state: generation 5699 (cycle)

This commit is contained in:
2026-09-11 13:11:39 +00:00
parent 6c88d28b96
commit f52cf7ad5c
9 changed files with 2163 additions and 2165 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-11T13:08:06.855277+00:00", "generatedAt": "2026-09-11T13:11:38.512700+00:00",
"summary": { "summary": {
"activeBlockCount": 66, "activeBlockCount": 66,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": { "8": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 408, "listingErrors": 409,
"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": 8, "nextAccountIndex": 9,
"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": "2026-09-11T13:08:06.831920+00:00", "updatedAt": "2026-09-11T13:11:38.490151+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,7 +416,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T13:06:26.691856+00:00", "generatedAt": "2026-09-11T13:09:18.414291+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": "2026-09-11T12:59:52.891244+00:00", "generatedAt": "2026-09-11T13:09:08.434430+00:00",
"lastSyncTime": "2026-09-11T12:59:52.253401+00:00", "lastSyncTime": "2026-09-11T13:09:08.149747+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7 "unresolvedFailureCount": 7
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 82, "attributableFailureCount": 83,
"decisionFailureRate": 0.8913, "decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1087, "decisionSuccessRate": 0.1075,
"decisionTotal": 92, "decisionTotal": 93,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 18,
"framework_architecture_unsupported": 48, "framework_architecture_unsupported": 48,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 33, "model_load": 34,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"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": 150, "failureCount": 151,
"failureRate": 0.9375, "failureRate": 0.9379,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 10, "successCount": 10,
"successRate": 0.0625, "successRate": 0.0621,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 160, "total": 161,
"unresolvedFailureCount": 67 "unresolvedFailureCount": 67
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
@@ -2290,29 +2290,29 @@
"unresolvedFailureCount": 5 "unresolvedFailureCount": 5
}, },
"unknown": { "unknown": {
"attributableFailureCount": 136, "attributableFailureCount": 137,
"decisionFailureRate": 0.7391, "decisionFailureRate": 0.7405,
"decisionSuccessRate": 0.2609, "decisionSuccessRate": 0.2595,
"decisionTotal": 184, "decisionTotal": 185,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 129, "ambiguous_runtime": 129,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 89, "framework_architecture_unsupported": 89,
"memory_capacity": 5, "memory_capacity": 5,
"model_load": 35, "model_load": 36,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 57, "参数/模板问题": 57,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 996, "failureCount": 997,
"failureRate": 0.954, "failureRate": 0.9541,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 48, "successCount": 48,
"successRate": 0.046, "successRate": 0.0459,
"total": 1044, "total": 1045,
"unresolvedFailureCount": 859 "unresolvedFailureCount": 859
}, },
"vllm": { "vllm": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-11T12:59:52.887160+00:00", "generatedAt": "2026-09-11T13:09:08.430453+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2606,27 +2606,27 @@
"unresolvedFailureCount": 43 "unresolvedFailureCount": 43
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 82, "attributableFailureCount": 83,
"decisionFailureRate": 0.8913, "decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1087, "decisionSuccessRate": 0.1075,
"decisionTotal": 92, "decisionTotal": 93,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 18,
"framework_architecture_unsupported": 48, "framework_architecture_unsupported": 48,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 33, "model_load": 34,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"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": 150, "failureCount": 151,
"failureRate": 0.9375, "failureRate": 0.9379,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 10, "successCount": 10,
"successRate": 0.0625, "successRate": 0.0621,
"total": 160, "total": 161,
"unresolvedFailureCount": 67 "unresolvedFailureCount": 67
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -4237,7 +4237,7 @@
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17, "attributableFailureCount": 17,
"consecutiveFailures": 15, "consecutiveFailures": 16,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444, "decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556, "decisionSuccessRate": 0.0556,
@@ -4252,7 +4252,7 @@
"failureRate": 0.95, "failureRate": 0.95,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00", "lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T12:50:33.752023+00:00", "lastTerminalAt": "2026-09-11T13:09:08.149747+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
@@ -4570,19 +4570,19 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"hygon_k100-ai|vllm|text-generation": { "hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 6, "attributableFailureCount": 5,
"consecutiveFailures": 6, "consecutiveFailures": 5,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 6, "decisionTotal": 5,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 12, "ambiguous_runtime": 12,
"framework_architecture_unsupported": 4, "framework_architecture_unsupported": 3,
"repository_structure": 1, "repository_structure": 1,
"runtime_memory": 1 "runtime_memory": 1
}, },
"failureCount": 18, "failureCount": 17,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -4594,7 +4594,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 18, "total": 17,
"unresolvedFailureCount": 12 "unresolvedFailureCount": 12
} }
}, },
@@ -6937,19 +6937,19 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1655, "terminalRecords": 1656,
"totalRecords": 1742, "totalRecords": 1743,
"totals": { "totals": {
"attributableFailureCount": 434, "attributableFailureCount": 435,
"decisionFailureRate": 0.8912, "decisionFailureRate": 0.8914,
"decisionSuccessRate": 0.1088, "decisionSuccessRate": 0.1086,
"decisionTotal": 487, "decisionTotal": 488,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 392, "ambiguous_runtime": 392,
"backend_operator": 40, "backend_operator": 40,
"framework_architecture_unsupported": 273, "framework_architecture_unsupported": 273,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 57, "model_load": 58,
"platform_infrastructure": 4, "platform_infrastructure": 4,
"repository_structure": 5, "repository_structure": 5,
"runtime_memory": 6, "runtime_memory": 6,
@@ -6957,30 +6957,31 @@
"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": 1602, "failureCount": 1603,
"failureRate": 0.968, "failureRate": 0.968,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 53, "successCount": 53,
"successRate": 0.032, "successRate": 0.032,
"total": 1655, "total": 1656,
"unresolvedFailureCount": 1164 "unresolvedFailureCount": 1164
}, },
"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。",
@@ -6995,11 +6996,10 @@
"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": 1742, "summarizedRecords": 1743,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-11T13:09:08.149747+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523311", "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": "2026-09-11T12:59:52.253401+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4531547", "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": "2026-09-11T12:59:52.253401+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4531547", "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": "2026-09-11T12:50:33.752023+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523324", "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": "2026-09-11T12:50:33.752023+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523324", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-11T11:19:08.306651+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:13:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4578314", "taskType": "text-generation", "verifyResult": -1} {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-11T11:19:08.306651+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:13:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4578314", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-08T10:00:15.603861+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080861", "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": "2026-09-08T10:00:15.603861+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080861", "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": "2026-09-08T10:00:15.603853+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:43:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4268342", "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": "2026-09-08T10:00:15.603853+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:43:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4268342", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-08T09:34:21.991823+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332983", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-08T09:34:21.991823+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332983", "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": "2026-09-08T09:05:31.097966+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:59:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079918", "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": "6cbe35828ef5a141a31fd3c167fc466e68a5e1bcd422b599327f732976e6f390", ".modelhub_state/architecture_compatibility_blacklist.json": "ad5ae67346a985f899e94b36fe5eb370cb7f3a607146869eaf5df2a4f4ea0d0c",
".modelhub_state/architecture_history_backfill.json": "ec8a48f856b5ad75f0f2f3a1887641a5327f2c99b1ee2ccc146a3123289c89be", ".modelhub_state/architecture_history_backfill.json": "3c17e5e37ede6d773342feaeadedac6f7efc5e5535a4cd4de1700858ba5691bb",
".modelhub_state/market_intelligence.json": "f8fc6750c730dfcb5c2628fa5c060b1d43380ad6c5c0b834f73b3fa7547a816b", ".modelhub_state/market_intelligence.json": "8bd5024618a6c11ebed91a2699afdced88e7161f04e6a7bda8cf226c5ea95daa",
".modelhub_state/official_capabilities.json": "cb80e3bcaac920e18a8e3f118b91b071e1cba8ba36b4a995f528065b99ff6e70", ".modelhub_state/official_capabilities.json": "433463eeb293c107f873cf06b5ad4a47d62ed3cfc798e4350f36dc8012dcff54",
".modelhub_state/outcome_checkpoint.json": "40633343daecca7a91472d185efed3015ee85b4b13ea8402099d80d440549212", ".modelhub_state/outcome_checkpoint.json": "fa2160f53ecffc3c528f8efb9365d52bb20df7bf3a1dee9e6e6aad6119ea15d7",
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b", ".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
".modelhub_state/recent_outcomes.jsonl": "0794ebabd88bc7ab78c5a8767a5c665f73b166e08bacdecf60a48b77a78639d7", ".modelhub_state/recent_outcomes.jsonl": "87422de52ccdf1fb67e8d4341ed10d2fd565df8d441f90c7386ce8b681973f48",
".modelhub_state/recovery_active_tasks.jsonl": "05f8f1b52578b662192934217d84e6e95013b7c222335f4b4f4ba19d4e6a13d8", ".modelhub_state/recovery_active_tasks.jsonl": "83d2a9f5f6a1372f68c352076db2e6d93add8d89a2ad77c5afb218e89b8ad5b7",
".modelhub_state/recovery_intents.jsonl": "41c463093c906af3430433662760f5cf1c5cba6a784854c6fd94c6010cae2b84", ".modelhub_state/recovery_intents.jsonl": "185fa3987aa0eee9dd3f017c5b7f7f3da45f2971016fa89a80636c2a5a3c2665",
".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": 5698, "generation": 5699,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-11T13:08:06.919742+00:00", "updatedAt": "2026-09-11T13:11:39.274361+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42" "writerId": "18252d8a8ef94333abd55823b2d81c42"
} }