state: generation 6126 (cycle)
This commit is contained in:
@@ -1362,7 +1362,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T09:05:12.989350+00:00",
|
||||
"generatedAt": "2026-09-12T09:08:17.354512+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 69,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"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": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-12T09:05:12.966640+00:00",
|
||||
"updatedAt": "2026-09-12T09:08:17.328568+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-12T09:03:28.376252+00:00",
|
||||
"generatedAt": "2026-09-12T09:06:23.239613+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T08:56:31.046689+00:00",
|
||||
"lastSyncTime": "2026-09-12T08:56:30.820631+00:00",
|
||||
"generatedAt": "2026-09-12T09:06:14.080731+00:00",
|
||||
"lastSyncTime": "2026-09-12T09:06:13.895768+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1896,11 +1896,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 32,
|
||||
"ambiguous_runtime": 33,
|
||||
"memory_capacity": 1,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 55,
|
||||
"failureCount": 56,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
@@ -1910,8 +1910,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 55,
|
||||
"unresolvedFailureCount": 54
|
||||
"total": 56,
|
||||
"unresolvedFailureCount": 55
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|visual-multi-modal": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2373,7 +2373,7 @@
|
||||
"decisionSuccessRate": 0.264,
|
||||
"decisionTotal": 197,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 131,
|
||||
"ambiguous_runtime": 132,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 91,
|
||||
"memory_capacity": 5,
|
||||
@@ -2383,15 +2383,15 @@
|
||||
"参数/模板问题": 59,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1009,
|
||||
"failureCount": 1010,
|
||||
"failureRate": 0.951,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 52,
|
||||
"successRate": 0.049,
|
||||
"total": 1061,
|
||||
"unresolvedFailureCount": 863
|
||||
"total": 1062,
|
||||
"unresolvedFailureCount": 864
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 264,
|
||||
@@ -2522,7 +2522,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T08:56:31.042291+00:00",
|
||||
"generatedAt": "2026-09-12T09:06:14.076618+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2715,20 +2715,20 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 66,
|
||||
"ambiguous_runtime": 67,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 91,
|
||||
"failureCount": 92,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 91,
|
||||
"unresolvedFailureCount": 90
|
||||
"total": 92,
|
||||
"unresolvedFailureCount": 91
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 48,
|
||||
@@ -4495,13 +4495,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3
|
||||
"ambiguous_runtime": 4
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T01:50:54.936024+00:00",
|
||||
"lastTerminalAt": "2026-09-12T09:06:13.895768+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4509,8 +4509,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7183,15 +7183,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1707,
|
||||
"totalRecords": 1794,
|
||||
"terminalRecords": 1708,
|
||||
"totalRecords": 1795,
|
||||
"totals": {
|
||||
"attributableFailureCount": 473,
|
||||
"decisionFailureRate": 0.8925,
|
||||
"decisionSuccessRate": 0.1075,
|
||||
"decisionTotal": 530,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 399,
|
||||
"ambiguous_runtime": 400,
|
||||
"backend_operator": 42,
|
||||
"framework_architecture_unsupported": 289,
|
||||
"memory_capacity": 11,
|
||||
@@ -7203,21 +7203,20 @@
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1650,
|
||||
"failureCount": 1651,
|
||||
"failureRate": 0.9666,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 57,
|
||||
"successRate": 0.0334,
|
||||
"total": 1707,
|
||||
"unresolvedFailureCount": 1173
|
||||
"total": 1708,
|
||||
"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。",
|
||||
@@ -7226,6 +7225,7 @@
|
||||
"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": 1794,
|
||||
"summarizedRecords": 1795,
|
||||
"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": "2026-09-12T09:06:13.895768+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}
|
||||
{"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}
|
||||
@@ -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", "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}
|
||||
{"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}
|
||||
|
||||
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": "2481ad05a7e344e66d31dabcc7eac09932e04ead72de921fbc6b59b8aa20acc9",
|
||||
".modelhub_state/architecture_history_backfill.json": "104a8696907d566e2b20df538bbc056ea558242c0d8e2d224c5f05808968a7e4",
|
||||
".modelhub_state/market_intelligence.json": "9b231ede9ee63ad7ccbfe8f899cddcc9891ea6ce43fe1482324ef0c3d0ddc809",
|
||||
".modelhub_state/official_capabilities.json": "634a42a2f015f3ef4c96593bd2f70f2de55f55de7015924b47c01ac4c65aa668",
|
||||
".modelhub_state/outcome_checkpoint.json": "33345b8cdf4261df4ca9da31897014b46f4e18f3219be95c43c8a5af0e8f95ad",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "0dc6acf909fe95de27ec90f626a5cc995bebcc5e8f69260b99acc1d83ff7dee2",
|
||||
".modelhub_state/architecture_history_backfill.json": "1abbe1448b337f1962c983056a88aa19b08c3f0e398ab0b17fe848c867be26a5",
|
||||
".modelhub_state/market_intelligence.json": "bf23c297354dd3702f0dabce701c73c1db61a70ffd2ead31f50f61f72e833480",
|
||||
".modelhub_state/official_capabilities.json": "454fcbf4a11d3c48a32b2a4d9bad7dce1309692b15e78bdefe864ff8174c2a62",
|
||||
".modelhub_state/outcome_checkpoint.json": "0f250e06f1ada2a080b5345dec7d60e6df79ccd18d45b2c4165cd71d0c045b57",
|
||||
".modelhub_state/queue_cleanup_latest.json": "6b05059de615759adb561da08f7e955c6aa7fc0a1781227efab19cf90b539800",
|
||||
".modelhub_state/recent_outcomes.jsonl": "1e95194ab02d07033c6d936c90142af36bcdb0f002e5eff0a379a5737416a847",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "c08d7661747afc85c07e74aea2397a2b3ad967ed86a86d4af9aec11fda746d9c",
|
||||
".modelhub_state/recovery_intents.jsonl": "08d1ffab1bbf4a81d6b28a1e1767af5290e92764de810bbfd0cdb497b558fe11",
|
||||
".modelhub_state/recent_outcomes.jsonl": "096214b4c67e171fe3dfd0b3e11b4c3c3c08227344ed0d7d5fb09327693e43ab",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "36a4472f03a77dc41d0b840c09e632233f016590198db7917b81bad1cb996056",
|
||||
".modelhub_state/recovery_intents.jsonl": "c8f5818bb2c03cb9b04768b430efef28a43f705a4e75f21a069e8438556c0e2d",
|
||||
".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": 6125,
|
||||
"generation": 6126,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-12T09:05:13.122991+00:00",
|
||||
"updatedAt": "2026-09-12T09:08:18.155186+00:00",
|
||||
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user