state: generation 6129 (cycle)

This commit is contained in:
2026-09-12 09:18:26 +00:00
parent c582860117
commit 14ca77cd94
9 changed files with 2132 additions and 2132 deletions

View File

@@ -1362,7 +1362,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T09:15:12.557800+00:00",
"generatedAt": "2026-09-12T09:18:25.734521+00:00",
"summary": {
"activeBlockCount": 69,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 440,
"listingErrors": 441,
"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": "2026-09-12T09:15:12.531012+00:00",
"updatedAt": "2026-09-12T09:18:25.711326+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T09:12:38.355975+00:00",
"generatedAt": "2026-09-12T09:16:21.970584+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": "2026-09-12T09:06:14.080731+00:00",
"lastSyncTime": "2026-09-12T09:06:13.895768+00:00",
"generatedAt": "2026-09-12T09:16:13.625860+00:00",
"lastSyncTime": "2026-09-12T09:16:13.411459+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2303,19 +2303,19 @@
"unresolvedFailureCount": 8
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 41,
"attributableFailureCount": 42,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 41,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 30,
"framework_architecture_unsupported": 31,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 58,
"failureCount": 59,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2325,7 +2325,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 58,
"total": 59,
"unresolvedFailureCount": 17
}
},
@@ -2394,14 +2394,14 @@
"unresolvedFailureCount": 864
},
"vllm": {
"attributableFailureCount": 264,
"attributableFailureCount": 265,
"decisionFailureRate": 0.9888,
"decisionSuccessRate": 0.0112,
"decisionTotal": 267,
"decisionTotal": 268,
"failureBreakdown": {
"ambiguous_runtime": 198,
"backend_operator": 34,
"framework_architecture_unsupported": 181,
"framework_architecture_unsupported": 182,
"memory_capacity": 6,
"model_load": 24,
"platform_infrastructure": 1,
@@ -2410,14 +2410,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 487,
"failureCount": 488,
"failureRate": 0.9939,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0061,
"total": 490,
"total": 491,
"unresolvedFailureCount": 222
},
"vllm-mlu": {
@@ -2522,7 +2522,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T09:06:14.076618+00:00",
"generatedAt": "2026-09-12T09:16:13.620568+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2828,13 +2828,13 @@
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
"attributableFailureCount": 44,
"attributableFailureCount": 45,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 33,
"framework_architecture_unsupported": 34,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
@@ -2842,14 +2842,14 @@
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 99,
"failureCount": 100,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 99,
"total": 100,
"unresolvedFailureCount": 55
}
},
@@ -4648,22 +4648,22 @@
"decisionTotal": 14,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2,
"platform_infrastructure": 1,
"tokenizer_compatibility": 12
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-12T06:34:23.913264+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 16,
"total": 15,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -4786,7 +4786,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T08:20:40.114686+00:00",
"lastTerminalAt": "2026-09-12T09:16:13.411459+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7183,17 +7183,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1708,
"totalRecords": 1795,
"terminalRecords": 1709,
"totalRecords": 1796,
"totals": {
"attributableFailureCount": 473,
"decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1075,
"decisionTotal": 530,
"attributableFailureCount": 474,
"decisionFailureRate": 0.8927,
"decisionSuccessRate": 0.1073,
"decisionTotal": 531,
"failureBreakdown": {
"ambiguous_runtime": 400,
"backend_operator": 42,
"framework_architecture_unsupported": 289,
"framework_architecture_unsupported": 290,
"memory_capacity": 11,
"model_load": 70,
"platform_infrastructure": 4,
@@ -7203,20 +7203,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1651,
"failureCount": 1652,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0334,
"total": 1708,
"total": 1709,
"unresolvedFailureCount": 1174
},
"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。",
@@ -7225,7 +7226,6 @@
"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。",
@@ -7247,6 +7247,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1795,
"summarizedRecords": 1796,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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", "framework": "vllm", "lastSyncTime": "2026-09-12T09:16:13.411459+00:00", "modelId": "amd/Qwen2-7B-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T09:11:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079981", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T09:06:13.895768+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:57:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560058", "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", "framework": "vllm", "lastSyncTime": "2026-09-12T08:56:30.820631+00:00", "modelId": "amd/Qwen-2.5-1.5B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079114", "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": "2026-09-12T08:47:44.834299+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523323", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-08T18:50:46.511489+00:00", "modelId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523304", "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", "failureUnsupportedArchitectures": ["Rwkv5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-08T18:50:46.511511+00:00", "modelId": "RWKV/rwkv-5-world-1b5", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:41:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4107039", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T18:40:55.416591+00:00", "modelId": "amd/Phi-3.5-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:37:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080043", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T18:32:01.542091+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:27:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152885", "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": "98b19f6039b12f3ee9fe2eef1cbd742d4c54ca651f0a4d3ba12315e7da4b7454",
".modelhub_state/architecture_history_backfill.json": "88ea7c0aeeb617b7c02622bc3479cf51a58c4dc928587266ead2bec850703a32",
".modelhub_state/market_intelligence.json": "57de6b7b0530628da4efcef2681b7a71bf268fca11dd5004f5cff7b54e41f5cb",
".modelhub_state/official_capabilities.json": "1364486daeedac40736ea38b8af32420e43994c7807c5ffb667f60742d1a78ac",
".modelhub_state/outcome_checkpoint.json": "0f250e06f1ada2a080b5345dec7d60e6df79ccd18d45b2c4165cd71d0c045b57",
".modelhub_state/architecture_compatibility_blacklist.json": "0e4819fdcc34821494c96898bcbd8668ab78c44c131c79083f6261ff749e3ffa",
".modelhub_state/architecture_history_backfill.json": "4ac33fcb0030d3f6346a7402fdbaf5b4efbf064508d047d2cddb12413ffed91e",
".modelhub_state/market_intelligence.json": "ae7362a6975c9fbc58c1ff24d713e307a75ffab16e9b761f9fe1ef5e8ab654bd",
".modelhub_state/official_capabilities.json": "fffbecad578038a4dd1008dd4a4151885489b4e71cd5c402d36ed03c18982a39",
".modelhub_state/outcome_checkpoint.json": "6635e8c788bbff5fe0371c99afa5f86d8a4af111647f0fe257f49a7522d71bcb",
".modelhub_state/queue_cleanup_latest.json": "6b05059de615759adb561da08f7e955c6aa7fc0a1781227efab19cf90b539800",
".modelhub_state/recent_outcomes.jsonl": "096214b4c67e171fe3dfd0b3e11b4c3c3c08227344ed0d7d5fb09327693e43ab",
".modelhub_state/recovery_active_tasks.jsonl": "36a4472f03a77dc41d0b840c09e632233f016590198db7917b81bad1cb996056",
".modelhub_state/recovery_intents.jsonl": "c8f5818bb2c03cb9b04768b430efef28a43f705a4e75f21a069e8438556c0e2d",
".modelhub_state/recent_outcomes.jsonl": "83c7508f67434c48d7e3b7d0b19a1d997a12affcb985a65ffab30e3dea20f046",
".modelhub_state/recovery_active_tasks.jsonl": "b3455086736afd4ad527992d7720c5a3953d7dfc7b38cad8b8baba4a5c85c31c",
".modelhub_state/recovery_intents.jsonl": "c6fb6b8c61dcc960c8035049b8ea79b14eec64a27846929ddbc7ed5b59736023",
".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": 6128,
"generation": 6129,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T09:15:12.638659+00:00",
"updatedAt": "2026-09-12T09:18:26.439014+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}