state: generation 5155 (cycle)

This commit is contained in:
2026-09-10 12:16:54 +00:00
parent 12bf25197e
commit 336957ac17
10 changed files with 1999 additions and 1975 deletions

View File

@@ -1313,7 +1313,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T12:14:13.612817+00:00",
"generatedAt": "2026-09-10T12:16:53.612470+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -75,7 +75,7 @@
"7": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 366,
"listingErrors": 367,
"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": 7,
"nextAccountIndex": 8,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T12:14:13.588711+00:00",
"updatedAt": "2026-09-10T12:16:53.586060+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T12:11:48.057472+00:00",
"generatedAt": "2026-09-10T12:15:21.497713+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": "2026-09-10T12:06:09.429869+00:00",
"lastSyncTime": "2026-09-10T12:06:09.109223+00:00",
"generatedAt": "2026-09-10T12:15:14.576026+00:00",
"lastSyncTime": "2026-09-10T12:15:14.346623+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1793,29 +1793,29 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 70,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 80,
"attributableFailureCount": 71,
"decisionFailureRate": 0.8765,
"decisionSuccessRate": 0.1235,
"decisionTotal": 81,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 46,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 23,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 136,
"failureRate": 0.9315,
"failureCount": 137,
"failureRate": 0.932,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0685,
"successRate": 0.068,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 146,
"total": 147,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -1868,10 +1868,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 29,
"参数/模板问题": 1
},
"failureCount": 29,
"failureCount": 30,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1881,8 +1881,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 29,
"unresolvedFailureCount": 29
"total": 30,
"unresolvedFailureCount": 30
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2008,9 +2008,10 @@
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 2
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 59,
"failureCount": 62,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2020,8 +2021,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 59,
"unresolvedFailureCount": 27
"total": 62,
"unresolvedFailureCount": 30
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2292,28 +2293,28 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 123,
"decisionFailureRate": 0.7193,
"decisionSuccessRate": 0.2807,
"decisionTotal": 171,
"attributableFailureCount": 124,
"decisionFailureRate": 0.7209,
"decisionSuccessRate": 0.2791,
"decisionTotal": 172,
"failureBreakdown": {
"ambiguous_runtime": 115,
"backend_operator": 3,
"framework_architecture_unsupported": 87,
"framework_architecture_unsupported": 88,
"memory_capacity": 5,
"model_load": 25,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 967,
"failureRate": 0.9527,
"failureCount": 968,
"failureRate": 0.9528,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0473,
"total": 1015,
"successRate": 0.0472,
"total": 1016,
"unresolvedFailureCount": 844
},
"vllm": {
@@ -2331,17 +2332,17 @@
"repository_structure": 5,
"runtime_memory": 5,
"tokenizer_compatibility": 3,
"参数/模板问题": 21
"参数/模板问题": 24
},
"failureCount": 424,
"failureRate": 0.9976,
"failureCount": 427,
"failureRate": 0.9977,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 425,
"unresolvedFailureCount": 188
"successRate": 0.0023,
"total": 428,
"unresolvedFailureCount": 191
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2408,22 +2409,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 29,
"ambiguous_runtime": 30,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 32,
"参数/模板问题": 7
},
"failureCount": 75,
"failureCount": 76,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 75,
"unresolvedFailureCount": 36
"total": 76,
"unresolvedFailureCount": 37
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2444,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T12:06:09.421970+00:00",
"generatedAt": "2026-09-10T12:15:14.571193+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2607,26 +2608,26 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 70,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 80,
"attributableFailureCount": 71,
"decisionFailureRate": 0.8765,
"decisionSuccessRate": 0.1235,
"decisionTotal": 81,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 46,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 23,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 136,
"failureRate": 0.9315,
"failureCount": 137,
"failureRate": 0.932,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0685,
"total": 146,
"successRate": 0.068,
"total": 147,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -2635,20 +2636,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 60,
"ambiguous_runtime": 61,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 85,
"failureCount": 86,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 85,
"unresolvedFailureCount": 84
"total": 86,
"unresolvedFailureCount": 85
},
"MetaX_c-500": {
"attributableFailureCount": 42,
@@ -2687,18 +2688,18 @@
"model_load": 3,
"repository_structure": 1,
"runtime_memory": 2,
"参数/模板问题": 7,
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 93,
"failureRate": 0.9789,
"failureCount": 96,
"failureRate": 0.9796,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0211,
"total": 95,
"unresolvedFailureCount": 60
"successRate": 0.0204,
"total": 98,
"unresolvedFailureCount": 63
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 35,
@@ -3482,9 +3483,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "starcoder2",
@@ -3496,8 +3497,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"MetaX_c-500|vllm|text-generation|aquila3|none": {
"attributableFailureCount": 0,
@@ -4250,7 +4251,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
"consecutiveFailures": 3,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8421,
"decisionSuccessRate": 0.1579,
@@ -4264,7 +4265,7 @@
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T12:06:09.109223+00:00",
"lastTerminalAt": "2026-09-10T12:15:14.346623+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6214,6 +6215,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7005,41 +7030,41 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1572,
"totalRecords": 1659,
"terminalRecords": 1577,
"totalRecords": 1664,
"totals": {
"attributableFailureCount": 412,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 463,
"attributableFailureCount": 413,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 464,
"failureBreakdown": {
"ambiguous_runtime": 338,
"ambiguous_runtime": 339,
"backend_operator": 35,
"framework_architecture_unsupported": 271,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 47,
"platform_infrastructure": 3,
"repository_structure": 5,
"runtime_memory": 5,
"tokenizer_compatibility": 38,
"参数/模板问题": 95,
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1521,
"failureRate": 0.9676,
"failureCount": 1526,
"failureRate": 0.9677,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0324,
"total": 1572,
"unresolvedFailureCount": 1106
"successRate": 0.0323,
"total": 1577,
"unresolvedFailureCount": 1110
},
"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 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。",
"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。",
@@ -7047,7 +7072,7 @@
"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 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。",
"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。",
@@ -7068,6 +7093,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1659,
"summarizedRecords": 1664,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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_moe"], "framework": "", "lastSyncTime": "2026-09-10T12:15:14.346623+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4463766", "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": "2026-09-10T12:06:09.109223+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523306", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T12:06:09.109198+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:03:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490278", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T11:57:54.623286+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:53:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610381", "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"], "framework": "", "lastSyncTime": "2026-09-07T23:43:05.101227+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:35:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332996", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-07T23:33:45.147699+00:00", "modelId": "mlx-community/Qwen-AgentWorld-35B-A3B-oQ4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:31:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080039", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-09-07T23:33:45.147733+00:00", "modelId": "kurakurai/Luth-LFM2-700M-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:31:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "3986792", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-07T23:33:45.147723+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332995", "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": "46bac041c23131ee7725876fd2a47a461189af2b875c05efe2e61e8509f52d94",
".modelhub_state/architecture_history_backfill.json": "66fb87c1f7cf26752eb376c80227f82d7fafd41f4f4cac5dceeee5b34bce011d",
".modelhub_state/market_intelligence.json": "cffd79ebb4541c5d9959d7f72f7fbf25d948621ea6f19c1dd09a9ef72f283c22",
".modelhub_state/official_capabilities.json": "bc6b206b3b2905f6fc75a4641c8031fd28ba3c2abd3464b9462410c8958ca122",
".modelhub_state/outcome_checkpoint.json": "f70df639228afadcc434c5740d4bc3c8299e4938de374429b87ccac3316d76c3",
".modelhub_state/architecture_compatibility_blacklist.json": "19a48d45216c50e6e86b0be930f5a4ac42044e508099fa4d4589e12dac46d0a7",
".modelhub_state/architecture_history_backfill.json": "c22c6f52017fbad7bd410a9116a636c307acf643ec1b2271332b76d0d6fa0522",
".modelhub_state/market_intelligence.json": "60f3c6701e14da3a6f7fcbe935c1fd3a32890215618fd5eab24e6ef773d892e5",
".modelhub_state/official_capabilities.json": "80d0f6f32de4f9035b9337a061bed32269d0ad3199cc288460a93a7195b2f6a1",
".modelhub_state/outcome_checkpoint.json": "19c82fc3ed0bbec6649a7b306f79c755b2d17a18aab1a8e388d84ca6ff383083",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "6d878b8b8aac1da3ee9e17bb4b67e245778c2ab336e44c9ae4ef80d49597916b",
".modelhub_state/recovery_active_tasks.jsonl": "7106eedc75cbad87e864f49eac2a423d8bb6b35335d5ce930c8532a6c4d10bc0",
".modelhub_state/recovery_intents.jsonl": "454118b75f1a473e9e1698927828fed2179216993d9449b1e72dcd0d05599052",
".modelhub_state/recent_outcomes.jsonl": "45ba37ec5777429da69b691166827644a7b83eaa6ffe42c2d4244d2a73a78c6d",
".modelhub_state/recovery_active_tasks.jsonl": "ded87b4b5919ac33f02c27882d2c639f5444c3dd923923434c0027093700c4d0",
".modelhub_state/recovery_intents.jsonl": "9c8d17ad30f0963b11d9a5d4e81699a75f241c6e7015fd9c2ed0c36424773a39",
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "8a621da5637d481c7de4b4e3375f2a68cbdabf71fe459244a727034f36ab3eb9",
"outcomes/submissions.jsonl": "eaa6922265ab874d46282c8353419da53665ddca2baca53c5b4240e410666d50"
"outcomes/submissions.jsonl": "3dc7b0773d134ec492c2a72ee218f706b6cf17ad01cb3d1e32a072f37b533130"
},
"generation": 5154,
"generation": 5155,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T12:14:13.684370+00:00",
"updatedAt": "2026-09-10T12:16:54.277840+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}

View File

@@ -198,7 +198,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613090+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:01:57.388649+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:33:26.815214+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22109595640, "estimatedRequiredGiB": 24.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22137550529, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 20921584848, "modelscopeTags": ["license:Apache License 2.0", "model_type:gpt_oss", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "mxfp4", "repositoryOnDiskBytes": 22137550529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:32:32.785339+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668538", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806846+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679220993, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679220993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806776+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:34:13.216402+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668650", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399910+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:05:58.785747+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669358", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399880+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:07:54.384483+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669411", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T00:59:44.608188+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "verifyResult": null}