state: generation 5093 (cycle)

This commit is contained in:
2026-09-10 09:22:52 +00:00
parent 7e21cdff9b
commit a976778853
9 changed files with 2055 additions and 2055 deletions

View File

@@ -1317,7 +1317,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-10T09:19:49.496645+00:00", "generatedAt": "2026-09-10T09:22:52.164069+00:00",
"summary": { "summary": {
"activeBlockCount": 66, "activeBlockCount": 66,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -75,7 +75,7 @@
"7": { "7": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 361, "listingErrors": 362,
"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": 7, "nextAccountIndex": 8,
"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": "2026-09-10T09:19:49.473853+00:00", "updatedAt": "2026-09-10T09:22:52.139835+00:00",
"version": 1 "version": 1
} }

View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-09-10T09:02:53.627910+00:00", "communityAttemptedAt": "2026-09-10T09:20:57.005650+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-09-10T09:02:53.627910+00:00", "communityUpdatedAt": "2026-09-10T09:20:57.005650+00:00",
"frameworkAttemptedAt": "2026-09-10T06:33:41.338309+00:00", "frameworkAttemptedAt": "2026-09-10T06:33:41.338309+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T09:17:44.464633+00:00", "generatedAt": "2026-09-10T09:20:57.005650+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": "2026-09-10T08:54:23.705220+00:00", "generatedAt": "2026-09-10T09:20:50.642259+00:00",
"lastSyncTime": "2026-09-10T08:54:23.346315+00:00", "lastSyncTime": "2026-09-10T09:20:50.207436+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1390,12 +1390,12 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 26, "decisionTotal": 26,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 22, "ambiguous_runtime": 23,
"framework_architecture_unsupported": 24, "framework_architecture_unsupported": 24,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1 "tokenizer_compatibility": 1
}, },
"failureCount": 48, "failureCount": 49,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -1405,8 +1405,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 48, "total": 49,
"unresolvedFailureCount": 22 "unresolvedFailureCount": 23
}, },
"Ascend_910-b4|llamacpp|text-generation": { "Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -1503,7 +1503,7 @@
"decisionSuccessRate": 0.04, "decisionSuccessRate": 0.04,
"decisionTotal": 25, "decisionTotal": 25,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 24, "ambiguous_runtime": 26,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"memory_capacity": 1, "memory_capacity": 1,
@@ -1511,18 +1511,18 @@
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 75, "failureCount": 77,
"failureRate": 0.9868, "failureRate": 0.9872,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0132, "successRate": 0.0128,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 76, "total": 78,
"unresolvedFailureCount": 51 "unresolvedFailureCount": 53
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -2300,7 +2300,7 @@
"decisionSuccessRate": 0.284, "decisionSuccessRate": 0.284,
"decisionTotal": 169, "decisionTotal": 169,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 113, "ambiguous_runtime": 115,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 87, "framework_architecture_unsupported": 87,
"memory_capacity": 5, "memory_capacity": 5,
@@ -2309,15 +2309,15 @@
"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": 963, "failureCount": 965,
"failureRate": 0.9525, "failureRate": 0.9526,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 48, "successCount": 48,
"successRate": 0.0475, "successRate": 0.0474,
"total": 1011, "total": 1013,
"unresolvedFailureCount": 842 "unresolvedFailureCount": 844
}, },
"vllm": { "vllm": {
"attributableFailureCount": 234, "attributableFailureCount": 234,
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0043, "decisionSuccessRate": 0.0043,
"decisionTotal": 235, "decisionTotal": 235,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 154, "ambiguous_runtime": 155,
"backend_operator": 28, "backend_operator": 28,
"framework_architecture_unsupported": 169, "framework_architecture_unsupported": 169,
"memory_capacity": 6, "memory_capacity": 6,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 21 "参数/模板问题": 21
}, },
"failureCount": 410, "failureCount": 411,
"failureRate": 0.9976, "failureRate": 0.9976,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 1, "successCount": 1,
"successRate": 0.0024, "successRate": 0.0024,
"total": 411, "total": 412,
"unresolvedFailureCount": 175 "unresolvedFailureCount": 176
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-10T08:54:23.700725+00:00", "generatedAt": "2026-09-10T09:20:50.635463+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2455,22 +2455,22 @@
"decisionSuccessRate": 0.037, "decisionSuccessRate": 0.037,
"decisionTotal": 27, "decisionTotal": 27,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 22, "ambiguous_runtime": 23,
"framework_architecture_unsupported": 24, "framework_architecture_unsupported": 24,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"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": 83, "failureCount": 84,
"failureRate": 0.9881, "failureRate": 0.9882,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0119, "successRate": 0.0118,
"total": 84, "total": 85,
"unresolvedFailureCount": 57 "unresolvedFailureCount": 58
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"attributableFailureCount": 38, "attributableFailureCount": 38,
@@ -2503,7 +2503,7 @@
"decisionSuccessRate": 0.0385, "decisionSuccessRate": 0.0385,
"decisionTotal": 26, "decisionTotal": 26,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 24, "ambiguous_runtime": 26,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"memory_capacity": 1, "memory_capacity": 1,
@@ -2511,15 +2511,15 @@
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 76, "failureCount": 78,
"failureRate": 0.987, "failureRate": 0.9873,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.013, "successRate": 0.0127,
"total": 77, "total": 79,
"unresolvedFailureCount": 51 "unresolvedFailureCount": 53
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 20, "attributableFailureCount": 20,
@@ -3971,14 +3971,14 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 3, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 16, "ambiguous_runtime": 17,
"framework_architecture_unsupported": 3 "framework_architecture_unsupported": 3
}, },
"failureCount": 19, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:40:56.094753+00:00", "lastTerminalAt": "2026-09-10T09:20:50.207436+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -3986,8 +3986,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 19, "total": 20,
"unresolvedFailureCount": 16 "unresolvedFailureCount": 17
}, },
"Ascend_910-b4|llamacpp|text-generation": { "Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -4048,51 +4048,51 @@
"decisionSuccessRate": 0.1429, "decisionSuccessRate": 0.1429,
"decisionTotal": 7, "decisionTotal": 7,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 8, "ambiguous_runtime": 10,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 3, "framework_architecture_unsupported": 3,
"model_load": 1 "model_load": 1
}, },
"failureCount": 14, "failureCount": 16,
"failureRate": 0.9333, "failureRate": 0.9412,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:11:26.144205+00:00", "lastTerminalAt": "2026-09-10T09:20:50.207399+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0667, "successRate": 0.0588,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 15, "total": 17,
"unresolvedFailureCount": 8 "unresolvedFailureCount": 10
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
"consecutiveFailures": 3, "consecutiveFailures": 3,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.75, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.25, "decisionSuccessRate": 0.0,
"decisionTotal": 4, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 8, "ambiguous_runtime": 8,
"framework_architecture_unsupported": 2, "framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1 "tokenizer_compatibility": 1
}, },
"failureCount": 11, "failureCount": 11,
"failureRate": 0.9167, "failureRate": 1.0,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T07:29:02.941680+00:00", "lastTerminalAt": "2026-09-10T07:29:02.941680+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 0,
"successRate": 0.0833, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 12, "total": 11,
"unresolvedFailureCount": 8 "unresolvedFailureCount": 8
}, },
"Cambricon_mlu-370-x8|unknown|text-generation": { "Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -4359,7 +4359,7 @@
"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,
@@ -4369,11 +4369,11 @@
"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": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
@@ -6986,15 +6986,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1546, "terminalRecords": 1549,
"totalRecords": 1633, "totalRecords": 1636,
"totals": { "totals": {
"attributableFailureCount": 404, "attributableFailureCount": 404,
"decisionFailureRate": 0.8879, "decisionFailureRate": 0.8879,
"decisionSuccessRate": 0.1121, "decisionSuccessRate": 0.1121,
"decisionTotal": 455, "decisionTotal": 455,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 321, "ambiguous_runtime": 324,
"backend_operator": 33, "backend_operator": 33,
"framework_architecture_unsupported": 271, "framework_architecture_unsupported": 271,
"memory_capacity": 11, "memory_capacity": 11,
@@ -7006,21 +7006,21 @@
"参数/模板问题": 95, "参数/模板问题": 95,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1495, "failureCount": 1498,
"failureRate": 0.967, "failureRate": 0.9671,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 51, "successCount": 51,
"successRate": 0.033, "successRate": 0.0329,
"total": 1546, "total": 1549,
"unresolvedFailureCount": 1089 "unresolvedFailureCount": 1092
}, },
"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 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 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。",
@@ -7028,7 +7028,7 @@
"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 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 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。",
@@ -7049,6 +7049,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1633, "summarizedRecords": 1636,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,6 @@
{"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": "2026-09-10T09:20:50.207436+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:19:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505117", "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": "2026-09-10T09:20:50.207399+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610375", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T09:20:50.207423+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610372", "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": "2026-09-10T08:54:23.346315+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:49:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471916", "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": "2026-09-10T08:54:23.346315+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:49:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471916", "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": "2026-09-10T08:45:45.454624+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:41:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493673", "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": "2026-09-10T08:45:45.454624+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:41:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493673", "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": "2026-09-10T08:45:45.454539+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:39:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493671", "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": "2026-09-10T08:45:45.454539+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:39:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493671", "taskType": "text-generation", "verifyResult": -1}
@@ -295,6 +298,3 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-07T20:39:52.300729+00:00", "modelId": "nightmedia/Gemma3-27B-it-vl-HERETIC-GLM4.7-2200x-cp515-q6-mlx", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-07T20:31:03+00:00", "targetGpu": "Vastai_va16", "taskId": "4079310", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-07T20:39:52.300729+00:00", "modelId": "nightmedia/Gemma3-27B-it-vl-HERETIC-GLM4.7-2200x-cp515-q6-mlx", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-07T20:31:03+00:00", "targetGpu": "Vastai_va16", "taskId": "4079310", "taskType": "text-generation", "verifyResult": null}
{"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": "2026-09-07T20:06:50.393090+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:01:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458360", "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": "2026-09-07T20:06:50.393090+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:01:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458360", "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": "2026-09-07T19:45:42.406219+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T19:39:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4498542", "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": "2026-09-07T19:45:42.406219+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T19:39:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4498542", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T18:56:39.802680+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T18:51:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4462836", "taskType": "text-generation", "verifyResult": 1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T18:43:35.404751+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T18:35:22+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4470642", "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": "2026-09-07T16:24:49.011467+00:00", "modelId": "neuralmagic/granite-3.1-2b-instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T16:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080306", "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": "755c9fa82e23a063c998e6fe079a06b459048d7cb073e6ff1c59c64cea19a321", ".modelhub_state/architecture_compatibility_blacklist.json": "a52a9fd5711bba4c98e91fe40ae5b895e37360fefc4ebea5f35f764c0c968835",
".modelhub_state/architecture_history_backfill.json": "1c75724af8a78380fb2a6e78eb02e4f55d17080960b69c8a237607ef81672ba5", ".modelhub_state/architecture_history_backfill.json": "39d209f81ebd8b35b68cf5789ae029dbcc5e34a7da2f1d4f9a1b996ab26ca834",
".modelhub_state/market_intelligence.json": "c678716fa18f37ff078f157b08d6344c57a61b15138f60a1bdbb4e8df42a40ec", ".modelhub_state/market_intelligence.json": "6d35a61b93564dcd896ec681c6d6951b49e66eb95281f17c5bf1dedab8b12267",
".modelhub_state/official_capabilities.json": "f379b50ff05429e696e9d445e4ac740234146b74a26067637d01ca8585f6bf42", ".modelhub_state/official_capabilities.json": "5fda6ccef8e0b47abacfcb418bfa037cd163689dc2a98cd853e9359333e5d56e",
".modelhub_state/outcome_checkpoint.json": "a6ed5a14e57587bb60603c109aacd43a4792955a19435865e995243013434861", ".modelhub_state/outcome_checkpoint.json": "f315ceac1dbb6b6b923f7e117db4cfe0c30eeddf9fa85adc500a27ffbe283b27",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5", ".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "3f4eb3b80793d738a987d76dea4a148cd835934a25f6019d67e1c3a051be172a", ".modelhub_state/recent_outcomes.jsonl": "f9963c20000f164f6b98cee10a1e169b3b276dfee771ab2ba1e2665771c04c71",
".modelhub_state/recovery_active_tasks.jsonl": "68f57c098330258f9801b044801f000c9cf9f69bfc2d1b2a1223764c79506fe8", ".modelhub_state/recovery_active_tasks.jsonl": "0c89a9e83990c2315c065c2e621543d52a5e30029f30f52694462765125bd6d4",
".modelhub_state/recovery_intents.jsonl": "42ad9d063b139009ae186055b5a47e078bb5426f2a0484064d4556a5f65509e9", ".modelhub_state/recovery_intents.jsonl": "980070abd42ebbd8cea9f778cb7a638ee06144b3e4e053e240020e6668cfdf31",
".modelhub_state/routing_intelligence.json": "8a52419d4402861a79d360da797632830eb2c915c1cd189832eea085096de774", ".modelhub_state/routing_intelligence.json": "8a52419d4402861a79d360da797632830eb2c915c1cd189832eea085096de774",
".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": "1933ad805d1becf435394dbda5110270c499a0bd490635a19dc4240e65cfe8b1", "ledger/submissions.jsonl": "1933ad805d1becf435394dbda5110270c499a0bd490635a19dc4240e65cfe8b1",
"outcomes/submissions.jsonl": "91fca38fede4537b5ee54c666edf87dc0a2de6ea7ea5ff03e2f533b115ba412e" "outcomes/submissions.jsonl": "91fca38fede4537b5ee54c666edf87dc0a2de6ea7ea5ff03e2f533b115ba412e"
}, },
"generation": 5092, "generation": 5093,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-10T09:19:49.560720+00:00", "updatedAt": "2026-09-10T09:22:52.764486+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977" "writerId": "58ff5dc2a2d64b119ad1e4560700f977"
} }