state: generation 5116 (cycle)

This commit is contained in:
2026-09-10 10:23:07 +00:00
parent 86a86715dc
commit ec4d4ff16f
9 changed files with 2195 additions and 2196 deletions

View File

@@ -1317,7 +1317,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T10:20:29.252611+00:00",
"generatedAt": "2026-09-10T10:23:07.203401+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 363,
"listingErrors": 364,
"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": 4,
"nextAccountIndex": 5,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T10:20:29.229056+00:00",
"updatedAt": "2026-09-10T10:23:07.179662+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T10:18:59.891436+00:00",
"generatedAt": "2026-09-10T10:21:37.044776+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": "2026-09-10T10:12:25.956598+00:00",
"lastSyncTime": "2026-09-10T10:12:25.704447+00:00",
"generatedAt": "2026-09-10T10:21:30.246957+00:00",
"lastSyncTime": "2026-09-10T10:21:30.006897+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2235,14 +2235,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 49,
"failureCount": 50,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2252,8 +2252,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 49,
"unresolvedFailureCount": 14
"total": 50,
"unresolvedFailureCount": 15
}
},
"frameworkSummaries": {
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"failureBreakdown": {
"ambiguous_runtime": 158,
"ambiguous_runtime": 159,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 415,
"failureCount": 416,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 416,
"unresolvedFailureCount": 179
"total": 417,
"unresolvedFailureCount": 180
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T10:12:25.950299+00:00",
"generatedAt": "2026-09-10T10:21:30.242348+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2754,7 +2754,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2763,15 +2763,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 89,
"failureCount": 90,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 89,
"unresolvedFailureCount": 51
"total": 90,
"unresolvedFailureCount": 52
}
},
"observedGpuMemoryGiB": {
@@ -4531,17 +4531,16 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 1,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
@@ -4553,7 +4552,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|unknown|text-generation": {
@@ -4687,16 +4686,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 6,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 19,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T09:47:33.262404+00:00",
"lastTerminalAt": "2026-09-10T10:21:30.006897+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4704,8 +4703,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 11
"total": 20,
"unresolvedFailureCount": 12
}
},
"recentProfileCombinationStats": {
@@ -7055,15 +7054,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1554,
"totalRecords": 1641,
"terminalRecords": 1555,
"totalRecords": 1642,
"totals": {
"attributableFailureCount": 405,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 456,
"failureBreakdown": {
"ambiguous_runtime": 328,
"ambiguous_runtime": 329,
"backend_operator": 34,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -7075,21 +7074,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1503,
"failureCount": 1504,
"failureRate": 0.9672,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0328,
"total": 1554,
"unresolvedFailureCount": 1096
"total": 1555,
"unresolvedFailureCount": 1097
},
"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。",
@@ -7097,7 +7096,7 @@
"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。",
@@ -7118,6 +7117,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1641,
"summarizedRecords": 1642,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-10T10:21:30.006897+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493599", "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, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T10:12:25.704447+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:11:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477783", "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": "2026-09-10T09:47:33.262404+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:47:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493608", "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, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T09:47:33.262382+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477720", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-07T21:05:55.523169+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:53:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4482387", "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, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:52:41.332062+00:00", "modelId": "kurakurai/Luth-LFM2-700M-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:51:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "3987175", "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": "2026-09-07T20:52:41.332106+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:51:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4478705", "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": "2026-09-07T20:52:41.332123+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:41:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4585069", "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": "692eb622f560fceaef332ef594a786fcbf21637287a6255e51b921a911ca9c82",
".modelhub_state/architecture_history_backfill.json": "1ce0eb0cf1b135fb9f5212a732b157bb51b0dc6ae0f569a048bb922b3d3a6370",
".modelhub_state/market_intelligence.json": "6eefd7c3c2cb70f13b322ff765a95d790fe89f8dd8727de8c418b342770a1e55",
".modelhub_state/official_capabilities.json": "f20bf984669271423b06c73b60d1b81457519a0a065dbeade7c3634eb9e6ea00",
".modelhub_state/outcome_checkpoint.json": "904a8312bd83cdeb54fb4211e6f66fc94ebecab6196b38521881cbed723cf5d1",
".modelhub_state/architecture_compatibility_blacklist.json": "3473ccc94bcc20543e2840d0a0edd8aff3a21f86b1a688da552a4992a62126c6",
".modelhub_state/architecture_history_backfill.json": "48f67d91352e38eb83852d27092f04ede6ee19a76960cbd1c29e16f1f8952eb1",
".modelhub_state/market_intelligence.json": "17effdc7a302799a84cc8aa57574f916a9454af6e9e468b0af1c3a6b0c244213",
".modelhub_state/official_capabilities.json": "adfd549f7bd050d8f1a1519792f820c8173c07116816a7919daa4d3d2f84438d",
".modelhub_state/outcome_checkpoint.json": "7af78e89a4dd04f488fd999ac52e38aa49161f0572a3ad54d3a3d74605587bd6",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "ad7d4dad969130d9fe9de98048755291976791298e5a8527f6c8b3ee38631c76",
".modelhub_state/recovery_active_tasks.jsonl": "266c14c3ca3fbe9d121a7bfe3817d45fb705d0d419e40b922367e7252b7a6a12",
".modelhub_state/recovery_intents.jsonl": "f93b35b075682d03f0b37cc12615110c69ffbf1950c11f5a88d10acb0de8a484",
".modelhub_state/recent_outcomes.jsonl": "7e513b1abbeafafb1c17473cbc96ead0e018a9df8443cdff0089e819b1cc96b9",
".modelhub_state/recovery_active_tasks.jsonl": "5da23f2a42cc8bf31c44ff8a2c0124e628c4089a3aa7592db43d8d52254d418c",
".modelhub_state/recovery_intents.jsonl": "09a5390b2a09c571ae0ec782dbd2fe997ac569a3ef7b0802e0371c37e0952ae9",
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "76cbabbced897a94b01593ff4cb86c58b9b0394b6c8fa89dd11a295e4678f70f",
"outcomes/submissions.jsonl": "7e7dceeb82e33a52f232d56ceba319292e0b24b25bc8ec08e03fa95367ce1163"
},
"generation": 5115,
"generation": 5116,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T10:20:29.327885+00:00",
"updatedAt": "2026-09-10T10:23:07.812798+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}