state: generation 5264 (cycle)

This commit is contained in:
2026-09-10 16:39:14 +00:00
parent 552cdcc7ed
commit 9001aac317
9 changed files with 2030 additions and 2031 deletions

View File

@@ -1311,7 +1311,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T16:36:33.611897+00:00",
"generatedAt": "2026-09-10T16:39:14.207190+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 374,
"listingErrors": 375,
"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": 5,
"nextAccountIndex": 6,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T16:36:33.587875+00:00",
"updatedAt": "2026-09-10T16:39:14.184302+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T16:21:17.064778+00:00",
"communityAttemptedAt": "2026-09-10T16:37:44.581340+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T16:21:17.064778+00:00",
"communityUpdatedAt": "2026-09-10T16:37:44.581340+00:00",
"frameworkAttemptedAt": "2026-09-10T15:27:32.924657+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T16:34:44.967508+00:00",
"generatedAt": "2026-09-10T16:37:44.581340+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": "2026-09-10T16:05:32.108357+00:00",
"lastSyncTime": "2026-09-10T16:05:31.804365+00:00",
"generatedAt": "2026-09-10T16:37:38.553337+00:00",
"lastSyncTime": "2026-09-10T16:37:38.117587+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1384,12 +1384,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 26,
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 52,
"failureCount": 54,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1399,8 +1399,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 52,
"unresolvedFailureCount": 26
"total": 54,
"unresolvedFailureCount": 28
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -2321,7 +2321,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 175,
"ambiguous_runtime": 177,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2332,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 440,
"failureCount": 442,
"failureRate": 0.9955,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0045,
"total": 442,
"unresolvedFailureCount": 199
"total": 444,
"unresolvedFailureCount": 201
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T16:05:32.103753+00:00",
"generatedAt": "2026-09-10T16:37:38.548745+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2451,22 +2451,22 @@
"decisionSuccessRate": 0.037,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 26,
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 87,
"failureRate": 0.9886,
"failureCount": 89,
"failureRate": 0.9889,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0114,
"total": 88,
"unresolvedFailureCount": 61
"successRate": 0.0111,
"total": 90,
"unresolvedFailureCount": 63
},
"Ascend_910-b4": {
"attributableFailureCount": 38,
@@ -4007,21 +4007,20 @@
},
"recentCombinationStats": {
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 1
"ambiguous_runtime": 20
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T11:40:52.603333+00:00",
"lastTerminalAt": "2026-09-10T16:37:38.117587+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4030,7 +4029,7 @@
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 19
"unresolvedFailureCount": 20
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -4062,9 +4061,9 @@
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8571,
"decisionSuccessRate": 0.1429,
"decisionTotal": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 10,
"backend_operator": 4,
@@ -4072,18 +4071,18 @@
"model_load": 1
},
"failureCount": 16,
"failureRate": 0.9412,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T13:55:40.785120+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0588,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 17,
"total": 16,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -7121,15 +7120,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1605,
"totalRecords": 1692,
"terminalRecords": 1607,
"totalRecords": 1694,
"totals": {
"attributableFailureCount": 421,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 473,
"failureBreakdown": {
"ambiguous_runtime": 358,
"ambiguous_runtime": 360,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7141,30 +7140,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1553,
"failureCount": 1555,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 52,
"successRate": 0.0324,
"total": 1605,
"unresolvedFailureCount": 1129
"total": 1607,
"unresolvedFailureCount": 1131
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 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。",
"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 MetaX_c-500 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 Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|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 Cambricon_mlu-370-x4|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 Mthreads_s4000|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。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7179,11 +7179,10 @@
"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 Iluvatar_bi-150|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 Vastai_va16|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-x4|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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1692,
"summarizedRecords": 1694,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-10T16:37:38.117587+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505124", "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": "2026-09-10T16:37:38.117560+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:31:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505123", "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": "2026-09-10T16:05:31.804335+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:59:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457978", "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": "2026-09-10T16:05:31.804365+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477834", "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": "2026-09-10T15:48:17.745912+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471922", "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": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T05:49:30.800105+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T05:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079986", "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": ["AquilaDenseForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-08T05:49:30.800060+00:00", "modelId": "BAAI/AquilaDense-7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T05:39:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079957", "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": "2026-09-08T03:52:50.094616+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:51:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4483788", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-08T03:52:50.094606+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-08T03:37:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610404", "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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-08T03:52:50.094582+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:33:22+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4478318", "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": "20a9afca02e1235c1d03554189c6e6cc86f3d2d262dd27254ecc90e301894b8c",
".modelhub_state/architecture_history_backfill.json": "c29c9af056ce53f20462e480a9653b5e426b45984b2b04ba30eccd6e63947913",
".modelhub_state/market_intelligence.json": "b6b750045301c8313f884e279d8f2cba37bfcf20b887a8816e9f049fad0f43b4",
".modelhub_state/official_capabilities.json": "d12aa20fd88efc1442f986fe7263bb7c05859f0401fa71774542295103d0b310",
".modelhub_state/outcome_checkpoint.json": "ab55380294516dac01a25937086b20b44df16b5a40786686683d134c2fbb72e5",
".modelhub_state/architecture_compatibility_blacklist.json": "a088732fbc8e189c2367813a043965ff5f9fbd9ce466bfa36414475cfcc618da",
".modelhub_state/architecture_history_backfill.json": "93aa88140245cabf7ba4627bb750b40afebef7979efd897027de14ede41d95cf",
".modelhub_state/market_intelligence.json": "7d8046c504c23ebcddb49d54d5cfb83e540ea55c50890c51f77888e8816e20f4",
".modelhub_state/official_capabilities.json": "12aa51289ad4ddeae8b3b80138e018eaf26aa4549b601191c9a46bc51dd9f396",
".modelhub_state/outcome_checkpoint.json": "2aedd7fde28dd73c95d9b48966b8a359344690286a23af5dbd3f4dd123e6b7e9",
".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
".modelhub_state/recent_outcomes.jsonl": "fc3a7c551aea5a2c51f6adddeca2af355c5bc536b5c721448ca74f2df383b291",
".modelhub_state/recovery_active_tasks.jsonl": "8c36b71f3d246828f71ec601b908bfa76b8658dcf705ec772664796b98aab5e1",
".modelhub_state/recovery_intents.jsonl": "8fd325f1b5aaddaf7013c04bf76996c5517d2889e5a1c96a63a9e0b910078cb9",
".modelhub_state/recent_outcomes.jsonl": "f786ab58697139703817248a636414bbac3074e34d3b3afc6838b6c8f034bf40",
".modelhub_state/recovery_active_tasks.jsonl": "379f89a1fd32f0c14f2771d937ee783f39e458441c8c36250d37ca34f7392b36",
".modelhub_state/recovery_intents.jsonl": "fba88969410b6f1d58b7e7fde2459f796a25c998b364361e0f2cf4401c569c5a",
".modelhub_state/routing_intelligence.json": "105acb4c688c8608310dfc43a2e337bb930f06325ac0acf2e6eb6fd96eb96a51",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "83760212ef857acd281f56c282e2622b4d3e6b575008d784dce7c6c3ef6f368a",
"outcomes/submissions.jsonl": "bce6dbb50eae912230cdd67eda9a332c099040daec32ad588361073c3c03c7d4"
},
"generation": 5263,
"generation": 5264,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T16:36:33.690746+00:00",
"updatedAt": "2026-09-10T16:39:14.763008+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}