state: generation 5660 (cycle)

This commit is contained in:
2026-09-11 11:11:01 +00:00
parent b915850643
commit 8344778192
9 changed files with 2146 additions and 2146 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-11T11:07:14.094437+00:00", "generatedAt": "2026-09-11T11:11:00.861815+00:00",
"summary": { "summary": {
"activeBlockCount": 66, "activeBlockCount": 66,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": { "5": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 405, "listingErrors": 406,
"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": 5, "nextAccountIndex": 6,
"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": "2026-09-11T11:07:14.071046+00:00", "updatedAt": "2026-09-11T11:11:00.838282+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T11:05:01.898930+00:00", "generatedAt": "2026-09-11T11:08:21.136453+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": "2026-09-11T07:43:04.447309+00:00", "generatedAt": "2026-09-11T11:08:15.025709+00:00",
"lastSyncTime": "2026-09-11T07:43:04.407471+00:00", "lastSyncTime": "2026-09-11T11:08:14.809954+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2042,17 +2042,17 @@
"unresolvedFailureCount": 33 "unresolvedFailureCount": 33
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 35, "attributableFailureCount": 36,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 35, "decisionTotal": 36,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 2, "framework_architecture_unsupported": 2,
"platform_infrastructure": 2, "platform_infrastructure": 2,
"tokenizer_compatibility": 33, "tokenizer_compatibility": 34,
"参数/模板问题": 6 "参数/模板问题": 6
}, },
"failureCount": 43, "failureCount": 44,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -2062,7 +2062,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 43, "total": 44,
"unresolvedFailureCount": 6 "unresolvedFailureCount": 6
}, },
"Sunrise_pt-200-x1|vllm|text-generation": { "Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2401,26 +2401,26 @@
"unresolvedFailureCount": 4 "unresolvedFailureCount": 4
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"attributableFailureCount": 38, "attributableFailureCount": 39,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 38, "decisionTotal": 39,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 36, "ambiguous_runtime": 36,
"framework_architecture_unsupported": 4, "framework_architecture_unsupported": 4,
"model_load": 1, "model_load": 1,
"platform_infrastructure": 2, "platform_infrastructure": 2,
"tokenizer_compatibility": 33, "tokenizer_compatibility": 34,
"参数/模板问题": 7 "参数/模板问题": 7
}, },
"failureCount": 83, "failureCount": 84,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 83, "total": 84,
"unresolvedFailureCount": 43 "unresolvedFailureCount": 43
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
@@ -2442,7 +2442,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-11T07:43:04.442818+00:00", "generatedAt": "2026-09-11T11:08:15.021564+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2700,26 +2700,26 @@
"unresolvedFailureCount": 77 "unresolvedFailureCount": 77
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"attributableFailureCount": 36, "attributableFailureCount": 37,
"decisionFailureRate": 0.973, "decisionFailureRate": 0.9737,
"decisionSuccessRate": 0.027, "decisionSuccessRate": 0.0263,
"decisionTotal": 37, "decisionTotal": 38,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 3, "framework_architecture_unsupported": 3,
"platform_infrastructure": 3, "platform_infrastructure": 3,
"tokenizer_compatibility": 33, "tokenizer_compatibility": 34,
"参数/模板问题": 9, "参数/模板问题": 9,
"验证失败": 32 "验证失败": 32
}, },
"failureCount": 81, "failureCount": 82,
"failureRate": 0.9878, "failureRate": 0.988,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 1, "successCount": 1,
"successRate": 0.0122, "successRate": 0.012,
"total": 82, "total": 83,
"unresolvedFailureCount": 42 "unresolvedFailureCount": 42
}, },
"Vastai_va16": { "Vastai_va16": {
@@ -4321,10 +4321,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 6, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3, "ambiguous_runtime": 2,
"framework_architecture_unsupported": 6 "framework_architecture_unsupported": 6
}, },
"failureCount": 9, "failureCount": 8,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -4336,8 +4336,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 9, "total": 8,
"unresolvedFailureCount": 3 "unresolvedFailureCount": 2
}, },
"Mthreads_s4000|llamacpp|text-generation": { "Mthreads_s4000|llamacpp|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -4415,22 +4415,22 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 14, "attributableFailureCount": 15,
"consecutiveFailures": 14, "consecutiveFailures": 15,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 14, "decisionTotal": 15,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 1, "framework_architecture_unsupported": 1,
"platform_infrastructure": 2, "platform_infrastructure": 2,
"tokenizer_compatibility": 13 "tokenizer_compatibility": 14
}, },
"failureCount": 16, "failureCount": 17,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00", "lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-10T16:05:31.804335+00:00", "lastTerminalAt": "2026-09-11T11:08:14.809954+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
@@ -4438,7 +4438,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 16, "total": 17,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation": { "Sunrise_pt-200-x1|vllm|text-generation": {
@@ -6936,13 +6936,13 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1650, "terminalRecords": 1651,
"totalRecords": 1737, "totalRecords": 1738,
"totals": { "totals": {
"attributableFailureCount": 430, "attributableFailureCount": 431,
"decisionFailureRate": 0.8903, "decisionFailureRate": 0.8905,
"decisionSuccessRate": 0.1097, "decisionSuccessRate": 0.1095,
"decisionTotal": 483, "decisionTotal": 484,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 391, "ambiguous_runtime": 391,
"backend_operator": 40, "backend_operator": 40,
@@ -6952,34 +6952,35 @@
"platform_infrastructure": 4, "platform_infrastructure": 4,
"repository_structure": 5, "repository_structure": 5,
"runtime_memory": 6, "runtime_memory": 6,
"tokenizer_compatibility": 39, "tokenizer_compatibility": 40,
"参数/模板问题": 99, "参数/模板问题": 99,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1597, "failureCount": 1598,
"failureRate": 0.9679, "failureRate": 0.9679,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 53, "successCount": 53,
"successRate": 0.0321, "successRate": 0.0321,
"total": 1650, "total": 1651,
"unresolvedFailureCount": 1163 "unresolvedFailureCount": 1163
}, },
"warnings": [ "warnings": [
"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 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 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 Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。", "GPU 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 Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -6994,11 +6995,10 @@
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。" "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1737, "summarizedRecords": 1738,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T11:08:14.809954+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457994", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T07:43:04.407471+00:00", "modelId": "deepreinforce-ai/Ornith-1.0-35B-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T07:38:33+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079996", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T07:43:04.407471+00:00", "modelId": "deepreinforce-ai/Ornith-1.0-35B-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T07:38:33+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079996", "taskType": "text-generation", "verifyResult": null}
{"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": "2026-09-11T07:33:47.206168+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523220", "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": "2026-09-11T07:33:47.206168+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523220", "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": "2026-09-11T07:24:30.143494+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505135", "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": "2026-09-11T07:24:30.143494+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505135", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T08:12:43.104862+00:00", "modelId": "amd/Qwen2.5_3B_Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:01:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079942", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T08:12:43.104862+00:00", "modelId": "amd/Qwen2.5_3B_Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:01:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079942", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T08:12:43.104895+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4494268", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T08:12:43.104895+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4494268", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T08:12:43.104903+00:00", "modelId": "nightmedia/Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080014", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T08:12:43.104903+00:00", "modelId": "nightmedia/Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080014", "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": "2026-09-08T07:47:20.009376+00:00", "modelId": "ModelCloud.AI/Marin-32B-Base-GPTQMODEL-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:41:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079069", "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": "ba5d7ba29633549b8e723e0ca2ba92add7952717b88aff879bec7fd236a58db1", ".modelhub_state/architecture_compatibility_blacklist.json": "dd23d4353ab82b28f38a4006793863533d8e09423dc96f7b83ced3ef254e9646",
".modelhub_state/architecture_history_backfill.json": "4e66b03ae9ac554d49f4efa8306aafbfd76da3942d344a889de488c87be4c3e9", ".modelhub_state/architecture_history_backfill.json": "0440a3f1db793459e6570752865aaa45c7b9fb4f0df283f56ef721f0a0c35c81",
".modelhub_state/market_intelligence.json": "2c8edc6de45de73fd1296f9e04098edacc91438857f657addb4523dc880001c3", ".modelhub_state/market_intelligence.json": "80ab18261a5c2cce68425c916fc133e7e911fee42d76917e6440901a9e051c62",
".modelhub_state/official_capabilities.json": "5d557f6e972bea8a35e4080530202935f5bb1282553c4f38cd2e9d53d6d7e721", ".modelhub_state/official_capabilities.json": "259c7e6a7e6dfe37ea00161c6d7309c2c07b0b63e5f319f155fbb76ab624ca26",
".modelhub_state/outcome_checkpoint.json": "502057f7f506ac7aea6130b20a3b225f6ccc1510a86779ebe5ce5ccdc1aaef13", ".modelhub_state/outcome_checkpoint.json": "738daae4d96f6b15097c7b1f7fd5c71771c203d17ce6790817773561e9ecdd41",
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b", ".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
".modelhub_state/recent_outcomes.jsonl": "a33ccc3fa6f0a8d1f1c645ff6013256fc4a07ac5401bd607a08dfae424e4f02e", ".modelhub_state/recent_outcomes.jsonl": "daca771dc12e1867e50ad6c80abfb423333720a8917956d9ad25d12ea685b2e7",
".modelhub_state/recovery_active_tasks.jsonl": "60a91ebf1e77523321810b6cde02a5d7a45f2ad34dd3d2f9e6f7bea56789d3c7", ".modelhub_state/recovery_active_tasks.jsonl": "bee434f77691735f87dda66f8405dedc239866e1389983caf4b6a65baabc2527",
".modelhub_state/recovery_intents.jsonl": "01375a1ade080c6ed3fe69a2ab0ed538641c2ad91c474c402a348c2d6b399a2d", ".modelhub_state/recovery_intents.jsonl": "c64bfa0762191e311a9b430311825ea56c28dd0c3fc574f83d6e914fea5e5f94",
".modelhub_state/routing_intelligence.json": "01755a7ae15e8408cf0586a62b0684ec4e7e2d46c2715b9b2bfe968c7d40353e", ".modelhub_state/routing_intelligence.json": "01755a7ae15e8408cf0586a62b0684ec4e7e2d46c2715b9b2bfe968c7d40353e",
".modelhub_state/submission_exclusions.jsonl": "3790b5c148f222a4de26d50a3d8afc58891c8da251a82d20dbaf4fc35e6dbd89", ".modelhub_state/submission_exclusions.jsonl": "3790b5c148f222a4de26d50a3d8afc58891c8da251a82d20dbaf4fc35e6dbd89",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba", ".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "0f2922a5f34c5777fcbb7e7ea1512bd1784eed2b74f5d6c3f05103cb3bbea37e", "ledger/submissions.jsonl": "0f2922a5f34c5777fcbb7e7ea1512bd1784eed2b74f5d6c3f05103cb3bbea37e",
"outcomes/submissions.jsonl": "9b436339a59d073250c1f14e08f71c1148a29e5b3db2301e39b71ed36893e02b" "outcomes/submissions.jsonl": "9b436339a59d073250c1f14e08f71c1148a29e5b3db2301e39b71ed36893e02b"
}, },
"generation": 5659, "generation": 5660,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-11T11:07:14.168220+00:00", "updatedAt": "2026-09-11T11:11:01.737299+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42" "writerId": "18252d8a8ef94333abd55823b2d81c42"
} }