state: generation 5037 (cycle)

This commit is contained in:
2026-09-10 07:06:53 +00:00
parent 5f3c51a6eb
commit 44b6cc3ba6
9 changed files with 2148 additions and 2149 deletions

View File

@@ -1317,7 +1317,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-10T07:03:56.552047+00:00", "generatedAt": "2026-09-10T07:06:52.500958+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": 357, "listingErrors": 358,
"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": "2026-09-10T07:03:56.525896+00:00", "updatedAt": "2026-09-10T07:06:52.475685+00:00",
"version": 1 "version": 1
} }

View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-09-10T06:48:43.517182+00:00", "communityAttemptedAt": "2026-09-10T07:05:03.576071+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-09-10T06:48:43.517182+00:00", "communityUpdatedAt": "2026-09-10T07:05:03.576071+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": "2026-09-10T07:02:05.806166+00:00", "generatedAt": "2026-09-10T07:05:03.576071+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": "2026-09-10T06:56:24.262905+00:00", "generatedAt": "2026-09-10T07:04:57.589678+00:00",
"lastSyncTime": "2026-09-10T06:56:22.046035+00:00", "lastSyncTime": "2026-09-10T07:04:57.311825+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1551,24 +1551,24 @@
"decisionSuccessRate": 0.0909, "decisionSuccessRate": 0.0909,
"decisionTotal": 22, "decisionTotal": 22,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 19,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 39 "验证失败": 39
}, },
"failureCount": 77, "failureCount": 78,
"failureRate": 0.9747, "failureRate": 0.975,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0253, "successRate": 0.025,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 79, "total": 80,
"unresolvedFailureCount": 57 "unresolvedFailureCount": 58
}, },
"Cambricon_mlu-370-x8|unknown|text-generation": { "Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -2235,14 +2235,14 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 35, "decisionTotal": 35,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 11, "ambiguous_runtime": 13,
"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": 46, "failureCount": 48,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -2252,8 +2252,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 46, "total": 48,
"unresolvedFailureCount": 11 "unresolvedFailureCount": 13
} }
}, },
"frameworkSummaries": { "frameworkSummaries": {
@@ -2300,7 +2300,7 @@
"decisionSuccessRate": 0.284, "decisionSuccessRate": 0.284,
"decisionTotal": 169, "decisionTotal": 169,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 106, "ambiguous_runtime": 107,
"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": 956, "failureCount": 957,
"failureRate": 0.9522, "failureRate": 0.9522,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 48, "successCount": 48,
"successRate": 0.0478, "successRate": 0.0478,
"total": 1004, "total": 1005,
"unresolvedFailureCount": 835 "unresolvedFailureCount": 836
}, },
"vllm": { "vllm": {
"attributableFailureCount": 230, "attributableFailureCount": 230,
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 230, "decisionTotal": 230,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 148, "ambiguous_runtime": 150,
"backend_operator": 24, "backend_operator": 24,
"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": 400, "failureCount": 402,
"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": 400, "total": 402,
"unresolvedFailureCount": 169 "unresolvedFailureCount": 171
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-10T06:56:24.258540+00:00", "generatedAt": "2026-09-10T07:04:57.585456+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2527,21 +2527,21 @@
"decisionSuccessRate": 0.0909, "decisionSuccessRate": 0.0909,
"decisionTotal": 22, "decisionTotal": 22,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 19,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 39 "验证失败": 39
}, },
"failureCount": 77, "failureCount": 78,
"failureRate": 0.9747, "failureRate": 0.975,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0253, "successRate": 0.025,
"total": 79, "total": 80,
"unresolvedFailureCount": 57 "unresolvedFailureCount": 58
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"attributableFailureCount": 17, "attributableFailureCount": 17,
@@ -2754,7 +2754,7 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 38, "decisionTotal": 38,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 13, "ambiguous_runtime": 15,
"framework_architecture_unsupported": 30, "framework_architecture_unsupported": 30,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 3, "model_load": 3,
@@ -2763,15 +2763,15 @@
"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": 86, "failureCount": 88,
"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": 86, "total": 88,
"unresolvedFailureCount": 48 "unresolvedFailureCount": 50
} }
}, },
"observedGpuMemoryGiB": { "observedGpuMemoryGiB": {
@@ -4051,28 +4051,28 @@
"attributableFailureCount": 3, "attributableFailureCount": 3,
"consecutiveFailures": 3, "consecutiveFailures": 3,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6, "decisionFailureRate": 0.75,
"decisionSuccessRate": 0.4, "decisionSuccessRate": 0.25,
"decisionTotal": 5, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 5, "ambiguous_runtime": 6,
"framework_architecture_unsupported": 2, "framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1 "tokenizer_compatibility": 1
}, },
"failureCount": 8, "failureCount": 9,
"failureRate": 0.8, "failureRate": 0.9,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:56:22.046014+00:00", "lastTerminalAt": "2026-09-10T07:04:57.311794+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 1,
"successRate": 0.2, "successRate": 0.1,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 10, "total": 10,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 6
}, },
"Cambricon_mlu-370-x8|unknown|text-generation": { "Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 2, "attributableFailureCount": 2,
@@ -4518,23 +4518,23 @@
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0, "decisionSuccessRate": 1.0,
"decisionTotal": 2, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"参数/模板问题": 2 "参数/模板问题": 2
}, },
"failureCount": 2, "failureCount": 2,
"failureRate": 0.5, "failureRate": 0.6667,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T22:32:11.428244+00:00", "lastTerminalAt": "2026-09-07T22:32:11.428244+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 1,
"successRate": 0.5, "successRate": 0.3333,
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation", "taskType": "text-generation",
"total": 4, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Vastai_va16|vllm_fix_tokenizer|text-generation": { "Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -4646,16 +4646,16 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 8, "decisionTotal": 8,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 8, "ambiguous_runtime": 10,
"framework_architecture_unsupported": 6, "framework_architecture_unsupported": 6,
"model_load": 1, "model_load": 1,
"repository_structure": 1 "repository_structure": 1
}, },
"failureCount": 16, "failureCount": 18,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:03:48.106939+00:00", "lastTerminalAt": "2026-09-10T07:04:57.311815+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4663,8 +4663,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 16, "total": 18,
"unresolvedFailureCount": 8 "unresolvedFailureCount": 10
} }
}, },
"recentProfileCombinationStats": { "recentProfileCombinationStats": {
@@ -6897,15 +6897,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1523, "terminalRecords": 1526,
"totalRecords": 1610, "totalRecords": 1613,
"totals": { "totals": {
"attributableFailureCount": 400, "attributableFailureCount": 400,
"decisionFailureRate": 0.8909, "decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091, "decisionSuccessRate": 0.1091,
"decisionTotal": 449, "decisionTotal": 449,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 304, "ambiguous_runtime": 307,
"backend_operator": 29, "backend_operator": 29,
"framework_architecture_unsupported": 271, "framework_architecture_unsupported": 271,
"memory_capacity": 11, "memory_capacity": 11,
@@ -6917,21 +6917,21 @@
"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": 1474, "failureCount": 1477,
"failureRate": 0.9678, "failureRate": 0.9679,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 49, "successCount": 49,
"successRate": 0.0322, "successRate": 0.0321,
"total": 1523, "total": 1526,
"unresolvedFailureCount": 1072 "unresolvedFailureCount": 1075
}, },
"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。",
@@ -6939,7 +6939,7 @@
"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。",
@@ -6960,6 +6960,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1610, "summarizedRecords": 1613,
"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": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T07:04:57.311815+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493609", "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": "2026-09-10T07:04:57.311825+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493601", "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": "2026-09-10T07:04:57.311794+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497056", "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": "2026-09-10T06:56:22.046014+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496936", "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": "2026-09-10T06:56:22.046014+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496936", "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": "2026-09-10T06:56:22.046035+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477785", "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": "2026-09-10T06:56:22.046035+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477785", "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": "2026-09-10T06:40:56.094753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505108", "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": "2026-09-10T06:40:56.094753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505108", "taskType": "text-generation", "verifyResult": -1}
@@ -295,6 +298,3 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T14:07:33.009927+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T14:05:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4471039", "taskType": "text-generation", "verifyResult": 1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T14:07:33.009927+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T14:05:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4471039", "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": "2026-09-07T13:23:28.609297+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T13:13:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4460285", "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": "2026-09-07T13:23:28.609297+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T13:13:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4460285", "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": "2026-09-07T13:23:28.609319+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T13:09:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4461004", "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": "2026-09-07T13:23:28.609319+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T13:09:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4461004", "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": "2026-09-07T13:23:28.609330+00:00", "modelId": "fla-hub/rwkv7-2.9B-world", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T13:07:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079226", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T13:23:28.609340+00:00", "modelId": "Josephgflowers/Phinance-Phi-3.5-mini-instruct-finance-v0.2", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T12:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079236", "taskType": "text-generation", "verifyResult": 1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T12:50:24.741614+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T12:45:22+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4470643", "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": "19c2497b7af91b37dd5bf60cb323a3b097d82b48c405ab6f47650d1e939b36b4", ".modelhub_state/architecture_compatibility_blacklist.json": "788fe4230bb80b85c189fa420cf93feb812e03a00e11c434ccedcf38da0fe638",
".modelhub_state/architecture_history_backfill.json": "60c18dbcf706e7e1415b552c650bf0c0cf6617d2f4567111497dc23b24cdb093", ".modelhub_state/architecture_history_backfill.json": "c808a8e600e91e00609477768cc037db5c0569a4c68ee15749aac1d960b1d940",
".modelhub_state/market_intelligence.json": "132d4711a23009fbf73cc1254c657e8be528022d0f65ec29820d23f936e504b4", ".modelhub_state/market_intelligence.json": "84740c6e0df6bad63dfb2ef3577d73ba85f6723fa23708f90231c097a2cd6775",
".modelhub_state/official_capabilities.json": "74bc157750cbec628e1a302d59d1d06622dd850795a0ef7603cf3c975332803e", ".modelhub_state/official_capabilities.json": "0879b05a2e4f36a926eefb235ba16b1fa374ee27f8a26e3792e3db7e50b66b37",
".modelhub_state/outcome_checkpoint.json": "40f98bc7877554d61a7e1dd6edd59c7c32f9bf53047fa20bcc5af0c272355666", ".modelhub_state/outcome_checkpoint.json": "3b61f8885f0819466de0814ed664f9260fbfb0975c364a4e673cb2cf4596fbea",
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99", ".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
".modelhub_state/recent_outcomes.jsonl": "612b94b37ae652c965046df6fba16f9a01a481cdff28ce01f24c4bc1ca89a860", ".modelhub_state/recent_outcomes.jsonl": "068ec3c6cf60871ee9053fc13c3cee78ec0bebb1489dcff4feb1ae224d56a1fe",
".modelhub_state/recovery_active_tasks.jsonl": "2997024e6c952bf7690aad9702909235a575eacbe06e5127263ad25469797a36", ".modelhub_state/recovery_active_tasks.jsonl": "27a00298f65186039c4dabdb420fccc4873dc8e35dfd15d234f7048263672a9e",
".modelhub_state/recovery_intents.jsonl": "b9a51255705742d1e57050c1fe89db42ca419a5888602b14821ae7a947f8fefc", ".modelhub_state/recovery_intents.jsonl": "b1e6a895c77d0856181f0e5855ffdfe289c1494aead7774754fc4fe1f1277022",
".modelhub_state/routing_intelligence.json": "442aeec7e5c877b1d9bd1bad61a541085714c971d178aa0fa2b1b08c7f4abe66", ".modelhub_state/routing_intelligence.json": "442aeec7e5c877b1d9bd1bad61a541085714c971d178aa0fa2b1b08c7f4abe66",
".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": "005ab916f621a4b956c7829251d4bc7b3ad3cc0e8c9e9ddc9e78e0102916ccee", "ledger/submissions.jsonl": "005ab916f621a4b956c7829251d4bc7b3ad3cc0e8c9e9ddc9e78e0102916ccee",
"outcomes/submissions.jsonl": "1127624edc74e87c349542974b68b328097a97a274d8a56a0ae5b32ddc849bc0" "outcomes/submissions.jsonl": "1127624edc74e87c349542974b68b328097a97a274d8a56a0ae5b32ddc849bc0"
}, },
"generation": 5036, "generation": 5037,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-10T07:03:56.646902+00:00", "updatedAt": "2026-09-10T07:06:53.096308+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977" "writerId": "58ff5dc2a2d64b119ad1e4560700f977"
} }