state: generation 5329 (cycle)
This commit is contained in:
@@ -1311,7 +1311,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T19:37:04.865473+00:00",
|
||||
"generatedAt": "2026-09-10T19:40:09.258560+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -35,7 +35,7 @@
|
||||
"2": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 379,
|
||||
"listingErrors": 380,
|
||||
"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": 2,
|
||||
"nextAccountIndex": 3,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-10T19:37:04.840323+00:00",
|
||||
"updatedAt": "2026-09-10T19:40:09.234635+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-10T19:20:54.121441+00:00",
|
||||
"communityAttemptedAt": "2026-09-10T19:38:11.550876+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-10T19:20:54.121441+00:00",
|
||||
"communityUpdatedAt": "2026-09-10T19:38:11.550876+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-10T15:27:32.924657+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T19:34:54.306456+00:00",
|
||||
"generatedAt": "2026-09-10T19:38:11.550876+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T19:27:43.149913+00:00",
|
||||
"lastSyncTime": "2026-09-10T19:27:42.923434+00:00",
|
||||
"generatedAt": "2026-09-10T19:38:05.803026+00:00",
|
||||
"lastSyncTime": "2026-09-10T19:38:05.602511+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1791,30 +1791,30 @@
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 75,
|
||||
"decisionFailureRate": 0.8824,
|
||||
"decisionSuccessRate": 0.1176,
|
||||
"decisionTotal": 85,
|
||||
"attributableFailureCount": 76,
|
||||
"decisionFailureRate": 0.8837,
|
||||
"decisionSuccessRate": 0.1163,
|
||||
"decisionTotal": 86,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 47,
|
||||
"framework_architecture_unsupported": 48,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 27,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 142,
|
||||
"failureRate": 0.9342,
|
||||
"failureCount": 143,
|
||||
"failureRate": 0.9346,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0658,
|
||||
"successRate": 0.0654,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 152,
|
||||
"total": 153,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -2292,14 +2292,14 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 129,
|
||||
"decisionFailureRate": 0.7288,
|
||||
"decisionSuccessRate": 0.2712,
|
||||
"decisionTotal": 177,
|
||||
"attributableFailureCount": 130,
|
||||
"decisionFailureRate": 0.7303,
|
||||
"decisionSuccessRate": 0.2697,
|
||||
"decisionTotal": 178,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 123,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 88,
|
||||
"framework_architecture_unsupported": 89,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 29,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2307,14 +2307,14 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 982,
|
||||
"failureCount": 983,
|
||||
"failureRate": 0.9534,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0466,
|
||||
"total": 1030,
|
||||
"total": 1031,
|
||||
"unresolvedFailureCount": 852
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2445,7 +2445,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T19:27:43.145530+00:00",
|
||||
"generatedAt": "2026-09-10T19:38:05.798763+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2608,27 +2608,27 @@
|
||||
"unresolvedFailureCount": 43
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 75,
|
||||
"decisionFailureRate": 0.8824,
|
||||
"decisionSuccessRate": 0.1176,
|
||||
"decisionTotal": 85,
|
||||
"attributableFailureCount": 76,
|
||||
"decisionFailureRate": 0.8837,
|
||||
"decisionSuccessRate": 0.1163,
|
||||
"decisionTotal": 86,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 47,
|
||||
"framework_architecture_unsupported": 48,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 27,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 142,
|
||||
"failureRate": 0.9342,
|
||||
"failureCount": 143,
|
||||
"failureRate": 0.9346,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0658,
|
||||
"total": 152,
|
||||
"successRate": 0.0654,
|
||||
"total": 153,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -4172,11 +4172,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4188,8 +4188,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
@@ -4270,27 +4270,27 @@
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 16,
|
||||
"consecutiveFailures": 8,
|
||||
"attributableFailureCount": 17,
|
||||
"consecutiveFailures": 9,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8421,
|
||||
"decisionSuccessRate": 0.1579,
|
||||
"decisionFailureRate": 0.8947,
|
||||
"decisionSuccessRate": 0.1053,
|
||||
"decisionTotal": 19,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 7,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"model_load": 9,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.85,
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.9,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
|
||||
"lastTerminalAt": "2026-09-10T19:27:42.923434+00:00",
|
||||
"lastTerminalAt": "2026-09-10T19:38:05.602511+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.15,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
@@ -4683,31 +4683,6 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastTerminalAt": "2026-09-08T16:13:44.313839+00:00",
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
@@ -7047,17 +7022,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1626,
|
||||
"totalRecords": 1713,
|
||||
"terminalRecords": 1627,
|
||||
"totalRecords": 1714,
|
||||
"totals": {
|
||||
"attributableFailureCount": 424,
|
||||
"decisionFailureRate": 0.8908,
|
||||
"decisionSuccessRate": 0.1092,
|
||||
"decisionTotal": 476,
|
||||
"attributableFailureCount": 425,
|
||||
"decisionFailureRate": 0.891,
|
||||
"decisionSuccessRate": 0.109,
|
||||
"decisionTotal": 477,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 375,
|
||||
"backend_operator": 40,
|
||||
"framework_architecture_unsupported": 272,
|
||||
"framework_architecture_unsupported": 273,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 51,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -7067,31 +7042,30 @@
|
||||
"参数/模板问题": 98,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1574,
|
||||
"failureCount": 1575,
|
||||
"failureRate": 0.968,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 52,
|
||||
"successRate": 0.032,
|
||||
"total": 1626,
|
||||
"total": 1627,
|
||||
"unresolvedFailureCount": 1146
|
||||
},
|
||||
"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。",
|
||||
@@ -7106,10 +7080,11 @@
|
||||
"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": 1713,
|
||||
"summarizedRecords": 1714,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"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_mtp"], "framework": "", "lastSyncTime": "2026-09-10T19:38:05.602511+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332704", "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": "2026-09-10T19:27:42.923434+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523215", "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": "2026-09-10T19:17:56.906562+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523222", "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": "2026-09-10T19:08:02.004176+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523301", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T04:17:40.427917+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.589203+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712819", "taskType": "text-generation", "verifyResult": null}
|
||||
{"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_mtp"], "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T18:40:55.416623+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 238933307, "estimatedRequiredGiB": 0.297, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 265664321, "modelscopeLicense": "apache-2.0", "modelscopeParams": 106194432, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:nvfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 265664321}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.587867+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712816", "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_mtp"], "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:49:45.832679+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 225662258, "estimatedRequiredGiB": 0.282, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 252393272, "modelscopeLicense": "apache-2.0", "modelscopeParams": 79652352, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:mxfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 252393272}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.586261+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712822", "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": "vllm-mlu", "lastSyncTime": "2026-09-08T16:13:44.313839+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.586014+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712812", "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": "578735199a6959d0b32cd7b3c0fd17abdbd45a79706ac71e1484f1b6559ac341",
|
||||
".modelhub_state/architecture_history_backfill.json": "1d1ebd49bd3f88e32b788056ef83bced011f0bf65d3b1c1e7ead4a6942009314",
|
||||
".modelhub_state/market_intelligence.json": "005033093a68cc5abeecc154c1ad423baa60b0065b44be87d38b71771f5f6084",
|
||||
".modelhub_state/official_capabilities.json": "d53b95531dfbd4c9656550d6fa3e1e07804420c610722e0811397b4aabc8fc98",
|
||||
".modelhub_state/outcome_checkpoint.json": "3e984e290a2eb45d510052cd1c2361437efecd9e582840ac8b03a56f96d872e4",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "7c638b43976f1dee1a2d6febce7243c49a2f5b43df54b24bf81689545857ae81",
|
||||
".modelhub_state/architecture_history_backfill.json": "034b5a56bd078f09f83127860e14a6960248aaa38aa6a8f734c75174f7ff928c",
|
||||
".modelhub_state/market_intelligence.json": "0a3bfa54048df6f0d6c79248297feefa97d92b863c62f2f202ddbdb98a437d02",
|
||||
".modelhub_state/official_capabilities.json": "671fb07978ffdbe3871640d5d81a5ab0d943b0cacda5789a2e07977b5811b6c7",
|
||||
".modelhub_state/outcome_checkpoint.json": "88430152ff98138b7888e1c11ccefb688db72a7638bdf9c1cde52aa208fdfc1b",
|
||||
".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
|
||||
".modelhub_state/recent_outcomes.jsonl": "1388ed8f857d6d0f8e9699669ebcd92e7c628f83e95275a1c38ec192fbef36a7",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "60dd585934e5eeaf6c97a92f271e8b00b5717a3aad35f8a5d544050a1578375a",
|
||||
".modelhub_state/recovery_intents.jsonl": "f833da6dc711951a98e34f857dcab778e2c387753f8d2ae895b0806f2845f562",
|
||||
".modelhub_state/recent_outcomes.jsonl": "18cca6e68b2debcaaf1300a8f56cc81bf83c5aac5f0a5ec6de306f37b9978c5f",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "8e55c188d6d9b626863015ba9999e20671134e3a98795026a83e71e9b66035d0",
|
||||
".modelhub_state/recovery_intents.jsonl": "13817573f8a507dd357fdf40a0ec06aeb0582ac258f42a6e8f212171d138cdf6",
|
||||
".modelhub_state/routing_intelligence.json": "7e77ebd4538eae240305b9b7218df18db6f864488fe914a9ce22b09526e6df6c",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
||||
"ledger/submissions.jsonl": "666d3d2a6579643ce987f9dc944f3169c02e619fe50a5b6144105e85857aa8c5",
|
||||
"outcomes/submissions.jsonl": "328b6e09b9ffd31462af8316c4ab7811046b316a1a9404ff8de3ff4fb90aff41"
|
||||
},
|
||||
"generation": 5328,
|
||||
"generation": 5329,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T19:37:04.942607+00:00",
|
||||
"updatedAt": "2026-09-10T19:40:09.893681+00:00",
|
||||
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user