state: generation 4914 (cycle)

This commit is contained in:
2026-09-10 02:51:55 +00:00
parent e294460c01
commit b27ce1ff1b
9 changed files with 2027 additions and 2029 deletions

View File

@@ -1306,7 +1306,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-10T02:49:11.558903+00:00", "generatedAt": "2026-09-10T02:51:54.714862+00:00",
"summary": { "summary": {
"activeBlockCount": 65, "activeBlockCount": 65,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": { "10": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 349, "listingErrors": 350,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 10, "nextAccountIndex": 11,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-10T02:49:11.533262+00:00", "updatedAt": "2026-09-10T02:51:54.688811+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T02:47:27.736389+00:00", "generatedAt": "2026-09-10T02:50:18.560416+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-10T02:40:45.261552+00:00", "generatedAt": "2026-09-10T02:50:12.530651+00:00",
"lastSyncTime": "2026-09-10T02:40:44.943974+00:00", "lastSyncTime": "2026-09-10T02:50:12.317776+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1786,29 +1786,29 @@
"unresolvedFailureCount": 7 "unresolvedFailureCount": 7
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 67, "attributableFailureCount": 68,
"decisionFailureRate": 0.8701, "decisionFailureRate": 0.8718,
"decisionSuccessRate": 0.1299, "decisionSuccessRate": 0.1282,
"decisionTotal": 77, "decisionTotal": 78,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 17, "ambiguous_runtime": 17,
"framework_architecture_unsupported": 44, "framework_architecture_unsupported": 45,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 22, "model_load": 22,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 133, "failureCount": 134,
"failureRate": 0.9301, "failureRate": 0.9306,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 10, "successCount": 10,
"successRate": 0.0699, "successRate": 0.0694,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 143, "total": 144,
"unresolvedFailureCount": 66 "unresolvedFailureCount": 66
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
@@ -2224,14 +2224,14 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 35, "decisionTotal": 35,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7, "ambiguous_runtime": 8,
"framework_architecture_unsupported": 27, "framework_architecture_unsupported": 27,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 3, "model_load": 3,
"repository_structure": 3, "repository_structure": 3,
"runtime_memory": 1 "runtime_memory": 1
}, },
"failureCount": 42, "failureCount": 43,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -2241,8 +2241,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 42, "total": 43,
"unresolvedFailureCount": 7 "unresolvedFailureCount": 8
} }
}, },
"frameworkSummaries": { "frameworkSummaries": {
@@ -2284,28 +2284,28 @@
"unresolvedFailureCount": 5 "unresolvedFailureCount": 5
}, },
"unknown": { "unknown": {
"attributableFailureCount": 119, "attributableFailureCount": 120,
"decisionFailureRate": 0.7126, "decisionFailureRate": 0.7143,
"decisionSuccessRate": 0.2874, "decisionSuccessRate": 0.2857,
"decisionTotal": 167, "decisionTotal": 168,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 101, "ambiguous_runtime": 101,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 85, "framework_architecture_unsupported": 86,
"memory_capacity": 5, "memory_capacity": 5,
"model_load": 24, "model_load": 24,
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 56, "参数/模板问题": 56,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 949, "failureCount": 950,
"failureRate": 0.9519, "failureRate": 0.9519,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 48, "successCount": 48,
"successRate": 0.0481, "successRate": 0.0481,
"total": 997, "total": 998,
"unresolvedFailureCount": 830 "unresolvedFailureCount": 830
}, },
"vllm": { "vllm": {
@@ -2314,7 +2314,7 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 227, "decisionTotal": 227,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 130, "ambiguous_runtime": 131,
"backend_operator": 22, "backend_operator": 22,
"framework_architecture_unsupported": 168, "framework_architecture_unsupported": 168,
"memory_capacity": 6, "memory_capacity": 6,
@@ -2325,15 +2325,15 @@
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 21 "参数/模板问题": 21
}, },
"failureCount": 379, "failureCount": 380,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 379, "total": 380,
"unresolvedFailureCount": 151 "unresolvedFailureCount": 152
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-10T02:40:45.256871+00:00", "generatedAt": "2026-09-10T02:50:12.526687+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2599,26 +2599,26 @@
"unresolvedFailureCount": 41 "unresolvedFailureCount": 41
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 67, "attributableFailureCount": 68,
"decisionFailureRate": 0.8701, "decisionFailureRate": 0.8718,
"decisionSuccessRate": 0.1299, "decisionSuccessRate": 0.1282,
"decisionTotal": 77, "decisionTotal": 78,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 17, "ambiguous_runtime": 17,
"framework_architecture_unsupported": 44, "framework_architecture_unsupported": 45,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 22, "model_load": 22,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 133, "failureCount": 134,
"failureRate": 0.9301, "failureRate": 0.9306,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 10, "successCount": 10,
"successRate": 0.0699, "successRate": 0.0694,
"total": 143, "total": 144,
"unresolvedFailureCount": 66 "unresolvedFailureCount": 66
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -2743,7 +2743,7 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 38, "decisionTotal": 38,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 9, "ambiguous_runtime": 10,
"framework_architecture_unsupported": 30, "framework_architecture_unsupported": 30,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 3, "model_load": 3,
@@ -2752,15 +2752,15 @@
"参数/模板问题": 8, "参数/模板问题": 8,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 82, "failureCount": 83,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 82, "total": 83,
"unresolvedFailureCount": 44 "unresolvedFailureCount": 45
} }
}, },
"observedGpuMemoryGiB": { "observedGpuMemoryGiB": {
@@ -4199,7 +4199,7 @@
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0, "decisionSuccessRate": 1.0,
"decisionTotal": 2, "decisionTotal": 1,
"failureBreakdown": {}, "failureBreakdown": {},
"failureCount": 0, "failureCount": 0,
"failureRate": 0.0, "failureRate": 0.0,
@@ -4209,11 +4209,11 @@
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 1,
"successRate": 1.0, "successRate": 1.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Iluvatar_bi-150|vllm|text-generation": { "Iluvatar_bi-150|vllm|text-generation": {
@@ -4224,11 +4224,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 4, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 6, "ambiguous_runtime": 5,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 2 "framework_architecture_unsupported": 2
}, },
"failureCount": 10, "failureCount": 9,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -4240,26 +4240,26 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 10, "total": 9,
"unresolvedFailureCount": 6 "unresolvedFailureCount": 5
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15, "attributableFailureCount": 15,
"consecutiveFailures": 0, "consecutiveFailures": 1,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8333, "decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667, "decisionSuccessRate": 0.1667,
"decisionTotal": 18, "decisionTotal": 18,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2, "ambiguous_runtime": 2,
"framework_architecture_unsupported": 8, "framework_architecture_unsupported": 9,
"model_load": 7 "model_load": 6
}, },
"failureCount": 17, "failureCount": 17,
"failureRate": 0.85, "failureRate": 0.85,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:40:44.943952+00:00", "lastTerminalAt": "2026-09-10T02:50:12.317748+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4633,16 +4633,16 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 10, "decisionTotal": 10,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 6, "ambiguous_runtime": 7,
"framework_architecture_unsupported": 8, "framework_architecture_unsupported": 8,
"model_load": 1, "model_load": 1,
"repository_structure": 1 "repository_structure": 1
}, },
"failureCount": 16, "failureCount": 17,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T22:06:26.296264+00:00", "lastTerminalAt": "2026-09-10T02:50:12.317776+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4650,8 +4650,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 16, "total": 17,
"unresolvedFailureCount": 6 "unresolvedFailureCount": 7
} }
}, },
"recentProfileCombinationStats": { "recentProfileCombinationStats": {
@@ -6764,17 +6764,17 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1488, "terminalRecords": 1490,
"totalRecords": 1572, "totalRecords": 1574,
"totals": { "totals": {
"attributableFailureCount": 393, "attributableFailureCount": 394,
"decisionFailureRate": 0.8891, "decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1109, "decisionSuccessRate": 0.1106,
"decisionTotal": 442, "decisionTotal": 443,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 277, "ambiguous_runtime": 278,
"backend_operator": 25, "backend_operator": 25,
"framework_architecture_unsupported": 268, "framework_architecture_unsupported": 269,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 46, "model_load": 46,
"platform_infrastructure": 2, "platform_infrastructure": 2,
@@ -6784,21 +6784,21 @@
"参数/模板问题": 94, "参数/模板问题": 94,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1439, "failureCount": 1441,
"failureRate": 0.9671, "failureRate": 0.9671,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 49, "successCount": 49,
"successRate": 0.0329, "successRate": 0.0329,
"total": 1488, "total": 1490,
"unresolvedFailureCount": 1044 "unresolvedFailureCount": 1045
}, },
"warnings": [ "warnings": [
"GPU Cambricon_mlu-370-x8 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 Ascend_910-b3 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_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 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 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 MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
@@ -6806,7 +6806,7 @@
"GPU hygon_k100-ai 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 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 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 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 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。", "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。",
@@ -6827,6 +6827,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1572, "summarizedRecords": 1574,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-10T02:50:12.317776+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:43:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493607", "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": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-10T02:50:12.317748+00:00", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4271675", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943952+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-10T02:37:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483083", "taskType": "text-generation", "verifyResult": 1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943952+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-10T02:37:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483083", "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": "2026-09-10T02:40:44.943965+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483082", "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": "2026-09-10T02:40:44.943965+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483082", "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": "2026-09-10T02:40:44.943974+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:35:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496938", "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": "2026-09-10T02:40:44.943974+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:35:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496938", "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": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T08:04:59.604222+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464045", "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": "2026-09-07T08:04:59.604222+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464045", "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": "2026-09-07T07:41:41.205199+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:33:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4459518", "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": "2026-09-07T07:41:41.205199+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:33:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4459518", "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": "2026-09-07T07:41:41.205155+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4461223", "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": "2026-09-07T07:41:41.205155+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4461223", "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": "2026-09-07T07:41:41.205219+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:09:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4462454", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T07:06:44.706649+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T06:49:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4461327", "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", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "01f21cd1b84e93d8b698976aadf8744707f95059d15e3c05c67bae09ffc212cb", ".modelhub_state/architecture_compatibility_blacklist.json": "7bc5b05e973b695401df99950ba71fc377e2ec2efe7ca40b7d371c13d2f522ea",
".modelhub_state/architecture_history_backfill.json": "06dfd846a79a0c592cb5d39e413b336c634194cc54da9ba3f7d5a6273e29ecf0", ".modelhub_state/architecture_history_backfill.json": "fc341e2136e9d251862be112cd970eff423cebb62abf91cd44aa1bcc9c838a87",
".modelhub_state/market_intelligence.json": "1ceb1563a0c3d29c1ca8c1368b4395ad86459ecb55649b70ca9ef60a3fde89ca", ".modelhub_state/market_intelligence.json": "f7d98e3ce53cd67e13ca677240b6bdf0fb087ec57f4077e6cd1493b117cddfea",
".modelhub_state/official_capabilities.json": "18a594a9fbe61a0a732225771d88a17e5b8cccf9b2ae4eae159dfa9860e0a329", ".modelhub_state/official_capabilities.json": "5d624a0aa28c8da46f7010a6b238c0bfb4a1a355d5fa146c7381f06f0793f568",
".modelhub_state/outcome_checkpoint.json": "ac0353427edef1545dcbb1f08137eac5a0602613b527249bd0c8b9a3a732dd20", ".modelhub_state/outcome_checkpoint.json": "53509b2d33fefbdbfe56392f582c2983abf0c282535c6ce09f7b6c19fa9fc167",
".modelhub_state/queue_cleanup_latest.json": "1ff9cf1dcc1b2c2557b532394e1e76da55fa710317d6832581664c56c6ecc7b3", ".modelhub_state/queue_cleanup_latest.json": "1ff9cf1dcc1b2c2557b532394e1e76da55fa710317d6832581664c56c6ecc7b3",
".modelhub_state/recent_outcomes.jsonl": "0fb15bca34e7b5f483d04fae8ac20b0e13f58c22111d8116b7b176ca2e6288a2", ".modelhub_state/recent_outcomes.jsonl": "fe1ad7982be490a4b6861efe900a7d2823ce6b804550372dc799712794aa2fc8",
".modelhub_state/recovery_active_tasks.jsonl": "20dc43166e965862c06fd9df9cb8f485a1aff97f13646acb29b8b81e2fe7288f", ".modelhub_state/recovery_active_tasks.jsonl": "7b54a6eda8bb505b3ff58f8b327f24ddd02508a4d8469010e12343fef594bfc4",
".modelhub_state/recovery_intents.jsonl": "a11e1e072f133e7b1df4a12b1d33e45b795461cc19807d721406a878bbdb0799", ".modelhub_state/recovery_intents.jsonl": "93ea7698c3fef30a3e86945873f7f0d7e10b3b0b014ef865aa7960a858cf8e1f",
".modelhub_state/routing_intelligence.json": "289584603011b6a895f3ab1c0b743c174293ab94ad8d2f1f5a3531e01a72207b", ".modelhub_state/routing_intelligence.json": "289584603011b6a895f3ab1c0b743c174293ab94ad8d2f1f5a3531e01a72207b",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76", ".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "d242179d528ce949e36ac1834a20e4f46e6d5194c7a834b19b8e1b58d9a1bea6", "ledger/submissions.jsonl": "d242179d528ce949e36ac1834a20e4f46e6d5194c7a834b19b8e1b58d9a1bea6",
"outcomes/submissions.jsonl": "aa4777b88adb640cc19bee1b1611d6a4701b470fc709ec54f48c2db876528cb5" "outcomes/submissions.jsonl": "aa4777b88adb640cc19bee1b1611d6a4701b470fc709ec54f48c2db876528cb5"
}, },
"generation": 4913, "generation": 4914,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-10T02:49:11.633664+00:00", "updatedAt": "2026-09-10T02:51:55.283006+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977" "writerId": "58ff5dc2a2d64b119ad1e4560700f977"
} }