state: generation 6515 (cycle)
This commit is contained in:
@@ -1454,7 +1454,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T04:22:06.888006+00:00",
|
||||
"generatedAt": "2026-09-13T04:24:43.323950+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 73,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
"11": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 471,
|
||||
"listingErrors": 472,
|
||||
"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": "2026-09-13T04:22:06.865296+00:00",
|
||||
"updatedAt": "2026-09-13T04:24:43.296225+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-13T04:20:20.319655+00:00",
|
||||
"generatedAt": "2026-09-13T04:23:14.414986+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T04:05:57.160347+00:00",
|
||||
"lastSyncTime": "2026-09-13T04:05:56.910845+00:00",
|
||||
"generatedAt": "2026-09-13T04:23:07.879464+00:00",
|
||||
"lastSyncTime": "2026-09-13T04:23:07.613289+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1689,24 +1689,24 @@
|
||||
"decisionSuccessRate": 0.087,
|
||||
"decisionTotal": 23,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 35,
|
||||
"ambiguous_runtime": 36,
|
||||
"framework_architecture_unsupported": 19,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 95,
|
||||
"failureRate": 0.9794,
|
||||
"failureCount": 96,
|
||||
"failureRate": 0.9796,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0206,
|
||||
"successRate": 0.0204,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 97,
|
||||
"unresolvedFailureCount": 74
|
||||
"total": 98,
|
||||
"unresolvedFailureCount": 75
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 8,
|
||||
@@ -2468,7 +2468,7 @@
|
||||
"decisionSuccessRate": 0.2647,
|
||||
"decisionTotal": 204,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 140,
|
||||
"ambiguous_runtime": 141,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 95,
|
||||
"memory_capacity": 5,
|
||||
@@ -2478,15 +2478,15 @@
|
||||
"参数/模板问题": 61,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1025,
|
||||
"failureCount": 1026,
|
||||
"failureRate": 0.95,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 54,
|
||||
"successRate": 0.05,
|
||||
"total": 1079,
|
||||
"unresolvedFailureCount": 874
|
||||
"total": 1080,
|
||||
"unresolvedFailureCount": 875
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 292,
|
||||
@@ -2617,7 +2617,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T04:05:57.155917+00:00",
|
||||
"generatedAt": "2026-09-13T04:23:07.875222+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2697,21 +2697,21 @@
|
||||
"decisionSuccessRate": 0.087,
|
||||
"decisionTotal": 23,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 35,
|
||||
"ambiguous_runtime": 36,
|
||||
"framework_architecture_unsupported": 19,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 95,
|
||||
"failureRate": 0.9794,
|
||||
"failureCount": 96,
|
||||
"failureRate": 0.9796,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0206,
|
||||
"total": 97,
|
||||
"unresolvedFailureCount": 74
|
||||
"successRate": 0.0204,
|
||||
"total": 98,
|
||||
"unresolvedFailureCount": 75
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 18,
|
||||
@@ -4557,7 +4557,7 @@
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T22:34:15.509071+00:00",
|
||||
"lastTerminalAt": "2026-09-13T04:23:07.613289+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4803,31 +4803,6 @@
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "llamacpp",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-09T08:32:12.414501+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
@@ -7393,15 +7368,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1761,
|
||||
"totalRecords": 1848,
|
||||
"terminalRecords": 1762,
|
||||
"totalRecords": 1849,
|
||||
"totals": {
|
||||
"attributableFailureCount": 509,
|
||||
"decisionFailureRate": 0.8961,
|
||||
"decisionSuccessRate": 0.1039,
|
||||
"decisionTotal": 568,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 413,
|
||||
"ambiguous_runtime": 414,
|
||||
"backend_operator": 42,
|
||||
"framework_architecture_unsupported": 320,
|
||||
"memory_capacity": 11,
|
||||
@@ -7413,21 +7388,20 @@
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1702,
|
||||
"failureCount": 1703,
|
||||
"failureRate": 0.9665,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 59,
|
||||
"successRate": 0.0335,
|
||||
"total": 1761,
|
||||
"unresolvedFailureCount": 1189
|
||||
"total": 1762,
|
||||
"unresolvedFailureCount": 1190
|
||||
},
|
||||
"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。",
|
||||
@@ -7436,6 +7410,7 @@
|
||||
"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。",
|
||||
@@ -7458,6 +7433,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1848,
|
||||
"summarizedRecords": 1849,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T04:23:07.613289+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:17:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4557614", "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": "2026-09-13T04:05:56.910845+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:05:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332432", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T04:05:56.910823+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458813", "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": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T03:22:02.529658+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:21:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4558358", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_mtp"], "framework": "", "lastSyncTime": "2026-09-09T11:01:57.287962+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332978", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-09T10:14:08.904917+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T10:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4421471", "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": "2026-09-09T09:03:44.512406+00:00", "modelId": "amd/Qwen3-4B-awq-quant-onnx-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T09:01:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079256", "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", "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-09-09T08:32:12.414501+00:00", "modelId": "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T08:31:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4574708", "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": "f8f7707ae88f78d7b881b9c45f9a0b500f3d58dcea2217bdc5d97eebe52eaf2f",
|
||||
".modelhub_state/architecture_history_backfill.json": "ef6b1747fc36ed39b621ccd2b3f69797c6062d8aaba2236d511f2e10a96323e3",
|
||||
".modelhub_state/market_intelligence.json": "f7c58b1c10e5b3186d0bff6b7ceba2424db282b8a75ebe672df6ef628c94a952",
|
||||
".modelhub_state/official_capabilities.json": "7890577068b41def67579b1ef283725ee195b364c8627ad958971bac19460af0",
|
||||
".modelhub_state/outcome_checkpoint.json": "69367c4e9b3bc8796278e9a5d93048a2dd5e28705bc20db5bfb2755d251e2c21",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "f6aa88a9c26577955fd73b40d4b6aa0a61b7c87bdb97eb2382ce4e4fc24a29bb",
|
||||
".modelhub_state/architecture_history_backfill.json": "b0076bbde05c8bca555076ce6e9388f6a3c842d83dc7de84b53ef6f3dfdb5756",
|
||||
".modelhub_state/market_intelligence.json": "bf7a7de82103f4439ad2a5afe8dea2f2ef9b13396ed27a0b9fb4e67eb246aa0c",
|
||||
".modelhub_state/official_capabilities.json": "531b64a1f33541757d7c726c738399e42a865724b5a09e609f217ed92def44a5",
|
||||
".modelhub_state/outcome_checkpoint.json": "8b6a8036a2b741d953f3e3ce8299f8ad58594f9e66d25efbb0a007f6ec9330c3",
|
||||
".modelhub_state/queue_cleanup_latest.json": "51e7d1585319177976584ac9d97c18e02335e06fbd17bfdd6be748f1310ef4da",
|
||||
".modelhub_state/recent_outcomes.jsonl": "0c55572f448fa6cb316e6207fa9f1bda381185c47737650346b7056dce4e34cb",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "d11d8fdda160c135043fcd2e1be063c7f9e01dba14860006ae8f2ad2783672c0",
|
||||
".modelhub_state/recovery_intents.jsonl": "4e9171d050867b9442eb16f6cf11092f29e35735678c3b58c2b762809d990e51",
|
||||
".modelhub_state/recent_outcomes.jsonl": "9449545c4b6a994a9814fac4dc18720affff0b6f5ac22f34952e768cfe9348d5",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "b37c043a516942aa22dee7770e1d4fb22981f07f8ad5c002b6b8d8588ad7efa1",
|
||||
".modelhub_state/recovery_intents.jsonl": "6ebf94c41d35209a817ce33bbbcd5a44deff0092744014196c4e153c2c6f883c",
|
||||
".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
|
||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
|
||||
"ledger/submissions.jsonl": "8f12d75f773632785dd64de0467afe57dcae00a4cf0c7c019d8a956931e393a1",
|
||||
"outcomes/submissions.jsonl": "52eb59d3f79d7002ef2c21ead04124871025575876c40b3c89e753c66cc8d521"
|
||||
},
|
||||
"generation": 6514,
|
||||
"generation": 6515,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-13T04:22:06.957903+00:00",
|
||||
"updatedAt": "2026-09-13T04:24:43.978616+00:00",
|
||||
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user