state: generation 6117 (cycle)

This commit is contained in:
2026-09-12 08:40:43 +00:00
parent 9d3cfed3ff
commit 89fbbdbe23
9 changed files with 2139 additions and 2141 deletions

View File

@@ -1364,7 +1364,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T08:37:56.356768+00:00",
"generatedAt": "2026-09-12T08:40:43.071394+00:00",
"summary": {
"activeBlockCount": 69,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 439,
"listingErrors": 440,
"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": "2026-09-12T08:37:56.333311+00:00",
"updatedAt": "2026-09-12T08:40:43.047075+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-12T08:23:38.889080+00:00",
"communityAttemptedAt": "2026-09-12T08:39:04.315696+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-12T08:23:38.889080+00:00",
"communityUpdatedAt": "2026-09-12T08:39:04.315696+00:00",
"frameworkAttemptedAt": "2026-09-12T08:18:06.149130+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T08:36:08.947769+00:00",
"generatedAt": "2026-09-12T08:39:04.315696+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": "2026-09-12T08:20:40.395370+00:00",
"lastSyncTime": "2026-09-12T08:20:40.114700+00:00",
"generatedAt": "2026-09-12T08:38:57.450801+00:00",
"lastSyncTime": "2026-09-12T08:38:57.213433+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1845,30 +1845,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 88,
"decisionFailureRate": 0.8713,
"decisionSuccessRate": 0.1287,
"decisionTotal": 101,
"attributableFailureCount": 89,
"decisionFailureRate": 0.8725,
"decisionSuccessRate": 0.1275,
"decisionTotal": 102,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 38,
"model_load": 39,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 157,
"failureRate": 0.9235,
"failureCount": 158,
"failureRate": 0.924,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 13,
"successRate": 0.0765,
"successRate": 0.076,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 170,
"total": 171,
"unresolvedFailureCount": 68
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2370,29 +2370,29 @@
"unresolvedFailureCount": 7
},
"unknown": {
"attributableFailureCount": 143,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 195,
"attributableFailureCount": 144,
"decisionFailureRate": 0.7347,
"decisionSuccessRate": 0.2653,
"decisionTotal": 196,
"failureBreakdown": {
"ambiguous_runtime": 131,
"backend_operator": 4,
"framework_architecture_unsupported": 91,
"memory_capacity": 5,
"model_load": 40,
"model_load": 41,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1007,
"failureCount": 1008,
"failureRate": 0.9509,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 52,
"successRate": 0.0491,
"total": 1059,
"total": 1060,
"unresolvedFailureCount": 863
},
"vllm": {
@@ -2524,7 +2524,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T08:20:40.389446+00:00",
"generatedAt": "2026-09-12T08:38:57.446440+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2688,27 +2688,27 @@
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 89,
"decisionFailureRate": 0.8725,
"decisionSuccessRate": 0.1275,
"decisionTotal": 102,
"attributableFailureCount": 90,
"decisionFailureRate": 0.8738,
"decisionSuccessRate": 0.1262,
"decisionTotal": 103,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 39,
"model_load": 40,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 158,
"failureRate": 0.924,
"failureCount": 159,
"failureRate": 0.9244,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 13,
"successRate": 0.076,
"total": 171,
"successRate": 0.0756,
"total": 172,
"unresolvedFailureCount": 68
},
"Kunlunxin_p-800": {
@@ -4464,7 +4464,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 0,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
@@ -4478,7 +4478,7 @@
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T08:20:40.114700+00:00",
"lastTerminalAt": "2026-09-12T08:38:57.213433+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7185,19 +7185,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1704,
"totalRecords": 1791,
"terminalRecords": 1705,
"totalRecords": 1792,
"totals": {
"attributableFailureCount": 470,
"decisionFailureRate": 0.8918,
"decisionSuccessRate": 0.1082,
"decisionTotal": 527,
"attributableFailureCount": 471,
"decisionFailureRate": 0.892,
"decisionSuccessRate": 0.108,
"decisionTotal": 528,
"failureBreakdown": {
"ambiguous_runtime": 399,
"backend_operator": 42,
"framework_architecture_unsupported": 288,
"memory_capacity": 11,
"model_load": 68,
"model_load": 69,
"platform_infrastructure": 4,
"repository_structure": 7,
"runtime_memory": 6,
@@ -7205,20 +7205,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1647,
"failureRate": 0.9665,
"failureCount": 1648,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0335,
"total": 1704,
"successRate": 0.0334,
"total": 1705,
"unresolvedFailureCount": 1173
},
"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。",
@@ -7227,7 +7228,6 @@
"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。",
@@ -7249,6 +7249,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1791,
"summarizedRecords": 1792,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-12T08:38:57.213433+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:35:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523313", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T08:20:40.114700+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T08:17:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523325", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T08:20:40.114654+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:13:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4547659", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T08:20:40.114686+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:13:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4543517", "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": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T18:12:11.499754+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460344", "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": "2026-09-08T18:12:11.499780+00:00", "modelId": "ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:03:22+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079264", "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": "2026-09-08T18:01:26.308083+00:00", "modelId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:59:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079094", "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"], "framework": "", "lastSyncTime": "2026-09-08T18:01:26.308040+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332979", "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": "caa5ae9114100d26a4200f3fbf8386502768945714272c401ddaeb3422cd836b",
".modelhub_state/architecture_history_backfill.json": "e81f70dc888dd23c181b463097de2f618a5147806653234ae6d0b115819c6a3c",
".modelhub_state/market_intelligence.json": "53ea51b1e4bd9f48b91461f54047c7772520ad7e6ad68ba4fa6aaccb67709906",
".modelhub_state/official_capabilities.json": "4c4a877d369cc1ea9314519f2e70f164ed00e171283660d0bd72f5f24805ac8e",
".modelhub_state/outcome_checkpoint.json": "a5dc9cac8991b10201f12637f1edb8fe9786c7cfdf981cdd767a7dd6a7b91678",
".modelhub_state/architecture_compatibility_blacklist.json": "f7cb874ac7a81d9f64b81d9afc5dd823d306cf678085961941ba1e0b43c7c613",
".modelhub_state/architecture_history_backfill.json": "06aeb045f64e96d2dbeef4bfe3fe043627e6a225f7c6d3f5f1f3b2c27c687116",
".modelhub_state/market_intelligence.json": "5891711c1106cba3be2e8cdafdc57feb29d5099b8577e0b808ca845510cd932d",
".modelhub_state/official_capabilities.json": "497a065c486377a535c2ad68d1e1432b61708693530bbfaeb000c1ccd6c5d747",
".modelhub_state/outcome_checkpoint.json": "0301d9b6ae8c111fa305d5cd714b6aa24d7d328685b2ddcfcca91f1138936b92",
".modelhub_state/queue_cleanup_latest.json": "6b05059de615759adb561da08f7e955c6aa7fc0a1781227efab19cf90b539800",
".modelhub_state/recent_outcomes.jsonl": "cfdcd0e9bc9f527b3b588626bc095af3cae843540c64cafc7dd4f2889cc4fcda",
".modelhub_state/recovery_active_tasks.jsonl": "eec75ad9186294d063d8b27dfbd6c8af67e88a9ad4fb011b1844c3782f3c3dd1",
".modelhub_state/recovery_intents.jsonl": "a02ad9ea8e894a7fb36157f7dc75ede0195a4450db67d7cbf260e36ffb98f4e3",
".modelhub_state/recent_outcomes.jsonl": "0180d194ddedf10c4e9724a8ad99d82e6854367871f30372bd8bb2b2e95a1aeb",
".modelhub_state/recovery_active_tasks.jsonl": "08ceefbde337e52cf68e3aec282b1294853f8fda41683fe0f78ddee27bf11eca",
".modelhub_state/recovery_intents.jsonl": "367d7710a43d0c4a739a7064cd3086a44d24e243ba34f50b6aa9f79ec7871a43",
".modelhub_state/routing_intelligence.json": "2855b5a64db2097d238c63bc8e3c9527429b37e5743e8c4067b04a47b96bf6d5",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "fce27fb2f360720694402834960f8bd72b07cc9cdb7df41af2ff877c48deb61a",
"outcomes/submissions.jsonl": "c1fb4ffb5f8805609635341d14f8a0d312d7065898c795a6d23cb2b73c0d9814"
},
"generation": 6116,
"generation": 6117,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T08:37:56.516641+00:00",
"updatedAt": "2026-09-12T08:40:43.668324+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}