state: generation 4994 (cycle)

This commit is contained in:
2026-09-10 05:57:57 +00:00
parent ab47651500
commit 830c5af776
9 changed files with 1915 additions and 1915 deletions

View File

@@ -1323,7 +1323,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T05:56:07.144015+00:00",
"generatedAt": "2026-09-10T05:57:57.004676+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 355,
"listingErrors": 356,
"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": 4,
"nextAccountIndex": 5,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T05:56:07.109261+00:00",
"updatedAt": "2026-09-10T05:57:56.977823+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T05:54:34.518709+00:00",
"generatedAt": "2026-09-10T05:56:10.570586+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": "2026-09-10T05:49:48.836041+00:00",
"lastSyncTime": "2026-09-10T05:49:48.500487+00:00",
"generatedAt": "2026-09-10T05:56:10.537740+00:00",
"lastSyncTime": "2026-09-10T05:56:10.303668+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2153,12 +2153,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 47,
"ambiguous_runtime": 48,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 91,
"failureCount": 92,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2168,8 +2168,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 91,
"unresolvedFailureCount": 47
"total": 92,
"unresolvedFailureCount": 48
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2331,7 +2331,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 140,
"ambiguous_runtime": 141,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2342,15 +2342,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 392,
"failureCount": 393,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 392,
"unresolvedFailureCount": 161
"total": 393,
"unresolvedFailureCount": 162
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2453,7 +2453,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T05:49:48.831661+00:00",
"generatedAt": "2026-09-10T05:56:10.533885+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2737,22 +2737,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 48,
"ambiguous_runtime": 49,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 238,
"failureRate": 0.9482,
"failureCount": 239,
"failureRate": 0.9484,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0518,
"total": 251,
"unresolvedFailureCount": 191
"successRate": 0.0516,
"total": 252,
"unresolvedFailureCount": 192
},
"hygon_k100-ai": {
"attributableFailureCount": 38,
@@ -4421,13 +4421,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 5,
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 10,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4439,8 +4439,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 6
"total": 9,
"unresolvedFailureCount": 5
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4569,21 +4569,21 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 5
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 4
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T00:51:37.399566+00:00",
"lastTerminalAt": "2026-09-10T05:56:10.303668+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4592,7 +4592,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 15
"unresolvedFailureCount": 16
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -6879,15 +6879,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1510,
"totalRecords": 1597,
"terminalRecords": 1511,
"totalRecords": 1598,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 449,
"failureBreakdown": {
"ambiguous_runtime": 291,
"ambiguous_runtime": 292,
"backend_operator": 29,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6899,21 +6899,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1461,
"failureRate": 0.9675,
"failureCount": 1462,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0325,
"total": 1510,
"unresolvedFailureCount": 1059
"successRate": 0.0324,
"total": 1511,
"unresolvedFailureCount": 1060
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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。",
"GPU Iluvatar_mrv-100 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 Ascend_910-b4 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。",
@@ -6921,7 +6921,7 @@
"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 Mthreads_s4000 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 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-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 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -6942,6 +6942,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1597,
"summarizedRecords": 1598,
"version": 1
}

View File

@@ -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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T05:56:10.303668+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477782", "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": "2026-09-10T05:49:48.500487+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:45:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471903", "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": "2026-09-10T05:49:48.500463+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471905", "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": "2026-09-10T05:27:18.447582+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:19:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481721", "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", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:33:34.194592+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T11:19:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4421469", "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": ["LlavaLlamaForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:12:18.209215+00:00", "modelId": "microsoft/llava-med-7b-delta", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T11:03:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079287", "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": ["Phi4FlashForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:12:18.209201+00:00", "modelId": "microsoft/Phi-4-mini-flash-reasoning", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:57:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079234", "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": "2026-09-07T10:52:36.106582+00:00", "modelId": "Qwen/Qwen1.5-1.8B-Chat-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:51:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4591616", "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": "810028a42f85c00b50d0046445a5f62bea9a6959aa18a62e73fc64cb7b24bc53",
".modelhub_state/architecture_history_backfill.json": "fd5e45313adfdb7a02b2e807e8e54fcce86e4b3761ac12f0770c07dc2d8dbe37",
".modelhub_state/market_intelligence.json": "4e4c7f87c52b3664c64066b3d4242e4c06b0a59b6ce3d4d8f1f7f979acec676f",
".modelhub_state/official_capabilities.json": "51599ab6573993995ee8519e7da1943919ba8467285e0b29ff30b9b97accc409",
".modelhub_state/outcome_checkpoint.json": "4a24ece16cd9ab81e05a82f2f92ec5ed16e21c84623a078d2d59482f9b28b660",
".modelhub_state/architecture_compatibility_blacklist.json": "3799f99ffd7619f6e0253a912073d72aba99de5293fc8e3fe017a8d29d7b2817",
".modelhub_state/architecture_history_backfill.json": "957cd5ff49c54828e89f483a2a6a7ca89aadfef40f3eaf963ae51abd2785d973",
".modelhub_state/market_intelligence.json": "0d6ab449a8bdbb5fafe0f2bafa71a9387803a0fd892a2683c3e0943ac5bbd763",
".modelhub_state/official_capabilities.json": "ea4e38992685116fd5dad883b00472922e811468a72112e226c41a695a034ef8",
".modelhub_state/outcome_checkpoint.json": "d3c796360452c81fea3db2b995a2e745a03dfccf3b9d0c7fada3194ac234a341",
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
".modelhub_state/recent_outcomes.jsonl": "9fbb92f0c6141cac281c5ef2fb77cc3a0730dd2b93034886348e899fb7cb40b9",
".modelhub_state/recovery_active_tasks.jsonl": "2bf096e23f78912ed6b53f4518ddda9d0d880b413da971e62d2894b102a5b2d1",
".modelhub_state/recovery_intents.jsonl": "36abce00437be2ea12ee5662fcb96492c90ba5dac2397a1d03c4b427346e4f65",
".modelhub_state/recent_outcomes.jsonl": "2de4abdb11aac7494df688e37d611995b5daa15ca3d778b109947bb2c6a3e78c",
".modelhub_state/recovery_active_tasks.jsonl": "95fde1b1873a925d0971bcbd23b11a0f9cd59b0e2df38048dbc6982cf057476a",
".modelhub_state/recovery_intents.jsonl": "40b62437f2def05bcac1822718f42e89fca5c57bfe58849d1cab8f07cb29253f",
".modelhub_state/routing_intelligence.json": "3bdff6c7dcd8d22cbbec51b438718a72cd7e92f73943dc4ff5b0a2b89cfab357",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "57af2196d56a3adcab8966bc608170a23d12e536b1ed4f85b420e201f6b03dc9",
"outcomes/submissions.jsonl": "782b764c8224e5fe77fbbf7718e8c6ffc31592db26598190c994c04a0b3d2038"
},
"generation": 4993,
"generation": 4994,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T05:56:07.627438+00:00",
"updatedAt": "2026-09-10T05:57:57.744614+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}