state: generation 5179 (cycle)
This commit is contained in:
@@ -1311,7 +1311,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T13:22:05.999294+00:00",
|
||||
"generatedAt": "2026-09-10T13:24:38.547044+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -75,7 +75,7 @@
|
||||
"7": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 368,
|
||||
"listingErrors": 369,
|
||||
"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": 7,
|
||||
"nextAccountIndex": 8,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-10T13:22:05.976049+00:00",
|
||||
"updatedAt": "2026-09-10T13:24:38.508764+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T13:19:52.717647+00:00",
|
||||
"generatedAt": "2026-09-10T13:23:12.883103+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T13:14:20.211520+00:00",
|
||||
"lastSyncTime": "2026-09-10T13:14:20.004672+00:00",
|
||||
"generatedAt": "2026-09-10T13:23:06.908779+00:00",
|
||||
"lastSyncTime": "2026-09-10T13:23:06.708419+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1545,24 +1545,24 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 21,
|
||||
"ambiguous_runtime": 22,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.9756,
|
||||
"failureCount": 81,
|
||||
"failureRate": 0.9759,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0244,
|
||||
"successRate": 0.0241,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 82,
|
||||
"unresolvedFailureCount": 60
|
||||
"total": 83,
|
||||
"unresolvedFailureCount": 61
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2296,7 +2296,7 @@
|
||||
"decisionSuccessRate": 0.2775,
|
||||
"decisionTotal": 173,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 115,
|
||||
"ambiguous_runtime": 116,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 88,
|
||||
"memory_capacity": 5,
|
||||
@@ -2305,15 +2305,15 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 969,
|
||||
"failureCount": 970,
|
||||
"failureRate": 0.9528,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0472,
|
||||
"total": 1017,
|
||||
"unresolvedFailureCount": 844
|
||||
"total": 1018,
|
||||
"unresolvedFailureCount": 845
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 236,
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T13:14:20.207683+00:00",
|
||||
"generatedAt": "2026-09-10T13:23:06.904847+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2523,21 +2523,21 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 21,
|
||||
"ambiguous_runtime": 22,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.9756,
|
||||
"failureCount": 81,
|
||||
"failureRate": 0.9759,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0244,
|
||||
"total": 82,
|
||||
"unresolvedFailureCount": 60
|
||||
"successRate": 0.0241,
|
||||
"total": 83,
|
||||
"unresolvedFailureCount": 61
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 17,
|
||||
@@ -4089,22 +4089,22 @@
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"ambiguous_runtime": 9,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T07:29:02.941680+00:00",
|
||||
"lastTerminalAt": "2026-09-10T13:23:06.708419+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4113,7 +4113,7 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 8
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -7053,15 +7053,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1589,
|
||||
"totalRecords": 1676,
|
||||
"terminalRecords": 1590,
|
||||
"totalRecords": 1677,
|
||||
"totals": {
|
||||
"attributableFailureCount": 415,
|
||||
"decisionFailureRate": 0.8906,
|
||||
"decisionSuccessRate": 0.1094,
|
||||
"decisionTotal": 466,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 349,
|
||||
"ambiguous_runtime": 350,
|
||||
"backend_operator": 35,
|
||||
"framework_architecture_unsupported": 272,
|
||||
"memory_capacity": 11,
|
||||
@@ -7073,21 +7073,21 @@
|
||||
"参数/模板问题": 98,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1538,
|
||||
"failureCount": 1539,
|
||||
"failureRate": 0.9679,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 51,
|
||||
"successRate": 0.0321,
|
||||
"total": 1589,
|
||||
"unresolvedFailureCount": 1120
|
||||
"total": 1590,
|
||||
"unresolvedFailureCount": 1121
|
||||
},
|
||||
"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。",
|
||||
@@ -7095,7 +7095,7 @@
|
||||
"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。",
|
||||
@@ -7116,6 +7116,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1676,
|
||||
"summarizedRecords": 1677,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"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": "2026-09-10T13:23:06.708419+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:19:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496965", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T12:40:42.405633+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523210", "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": "2026-09-10T12:32:29.847014+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:27:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477841", "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": "2026-09-10T12:23:25.501701+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:23:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471971", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"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": "2026-09-08T02:44:16.604726+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T02:41:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079153", "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": "2026-09-08T02:11:07.432317+00:00", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T02:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4133668", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T01:27:33.503535+00:00", "modelId": "poolside/Laguna-XS-2.1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T01:19:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609109", "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", "failureUnsupportedArchitectures": ["NemotronHForCausalLM"], "framework": "", "lastSyncTime": "2026-09-08T01:18:10.323644+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T01:13:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4470644", "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": "0bd5f1d10d8d8539b4bf793b80cd9edb5e97d8e9048bd9cab1ee04dd68756eaa",
|
||||
".modelhub_state/architecture_history_backfill.json": "e8cdcab6963ff76b97cf6646fe8e02a6e70309372985e6f66f8b2a30f4cc81a9",
|
||||
".modelhub_state/market_intelligence.json": "2df274c0b652ceba936c49d2302ca7a48e89020ced545f7d12572be226a08fe1",
|
||||
".modelhub_state/official_capabilities.json": "21f3f0d8aa70ac63cd4379fcaaa574da6fcdaff419cf1f533f1799f3d8503582",
|
||||
".modelhub_state/outcome_checkpoint.json": "e7467b80a2a8e560614728a9b8757b97eef839b1c3357d810224afe2480887ad",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "02f20bdca4f57fb564042bb462cec9268d7815afdd3517bf81d1e3c59d1a9ffe",
|
||||
".modelhub_state/architecture_history_backfill.json": "6e4365bdf647b8b03d27c86e8e456d0ffcce512e077364a0e70fee0b3b47884e",
|
||||
".modelhub_state/market_intelligence.json": "a3a20879d3b8044a1b5ad7d426fa1a89742c38a457cf043057950ec85fabad61",
|
||||
".modelhub_state/official_capabilities.json": "a6fbc9724e0ff845f3250fefa619adbbedcbf70aa5bf5b7934a0ab3263752e5f",
|
||||
".modelhub_state/outcome_checkpoint.json": "20e067764c2f423b2352eff7f7ca2d4131dd4f1ae47b97dee778e00d9dadb421",
|
||||
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
|
||||
".modelhub_state/recent_outcomes.jsonl": "4926726ca46245fe3094ee05784217df2651ab00c0c4c3db480dbc0c4ecb8840",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "0b7fbab3afdc0fd458cac322894fd45e65a4a0959640342c0a2a8a9bd1b049f4",
|
||||
".modelhub_state/recovery_intents.jsonl": "67e6370d1557d901f6f5941d30165b965bbb7ee7821f674eab4585f266d0a682",
|
||||
".modelhub_state/recent_outcomes.jsonl": "d506b0aed81c2b86f56bb1aa6793440e05c5910bcc528b31627be3f862960794",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "32c09cab905e420fcac4fa51794fc05dfdd52f0c1b60bd3378133ce586eeb1eb",
|
||||
".modelhub_state/recovery_intents.jsonl": "0c35c4de057b6765a37f09550017bb78117a99087b9d891e87bd62df8338ad83",
|
||||
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||
"ledger/submissions.jsonl": "8a621da5637d481c7de4b4e3375f2a68cbdabf71fe459244a727034f36ab3eb9",
|
||||
"outcomes/submissions.jsonl": "33a523dd7db393a02a7681136cc35548ede659d29e0cc83c7d8799eb0529cffb"
|
||||
},
|
||||
"generation": 5178,
|
||||
"generation": 5179,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T13:22:06.080716+00:00",
|
||||
"updatedAt": "2026-09-10T13:24:40.436705+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user