state: generation 10711 (cycle)

This commit is contained in:
2026-09-20 16:12:55 +00:00
parent 2f708b77cd
commit fcbab467c6
8 changed files with 1866 additions and 1866 deletions

View File

@@ -1950,7 +1950,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-20T16:09:18.459840+00:00",
"generatedAt": "2026-09-20T16:12:47.895170+00:00",
"summary": {
"activeBlockCount": 95,
"byGpuFramework": {

View File

@@ -425,7 +425,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-20T16:11:44.428875+00:00",
"generatedAt": "2026-09-20T16:12:55.073354+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-20T16:11:44.428875+00:00",
"catalogUpdatedAt": "2026-09-20T16:12:55.073354+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-20T16:11:44.428875+00:00",
"generatedAt": "2026-09-20T16:12:55.073354+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6333,6 +6333,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-20T16:11:44.428875+00:00",
"taskTreeUpdatedAt": "2026-09-20T16:12:55.073354+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T15:35:52.077496+00:00",
"lastSyncTime": "2026-09-20T15:35:51.777956+00:00",
"generatedAt": "2026-09-20T16:12:47.839143+00:00",
"lastSyncTime": "2026-09-20T16:12:47.264793+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4316,16 +4316,16 @@
"unresolvedFailureCount": 20
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 647,
"attributableFailureCount": 648,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 647,
"decisionTotal": 648,
"failureBreakdown": {
"ambiguous_runtime": 152,
"ambiguous_runtime": 153,
"architecture_compatibility": 30,
"attention_backend": 1,
"context_length": 42,
"framework_architecture_unsupported": 220,
"framework_architecture_unsupported": 221,
"memory_capacity": 58,
"model_load": 56,
"platform_infrastructure": 3,
@@ -4333,7 +4333,7 @@
"runtime_memory": 52,
"tokenizer_compatibility": 79
},
"failureCount": 802,
"failureCount": 804,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -4343,8 +4343,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 802,
"unresolvedFailureCount": 152
"total": 804,
"unresolvedFailureCount": 153
},
"hygon_k100-ai|vllm|unknown": {
"attributableFailureCount": 1,
@@ -4467,17 +4467,17 @@
"unresolvedFailureCount": 6405
},
"vllm": {
"attributableFailureCount": 3476,
"attributableFailureCount": 3477,
"decisionFailureRate": 0.9778,
"decisionSuccessRate": 0.0222,
"decisionTotal": 3555,
"decisionTotal": 3556,
"failureBreakdown": {
"ambiguous_runtime": 1434,
"ambiguous_runtime": 1435,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1261,
"framework_architecture_unsupported": 1262,
"memory_capacity": 720,
"model_load": 199,
"platform_infrastructure": 864,
@@ -4486,15 +4486,15 @@
"tokenizer_compatibility": 408,
"参数/模板问题": 40
},
"failureCount": 5814,
"failureCount": 5816,
"failureRate": 0.9866,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 79,
"successRate": 0.0134,
"total": 5893,
"unresolvedFailureCount": 1474
"total": 5895,
"unresolvedFailureCount": 1475
},
"vllm-customized": {
"attributableFailureCount": 1,
@@ -4627,7 +4627,7 @@
"unresolvedFailureCount": 24
}
},
"generatedAt": "2026-09-20T15:35:52.067113+00:00",
"generatedAt": "2026-09-20T16:12:47.830442+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 75,
@@ -5007,16 +5007,16 @@
"unresolvedFailureCount": 1303
},
"hygon_k100-ai": {
"attributableFailureCount": 682,
"attributableFailureCount": 683,
"decisionFailureRate": 0.9579,
"decisionSuccessRate": 0.0421,
"decisionTotal": 712,
"decisionTotal": 713,
"failureBreakdown": {
"ambiguous_runtime": 297,
"ambiguous_runtime": 298,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
"framework_architecture_unsupported": 235,
"framework_architecture_unsupported": 236,
"memory_capacity": 58,
"model_load": 57,
"platform_infrastructure": 4,
@@ -5027,15 +5027,15 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1452,
"failureCount": 1454,
"failureRate": 0.9798,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 30,
"successRate": 0.0202,
"total": 1482,
"unresolvedFailureCount": 766
"total": 1484,
"unresolvedFailureCount": 767
}
},
"observedGpuMemoryGiB": {
@@ -11304,14 +11304,14 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 7,
"model_load": 1,
"runtime_memory": 2,
"参数/模板问题": 1
},
"failureCount": 15,
"failureRate": 0.9375,
"failureCount": 14,
"failureRate": 0.9333,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T06:27:54.872472+00:00",
@@ -11319,11 +11319,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0625,
"successRate": 0.0667,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 5
"total": 15,
"unresolvedFailureCount": 4
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -11550,9 +11550,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 12
"ambiguous_runtime": 11
},
"failureCount": 12,
"failureCount": 11,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -11564,8 +11564,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 12
"total": 11,
"unresolvedFailureCount": 11
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -11879,22 +11879,22 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 11,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 10,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 11,
"model_load": 1
},
"failureCount": 18,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T12:21:49.901980+00:00",
"lastTerminalAt": "2026-09-20T16:12:47.264764+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -11902,8 +11902,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 7
"total": 20,
"unresolvedFailureCount": 8
}
},
"recentProfileCombinationStats": {
@@ -22546,20 +22546,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 15879,
"totalRecords": 15984,
"terminalRecords": 15881,
"totalRecords": 15986,
"totals": {
"attributableFailureCount": 5758,
"decisionFailureRate": 0.8613,
"decisionSuccessRate": 0.1387,
"decisionTotal": 6685,
"attributableFailureCount": 5759,
"decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386,
"decisionTotal": 6686,
"failureBreakdown": {
"ambiguous_runtime": 3770,
"ambiguous_runtime": 3771,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 318,
"framework_architecture_unsupported": 1986,
"framework_architecture_unsupported": 1987,
"memory_capacity": 1195,
"model_load": 479,
"platform_infrastructure": 922,
@@ -22570,15 +22570,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14952,
"failureCount": 14954,
"failureRate": 0.9416,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 927,
"successRate": 0.0584,
"total": 15879,
"unresolvedFailureCount": 8272
"total": 15881,
"unresolvedFailureCount": 8273
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -22623,12 +22623,12 @@
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 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。",
"组合 Iluvatar_bi-150|transformers|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 Cambricon_mlu-370-x8|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 Ascend_910-b3|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-b3|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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 15984,
"summarizedRecords": 15986,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-20T16:12:47.264764+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T16:11:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592334", "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": "2026-09-20T16:12:47.264793+00:00", "modelId": "KenDual3090tiNvlink/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T16:11:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080000", "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": "2026-09-20T14:32:15.260773+00:00", "modelId": "AI-ModelScope/granite-20b-code-base", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:25:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079181", "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": "2026-09-20T14:18:03.259001+00:00", "modelId": "QuantTrio/Kimi-Dev-72B-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:17:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079164", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-20T13:34:22.859864+00:00", "modelId": "AI-ModelScope/granite-20b-code-instruct-8k", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T13:31:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079142", "taskType": "text-generation", "verifyResult": 1}
@@ -296,5 +298,3 @@
{"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": "2026-09-14T07:31:50.924177+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T07:09:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505074", "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": "2026-09-14T07:06:22.844621+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T06:39:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4590765", "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": "2026-09-14T06:35:29.110873+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T06:31:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4590281", "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": "2026-09-14T04:51:03.045568+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T04:45:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610351", "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": "2026-09-14T03:38:15.505403+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T03:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596909", "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": "2026.09.20.2",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "eb10e4a90c2c792c03b3926688a23bc190e4c5c71f334cf4061dd5f8b4869e3e",
".modelhub_state/architecture_compatibility_blacklist.json": "b578c27ce12bfc6cc08fb3ba1f44897392420af148e783989dfc6a5806a19f0c",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "cd0dcbcd12564883d7a76adf6fca92e189c71815290f894b51f6214f819307c7",
".modelhub_state/official_capabilities.json": "0880778316d6abd73b27eccb6c3d13735386d3896de06038ea64ff2273b86f2f",
".modelhub_state/outcome_checkpoint.json": "53bdfa81eee598248669388bcbc9796ad0ed5ededecb1b10744d7d73f85c048e",
".modelhub_state/market_intelligence.json": "1fe9017e1d0bbc1e59be673b922bf07605038ee30bd247cda8d4655ac167297d",
".modelhub_state/official_capabilities.json": "1eed2d3d70fa0c7cc51eba2cee5e347f16cf6806724d8861ea0f8c18e973addb",
".modelhub_state/outcome_checkpoint.json": "18462e0d2b46bc79814b92e8356ef6feea711a45609f89e0f172f6c8d538970b",
".modelhub_state/queue_cleanup_latest.json": "c08f8d05133b1c670eeecc05c2f1f58fb85c2589e80bc520cfd00c86c079ea31",
".modelhub_state/recent_outcomes.jsonl": "a3921c626fada716d874c7301cda0727aa0d2309c50c4e5b46c51cd7d9265eb9",
".modelhub_state/recovery_active_tasks.jsonl": "585d32450c03e58a53c69d8574ee8ac0ead7c0313faa33da5eb19450dc321f65",
".modelhub_state/recovery_intents.jsonl": "58d1acc8e6e6d470257137ac68291183113d207ac15a53897eff6a94a199f361",
".modelhub_state/recent_outcomes.jsonl": "24b14f987910435e78f54e56f0bf38ac8accd31f7ff6a59072b4a4aae4cbc4e7",
".modelhub_state/recovery_active_tasks.jsonl": "2816d04a0727d24eaa83bc922b63d4129765613a96985d90e61844f8d64ae9a8",
".modelhub_state/recovery_intents.jsonl": "9ac5664a3432dd71dca6787f901a2f9b84fc18e656e0033b505fb25330b3df6f",
".modelhub_state/routing_intelligence.json": "43dabb5759e0ffa7ff610d3220ee2b32e2f9d418aaaaa24df64b89321f9dd111",
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "a4e9a336263c1c9b7b880a5709d1bff52a2f2849a87bbc73b1fc9d83d2106848",
"outcomes/submissions.jsonl": "a2b8bd8632201964d064feec01a2ee2bc0c6f65f77dfece592bf79010c081388"
},
"generation": 10710,
"generation": 10711,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-20T16:11:44.910378+00:00",
"updatedAt": "2026-09-20T16:12:55.946685+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996"
}