667d70580f35a1faf23691f260207d3f512ed585af2f",
".modelhub_state/market_intelligence.json": "2f95dd818e882942e931dd8565361659fc37759f3e80d59931d8321b17c70b45",
".modelhub_state/official_capabilities.json": "dee8342012522682494cf6324cb2d1979ad02f6065eca463bef943d62d239b9c",
".modelhub_state/outcome_checkpoint.json": "bbe55c729e4a340436db42c63de701ccdcc939fdb6de2977c22f83fc4705f91f",
".modelhub_state/architecture_compatibility_blacklist.json": "c3b1912c41853b0c075499313e7117f506d195bd77b434fde3ac1cd57e27bb74",
".modelhub_state/architecture_history_backfill.json": "d54d0d3c36e61430d28c477059b657253879bc1d7e66f26f81257a85216cab53",
".modelhub_state/market_intelligence.json": "da45f9f58cf9675626c7b0a375fd6320dfbb840adc17eafbf4a6da1d20540b97",
".modelhub_state/official_capabilities.json": "11775c4814e79c91ca26e0a026aaf575c135e4d3e8640de3530fdbbc60a4bc25",
".modelhub_state/outcome_checkpoint.json": "65e98bef07ed6f06542684b81ead8e7f4273b227e7048da2d6590f7b8896cc60",
".modelhub_state/queue_cleanup_latest.json": "9a11c448074d1c105fe90e48fb81cfc27bce5e7e08d76397232f05c4c9432a32",
".modelhub_state/recent_outcomes.jsonl": "944207f7dee4d9c95fcebdb59ceadfb36d135122f20bb4910e1c3eb6d1e9ed07",
".modelhub_state/recovery_active_tasks.jsonl": "daf45aa89be21339d8215b1f21cc3bd5e806623ae75eaf8ceb673f256164e053",
".modelhub_state/recovery_intents.jsonl": "543eba50a16cb151bbf2015fee1bab48d72bb92775dccb6016038d024ba1dcf8",
".modelhub_state/recent_outcomes.jsonl": "13c54a0d397b7760fc9622a20cde1b7e5cdf794fc19cb920d3bc83e9da7fc259",
".modelhub_state/recovery_active_tasks.jsonl": "1fa1bc5cd73ae1168b41c9dc2d5bfee6c0adcf6d7ac8891e15b50f22a19499f4",
".modelhub_state/recovery_intents.jsonl": "0a383bbcf1305f55cb2f2c238768770f9bd38afcc460e6faf232f295ddc39d80",
".modelhub_state/routing_intelligence.json": "4effdc96741bb83e9319ea4665226a7e2442dc48c76af38dae47ff1343260b42",
".modelhub_state/submission_exclusions.jsonl": "363b21d9f5526f9b072e4f5ff55cc1ff126e844da64fb08a7b6e4d09b2559cdb",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "877ac486271d5afd91db3f6b8aee973a960a405d6789142e0a8e03758d9691ba",
"outcomes/submissions.jsonl": "e579fb8d5b700e664329c0f65817d051df1dceeddea02016efd539c927b19ab3"
},
"generation": 4823,
"generation": 4824,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-09T22:56:38.085998+00:00",
"updatedAt": "2026-09-09T22:59:26.312910+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}