state: generation 5663 (cycle)
This commit is contained in:
@@ -1307,7 +1307,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-11T11:18:07.273606+00:00",
|
||||
"generatedAt": "2026-09-11T11:21:51.649021+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 405,
|
||||
"listingErrors": 406,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-11T11:18:07.249933+00:00",
|
||||
"updatedAt": "2026-09-11T11:21:51.623800+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-11T11:15:38.580583+00:00",
|
||||
"generatedAt": "2026-09-11T11:19:15.887456+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-11T11:08:15.025709+00:00",
|
||||
"lastSyncTime": "2026-09-11T11:08:14.809954+00:00",
|
||||
"generatedAt": "2026-09-11T11:19:08.559808+00:00",
|
||||
"lastSyncTime": "2026-09-11T11:19:08.306651+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2042,17 +2042,17 @@
|
||||
"unresolvedFailureCount": 33
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 36,
|
||||
"attributableFailureCount": 37,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 36,
|
||||
"decisionTotal": 37,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 2,
|
||||
"platform_infrastructure": 2,
|
||||
"tokenizer_compatibility": 34,
|
||||
"tokenizer_compatibility": 35,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 44,
|
||||
"failureCount": 45,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -2062,21 +2062,22 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 44,
|
||||
"total": 45,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2086,7 +2087,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Vastai_va16|unknown|text-generation": {
|
||||
@@ -2315,10 +2316,10 @@
|
||||
"unresolvedFailureCount": 858
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 240,
|
||||
"attributableFailureCount": 241,
|
||||
"decisionFailureRate": 0.9877,
|
||||
"decisionSuccessRate": 0.0123,
|
||||
"decisionTotal": 243,
|
||||
"decisionTotal": 244,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 195,
|
||||
"backend_operator": 33,
|
||||
@@ -2328,17 +2329,17 @@
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 5,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 3,
|
||||
"tokenizer_compatibility": 4,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 460,
|
||||
"failureCount": 461,
|
||||
"failureRate": 0.9935,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0065,
|
||||
"total": 463,
|
||||
"total": 464,
|
||||
"unresolvedFailureCount": 219
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2401,26 +2402,26 @@
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 39,
|
||||
"attributableFailureCount": 40,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 39,
|
||||
"decisionTotal": 40,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 36,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"model_load": 1,
|
||||
"platform_infrastructure": 2,
|
||||
"tokenizer_compatibility": 34,
|
||||
"tokenizer_compatibility": 35,
|
||||
"参数/模板问题": 7
|
||||
},
|
||||
"failureCount": 84,
|
||||
"failureCount": 85,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 84,
|
||||
"total": 85,
|
||||
"unresolvedFailureCount": 43
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -2442,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-11T11:08:15.021564+00:00",
|
||||
"generatedAt": "2026-09-11T11:19:08.555805+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2700,26 +2701,26 @@
|
||||
"unresolvedFailureCount": 77
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 37,
|
||||
"decisionFailureRate": 0.9737,
|
||||
"decisionSuccessRate": 0.0263,
|
||||
"decisionTotal": 38,
|
||||
"attributableFailureCount": 39,
|
||||
"decisionFailureRate": 0.975,
|
||||
"decisionSuccessRate": 0.025,
|
||||
"decisionTotal": 40,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"platform_infrastructure": 3,
|
||||
"tokenizer_compatibility": 34,
|
||||
"tokenizer_compatibility": 36,
|
||||
"参数/模板问题": 9,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 82,
|
||||
"failureRate": 0.988,
|
||||
"failureCount": 84,
|
||||
"failureRate": 0.9882,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 1,
|
||||
"successRate": 0.012,
|
||||
"total": 83,
|
||||
"successRate": 0.0118,
|
||||
"total": 85,
|
||||
"unresolvedFailureCount": 42
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -4415,22 +4416,22 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 15,
|
||||
"consecutiveFailures": 15,
|
||||
"attributableFailureCount": 16,
|
||||
"consecutiveFailures": 16,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 15,
|
||||
"decisionTotal": 16,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 2,
|
||||
"tokenizer_compatibility": 14
|
||||
"tokenizer_compatibility": 15
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureCount": 18,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
|
||||
"lastTerminalAt": "2026-09-11T11:08:14.809954+00:00",
|
||||
"lastTerminalAt": "2026-09-11T11:19:08.306628+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
@@ -4438,25 +4439,26 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"platform_infrastructure": 1
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
|
||||
"lastTerminalAt": "2026-09-10T12:06:09.109198+00:00",
|
||||
"lastTerminalAt": "2026-09-11T11:19:08.306651+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
@@ -4464,7 +4466,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -6936,13 +6938,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1651,
|
||||
"totalRecords": 1738,
|
||||
"terminalRecords": 1653,
|
||||
"totalRecords": 1740,
|
||||
"totals": {
|
||||
"attributableFailureCount": 431,
|
||||
"decisionFailureRate": 0.8905,
|
||||
"decisionSuccessRate": 0.1095,
|
||||
"decisionTotal": 484,
|
||||
"attributableFailureCount": 433,
|
||||
"decisionFailureRate": 0.8909,
|
||||
"decisionSuccessRate": 0.1091,
|
||||
"decisionTotal": 486,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 391,
|
||||
"backend_operator": 40,
|
||||
@@ -6952,35 +6954,34 @@
|
||||
"platform_infrastructure": 4,
|
||||
"repository_structure": 5,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 40,
|
||||
"tokenizer_compatibility": 42,
|
||||
"参数/模板问题": 99,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1598,
|
||||
"failureCount": 1600,
|
||||
"failureRate": 0.9679,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 53,
|
||||
"successRate": 0.0321,
|
||||
"total": 1651,
|
||||
"total": 1653,
|
||||
"unresolvedFailureCount": 1163
|
||||
},
|
||||
"warnings": [
|
||||
"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 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 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 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-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。",
|
||||
"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 Cambricon_mlu-370-x4 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 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 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。",
|
||||
@@ -6995,10 +6996,11 @@
|
||||
"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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1738,
|
||||
"summarizedRecords": 1740,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
{"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_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T11:19:08.306628+00:00", "modelId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457980", "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_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": "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}
|
||||
@@ -296,5 +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": "2026-09-08T09:05:31.097966+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}
|
||||
{"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": "2026-09-08T08:12:43.104884+00:00", "modelId": "nv-community/Qwen3-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:03:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079088", "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": "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}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "3b9c56ea1113f1ceca7bc923ae606d1f0212aa5dc9818a3a7965f0d694b2f580",
|
||||
".modelhub_state/architecture_history_backfill.json": "f477d32a76471dcd77d0fabc05a86b9b4cad1a482839ffa2a42d777b33e30fe2",
|
||||
".modelhub_state/market_intelligence.json": "d0421263820aff5acf5d9e6de64f0baccc66267d8e917921fb8807b774ae09f7",
|
||||
".modelhub_state/official_capabilities.json": "cfc5359534ce76c4ef3cd021b010119fa89d47da497f560131a6bdb2d5fddd44",
|
||||
".modelhub_state/outcome_checkpoint.json": "738daae4d96f6b15097c7b1f7fd5c71771c203d17ce6790817773561e9ecdd41",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "31a9db76cd7354a516e91f1da2bd2e68cea68ed04ba57d75d482d4543256924b",
|
||||
".modelhub_state/architecture_history_backfill.json": "7d2a6b9f278b7aee2043fef8e0387780cfe5f5fbdc0d57d27746e81cf58f2f67",
|
||||
".modelhub_state/market_intelligence.json": "62ff67c9166b85ae73d173777dba306a42f574550ea3d875d020be2ed829a29a",
|
||||
".modelhub_state/official_capabilities.json": "64605402ccde5d1f1e2681e8758cf6230ca2ff5b56a07d4c2446632e378e7518",
|
||||
".modelhub_state/outcome_checkpoint.json": "c2d11f8fa2c54c709b06c66c02bba10ff3f4ee109ea7db2ce3a39a44c139fc1f",
|
||||
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
|
||||
".modelhub_state/recent_outcomes.jsonl": "daca771dc12e1867e50ad6c80abfb423333720a8917956d9ad25d12ea685b2e7",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "bee434f77691735f87dda66f8405dedc239866e1389983caf4b6a65baabc2527",
|
||||
".modelhub_state/recovery_intents.jsonl": "c64bfa0762191e311a9b430311825ea56c28dd0c3fc574f83d6e914fea5e5f94",
|
||||
".modelhub_state/recent_outcomes.jsonl": "84a846ee1c2269ec077c25ffd0d77f9ca4fe2b3bb5a6ed6f689cb0f45756f8cb",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "90dc420af8f70a86f3e4671648e8865b4a273b7b76c0b294da972ad37e2b2c77",
|
||||
".modelhub_state/recovery_intents.jsonl": "15c061af2cc60f594031bf186294777499921b6b3751c9031767cd900faccc52",
|
||||
".modelhub_state/routing_intelligence.json": "01755a7ae15e8408cf0586a62b0684ec4e7e2d46c2715b9b2bfe968c7d40353e",
|
||||
".modelhub_state/submission_exclusions.jsonl": "3790b5c148f222a4de26d50a3d8afc58891c8da251a82d20dbaf4fc35e6dbd89",
|
||||
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
||||
"ledger/submissions.jsonl": "0f2922a5f34c5777fcbb7e7ea1512bd1784eed2b74f5d6c3f05103cb3bbea37e",
|
||||
"outcomes/submissions.jsonl": "9b436339a59d073250c1f14e08f71c1148a29e5b3db2301e39b71ed36893e02b"
|
||||
},
|
||||
"generation": 5662,
|
||||
"generation": 5663,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-11T11:18:07.348584+00:00",
|
||||
"updatedAt": "2026-09-11T11:21:52.135970+00:00",
|
||||
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user