state: generation 5024 (cycle)
This commit is contained in:
@@ -1319,7 +1319,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T06:39:55.278288+00:00",
|
||||
"generatedAt": "2026-09-10T06:43:04.269491+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
"10": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 356,
|
||||
"listingErrors": 357,
|
||||
"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": "2026-09-10T06:39:55.254294+00:00",
|
||||
"updatedAt": "2026-09-10T06:43:04.245563+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T06:38:26.491647+00:00",
|
||||
"generatedAt": "2026-09-10T06:41:03.156607+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T06:33:34.530839+00:00",
|
||||
"lastSyncTime": "2026-09-10T06:33:34.200761+00:00",
|
||||
"generatedAt": "2026-09-10T06:40:56.332322+00:00",
|
||||
"lastSyncTime": "2026-09-10T06:40:56.094753+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1392,12 +1392,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 26,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 21,
|
||||
"ambiguous_runtime": 22,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 47,
|
||||
"failureCount": 48,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -1407,8 +1407,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 47,
|
||||
"unresolvedFailureCount": 21
|
||||
"total": 48,
|
||||
"unresolvedFailureCount": 22
|
||||
},
|
||||
"Ascend_910-b4|llamacpp|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -2327,7 +2327,7 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 230,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 146,
|
||||
"ambiguous_runtime": 147,
|
||||
"backend_operator": 24,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 6,
|
||||
@@ -2338,15 +2338,15 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 21
|
||||
},
|
||||
"failureCount": 398,
|
||||
"failureCount": 399,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 398,
|
||||
"unresolvedFailureCount": 167
|
||||
"total": 399,
|
||||
"unresolvedFailureCount": 168
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2449,7 +2449,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T06:33:34.524716+00:00",
|
||||
"generatedAt": "2026-09-10T06:40:56.328362+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2457,22 +2457,22 @@
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 27,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 21,
|
||||
"ambiguous_runtime": 22,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 8,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 82,
|
||||
"failureRate": 0.988,
|
||||
"failureCount": 83,
|
||||
"failureRate": 0.9881,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.012,
|
||||
"total": 83,
|
||||
"unresolvedFailureCount": 56
|
||||
"successRate": 0.0119,
|
||||
"total": 84,
|
||||
"unresolvedFailureCount": 57
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 38,
|
||||
@@ -3952,14 +3952,14 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15,
|
||||
"ambiguous_runtime": 16,
|
||||
"framework_architecture_unsupported": 3
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureCount": 19,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T06:33:34.200730+00:00",
|
||||
"lastTerminalAt": "2026-09-10T06:40:56.094753+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -3967,8 +3967,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 15
|
||||
"total": 19,
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Ascend_910-b4|llamacpp|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4648,12 +4648,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9,
|
||||
"ambiguous_runtime": 8,
|
||||
"framework_architecture_unsupported": 7,
|
||||
"model_load": 1,
|
||||
"repository_structure": 1
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4665,8 +4665,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 9
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 8
|
||||
}
|
||||
},
|
||||
"recentProfileCombinationStats": {
|
||||
@@ -6899,15 +6899,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1520,
|
||||
"totalRecords": 1607,
|
||||
"terminalRecords": 1521,
|
||||
"totalRecords": 1608,
|
||||
"totals": {
|
||||
"attributableFailureCount": 400,
|
||||
"decisionFailureRate": 0.8909,
|
||||
"decisionSuccessRate": 0.1091,
|
||||
"decisionTotal": 449,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 301,
|
||||
"ambiguous_runtime": 302,
|
||||
"backend_operator": 29,
|
||||
"framework_architecture_unsupported": 271,
|
||||
"memory_capacity": 11,
|
||||
@@ -6919,21 +6919,21 @@
|
||||
"参数/模板问题": 95,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1471,
|
||||
"failureCount": 1472,
|
||||
"failureRate": 0.9678,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 49,
|
||||
"successRate": 0.0322,
|
||||
"total": 1520,
|
||||
"unresolvedFailureCount": 1069
|
||||
"total": 1521,
|
||||
"unresolvedFailureCount": 1070
|
||||
},
|
||||
"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 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。",
|
||||
"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。",
|
||||
@@ -6941,7 +6941,7 @@
|
||||
"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 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 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。",
|
||||
@@ -6962,6 +6962,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1607,
|
||||
"summarizedRecords": 1608,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -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": "2026-09-10T06:40:56.094753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505108", "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": "2026-09-10T06:33:34.200730+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505109", "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": "2026-09-10T06:33:34.200752+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505107", "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": "2026-09-10T06:33:34.200761+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505106", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T12:50:24.741614+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T12:45:22+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4470643", "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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T12:50:24.741640+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T12:45:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4462837", "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_moe"], "framework": "", "lastSyncTime": "2026-09-07T12:14:36.308566+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T12:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4470641", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T12:14:36.308543+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T12:01:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4460364", "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
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "939963dec089f5624bda81bdca7089a93b6a26847b2563dba18c7580141602cb",
|
||||
".modelhub_state/architecture_history_backfill.json": "ebdc012a80aa6e1364b6a0c9101c75efa0945d171291843fe286a12b6ec65b4b",
|
||||
".modelhub_state/market_intelligence.json": "59aa9043f03f9baf514e7f821b8fea5acf037cfc3fd3238c4fdde839f2862e31",
|
||||
".modelhub_state/official_capabilities.json": "e522572295bed4e8c5adfe944d0fafd7b9e0a365f6f38bb5732cd0186a38f35f",
|
||||
".modelhub_state/outcome_checkpoint.json": "9348ed0af2bcfa4ee558c87d2128278ba3b25992a658427252d9fa84bcf3883c",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "9e2c67141591b22b2d35eccbfa047b6885547e2e339d47430237e3e4a37332fc",
|
||||
".modelhub_state/architecture_history_backfill.json": "f0c405d0b93bf4bd73070375ab48412303327707ab73cef8be07efd18efb084d",
|
||||
".modelhub_state/market_intelligence.json": "f54e3a06d5e2ad926187f9797e9c542c8e2a6cc8d77128c3486fc1709d21b68a",
|
||||
".modelhub_state/official_capabilities.json": "f466b8ec86314218b87cc5048b6837e139ef058ec7e85942a60a26d4249f0727",
|
||||
".modelhub_state/outcome_checkpoint.json": "461ecb7c11e26edcf456ae93ac56f1707941ab88a6e87accd58f1c2e6221cfb1",
|
||||
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
|
||||
".modelhub_state/recent_outcomes.jsonl": "80e4970dcb144210333764ba4d8f39c8f3a948957675abac1f97b17069b93c64",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "2f1014b497841f9c2c682ef1701d04979dad00f4412d70ce43a56f9ee3585795",
|
||||
".modelhub_state/recovery_intents.jsonl": "4e40f2d8efd2304355c9438c612a891f0a378a96cc187d47b14bf8005a10fa85",
|
||||
".modelhub_state/recent_outcomes.jsonl": "cf9f7eb487867d8a7db1763c12ce60d45c69e96098b7b6322fe453dd5ca49a01",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "6775576336705d6358d60c6af33ecf9f3f96ef86db61ef5331d3e53edcfe34cf",
|
||||
".modelhub_state/recovery_intents.jsonl": "36d721e8d825305a404b708ded0bbd36139b2e72bcc75910881e55c0259c3512",
|
||||
".modelhub_state/routing_intelligence.json": "104e6c843ba73c63c1de5e58af9c052e59aa75d2847951b582dce0b6b1b0055b",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||
"ledger/submissions.jsonl": "650d9438a6c4cd232ff238d2118575e335bb3d95c05fd31659dfc1d92791f6ab",
|
||||
"outcomes/submissions.jsonl": "cda89af250e6b80a8745acb90ff5274479336c8bacd9aad7694f63c3602486a8"
|
||||
},
|
||||
"generation": 5023,
|
||||
"generation": 5024,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T06:39:55.412711+00:00",
|
||||
"updatedAt": "2026-09-10T06:43:04.801604+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user