state: generation 18962 (cycle)

This commit is contained in:
2026-09-30 22:32:41 +00:00
parent 03e6486c6c
commit dada53f249
8 changed files with 1304 additions and 1305 deletions

View File

@@ -3320,7 +3320,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-30T22:20:26.468335+00:00",
"generatedAt": "2026-09-30T22:30:37.121909+00:00",
"summary": {
"activeBlockCount": 167,
"byGpuFramework": {

View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-30T22:29:31.950264+00:00",
"generatedAt": "2026-09-30T22:32:15.369827+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-30T22:29:31.950264+00:00",
"catalogUpdatedAt": "2026-09-30T22:32:15.369827+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-30T22:29:31.950264+00:00",
"generatedAt": "2026-09-30T22:32:15.369827+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6339,6 +6339,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-30T22:29:31.950264+00:00",
"taskTreeUpdatedAt": "2026-09-30T22:32:15.369827+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-30T21:40:39.264643+00:00",
"lastSyncTime": "2026-09-30T21:40:39.047183+00:00",
"generatedAt": "2026-09-30T22:30:37.028813+00:00",
"lastSyncTime": "2026-09-30T22:30:36.747089+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4590,30 +4590,30 @@
"unresolvedFailureCount": 82
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 43,
"decisionFailureRate": 0.6935,
"decisionSuccessRate": 0.3065,
"decisionTotal": 62,
"attributableFailureCount": 44,
"decisionFailureRate": 0.6984,
"decisionSuccessRate": 0.3016,
"decisionTotal": 63,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 6,
"framework_architecture_unsupported": 20,
"framework_architecture_unsupported": 21,
"memory_capacity": 1,
"model_load": 6,
"runtime_memory": 10,
"参数/模板问题": 2
},
"failureCount": 71,
"failureRate": 0.7889,
"failureCount": 72,
"failureRate": 0.7912,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.2111,
"successRate": 0.2088,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 90,
"total": 91,
"unresolvedFailureCount": 28
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -6119,27 +6119,27 @@
"unresolvedFailureCount": 53
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 43,
"decisionFailureRate": 0.6935,
"decisionSuccessRate": 0.3065,
"decisionTotal": 62,
"attributableFailureCount": 44,
"decisionFailureRate": 0.6984,
"decisionSuccessRate": 0.3016,
"decisionTotal": 63,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 6,
"framework_architecture_unsupported": 20,
"framework_architecture_unsupported": 21,
"memory_capacity": 1,
"model_load": 6,
"runtime_memory": 10,
"参数/模板问题": 2
},
"failureCount": 71,
"failureRate": 0.7889,
"failureCount": 72,
"failureRate": 0.7912,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.2111,
"total": 90,
"successRate": 0.2088,
"total": 91,
"unresolvedFailureCount": 28
},
"vllm_fix_tokenizer": {
@@ -6196,7 +6196,7 @@
"unresolvedFailureCount": 218
}
},
"generatedAt": "2026-09-30T21:40:39.252002+00:00",
"generatedAt": "2026-09-30T22:30:37.015802+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 109,
@@ -6361,16 +6361,16 @@
"unresolvedFailureCount": 568
},
"Iluvatar_bi-150": {
"attributableFailureCount": 760,
"decisionFailureRate": 0.8352,
"decisionSuccessRate": 0.1648,
"decisionTotal": 910,
"attributableFailureCount": 761,
"decisionFailureRate": 0.8353,
"decisionSuccessRate": 0.1647,
"decisionTotal": 911,
"failureBreakdown": {
"ambiguous_runtime": 653,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
"framework_architecture_unsupported": 253,
"framework_architecture_unsupported": 254,
"memory_capacity": 153,
"model_load": 126,
"platform_infrastructure": 21,
@@ -6381,14 +6381,14 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1939,
"failureCount": 1940,
"failureRate": 0.9282,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 150,
"successRate": 0.0718,
"total": 2089,
"total": 2090,
"unresolvedFailureCount": 1158
},
"Iluvatar_mrv-100": {
@@ -53885,20 +53885,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17170,
"totalRecords": 17391,
"terminalRecords": 17171,
"totalRecords": 17392,
"totals": {
"attributableFailureCount": 6153,
"attributableFailureCount": 6154,
"decisionFailureRate": 0.8632,
"decisionSuccessRate": 0.1368,
"decisionTotal": 7128,
"decisionTotal": 7129,
"failureBreakdown": {
"ambiguous_runtime": 4476,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 326,
"framework_architecture_unsupported": 2200,
"framework_architecture_unsupported": 2201,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 943,
@@ -53909,30 +53909,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16195,
"failureCount": 16196,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 943,
"successCount": 975,
"successRate": 0.0568,
"total": 17170,
"total": 17171,
"unresolvedFailureCount": 9099
},
"warnings": [
"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 Biren_166m 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 Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 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-x8 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 Kunlunxin_p-800 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 Sunrise_pt-200-x1 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 Vastai_va16 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 Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -53977,6 +53977,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17391,
"summarizedRecords": 17392,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "d7f2e546a9e5b50e83bbc3621f35cbef685f547e4fd3054cbfc6bd6bd141feed",
".modelhub_state/architecture_compatibility_blacklist.json": "dda1eb7299875a96e3a68daac844168b7eb4e4b20e12b3f11de0f0f59fa8148d",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "a906e9d8c9b8d599873d731bb06fe7990a55d617d7bc823e5ff6f68d94bb1517",
".modelhub_state/official_capabilities.json": "49080f5bb196d77a211a55280eebb8be9ce2e14b074548c673c9678fcffb20c6",
".modelhub_state/outcome_checkpoint.json": "28f933235a7ffb9352a69552842bc8f31642e3cae88e34b52cea400966262e7d",
".modelhub_state/market_intelligence.json": "fb22a6cdcd9379cbc22e15f7af798ce6a5d261b7d0832fc82927bf3c9165a1af",
".modelhub_state/official_capabilities.json": "41d61ddda199e0fcbd74880296101dc35f52b1e83e3eb525ae5036b5a8f21d0a",
".modelhub_state/outcome_checkpoint.json": "fe096c06becb3a0ef7546560d834f851df17e7c1211a8f2a5f5d0541c2d788af",
".modelhub_state/queue_cleanup_latest.json": "c1930ca8fdcacb5490295c7c7dc06f8ef1bd9c45953bf68d684e316cf0b931fd",
".modelhub_state/recent_outcomes.jsonl": "22f7b87632023997b593fd86481617dc1a68e0e3a80c4eccff832831ef110581",
".modelhub_state/recovery_active_tasks.jsonl": "983ef95de54da211aeebf5122a70988f05d94b5ed97806f66b77d12787e36860",
".modelhub_state/recovery_intents.jsonl": "f217e91e9bd473b99c653b94bcf5cb73abf730a31248ab6b35f06ab2005d5937",
".modelhub_state/recovery_active_tasks.jsonl": "e81fa40c93d1e981249a36c94ae708f14e6557ad99ec9cea2593966abe72be7e",
".modelhub_state/recovery_intents.jsonl": "a2d697a16d42f231ca61ba5e5d2b85573633b9e2e3e27f2aa753a09034ecbba2",
".modelhub_state/routing_intelligence.json": "09cc69960b345ef40104091dc4737ddc82df87d637c93fb6b2c12b4e9f5ead9e",
".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
"ledger/submissions.jsonl": "0ae087d0a1ec37eefc7586b2030390aa08232076d2972d18a8d3320a4d29de46",
"outcomes/submissions.jsonl": "500c407e29157426b6867415c4299e8a0138c43b1a7440243bdba2f7705bc531"
"outcomes/submissions.jsonl": "ba9fabc8745ab9a7ed211e5783ed1e28fb4a04a72ab27fbb221553f2cb793c3b"
},
"generation": 18961,
"generation": 18962,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-30T22:29:35.265799+00:00",
"updatedAt": "2026-09-30T22:32:41.935249+00:00",
"writerId": "a812d0e025c3474eb16b828a4d987334"
}

View File

@@ -140,7 +140,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-16T17:09:11.209752+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:03:09.666793+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4889677", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T17:25:59.446149+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:20:28.174669+00:00", "targetGpu": "MetaX_c-500", "taskId": "4889839", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-16T17:41:50.112754+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:37:59.405066+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4890080", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-16T17:50:41.534321+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:49:03.662873+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4890217", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T18:07:34.714203+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:59:53.000301+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4890315", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T18:24:50.147957+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T10:17:32.995862+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4890520", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-16T21:06:51.250639+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T12:59:29.226923+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4892870", "taskType": "text-generation", "verifyResult": null}