state: generation 10616 (cycle)
This commit is contained in:
@@ -1493,7 +1493,7 @@
|
||||
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 2,
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-16T01:37:21+00:00",
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"latestFailureAt": "2026-09-16T01:37:21+00:00",
|
||||
@@ -1501,12 +1501,10 @@
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5",
|
||||
"sourceModelIds": [
|
||||
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed",
|
||||
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
|
||||
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4337531",
|
||||
"4336358"
|
||||
"4337531"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
@@ -1941,7 +1939,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T14:14:40.032009+00:00",
|
||||
"generatedAt": "2026-09-20T14:18:03.645070+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 94,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -425,7 +425,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T14:17:02.156410+00:00",
|
||||
"generatedAt": "2026-09-20T14:18:09.699689+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-20T14:17:02.156410+00:00",
|
||||
"catalogUpdatedAt": "2026-09-20T14:18:09.699689+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-20T14:17:02.156410+00:00",
|
||||
"generatedAt": "2026-09-20T14:18:09.699689+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6359,6 +6359,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-20T14:17:02.156410+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-20T14:18:09.699689+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T14:14:39.977491+00:00",
|
||||
"lastSyncTime": "2026-09-20T14:14:39.678936+00:00",
|
||||
"generatedAt": "2026-09-20T14:18:03.550019+00:00",
|
||||
"lastSyncTime": "2026-09-20T14:18:03.259028+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1497,7 +1497,7 @@
|
||||
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 2,
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-16T01:37:21+00:00",
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"latestFailureAt": "2026-09-16T01:37:21+00:00",
|
||||
@@ -1505,12 +1505,10 @@
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5",
|
||||
"sourceModelIds": [
|
||||
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed",
|
||||
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
|
||||
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4337531",
|
||||
"4336358"
|
||||
"4337531"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
@@ -2236,15 +2234,15 @@
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 11,
|
||||
"attributableFailureCount": 12,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 11,
|
||||
"decisionTotal": 12,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 11
|
||||
"framework_architecture_unsupported": 12
|
||||
},
|
||||
"failureCount": 28,
|
||||
"failureCount": 29,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -2254,7 +2252,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 28,
|
||||
"total": 29,
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
@@ -3649,7 +3647,7 @@
|
||||
"decisionSuccessRate": 0.0359,
|
||||
"decisionTotal": 641,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 124,
|
||||
"ambiguous_runtime": 125,
|
||||
"architecture_compatibility": 20,
|
||||
"backend_operator": 43,
|
||||
"context_length": 46,
|
||||
@@ -3661,7 +3659,7 @@
|
||||
"tokenizer_compatibility": 78,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 754,
|
||||
"failureCount": 755,
|
||||
"failureRate": 0.9704,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3671,8 +3669,8 @@
|
||||
"successRate": 0.0296,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 777,
|
||||
"unresolvedFailureCount": 133
|
||||
"total": 778,
|
||||
"unresolvedFailureCount": 134
|
||||
},
|
||||
"MetaX_c-500|vllm|unknown": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4463,7 +4461,7 @@
|
||||
"decisionSuccessRate": 0.0217,
|
||||
"decisionTotal": 3551,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1429,
|
||||
"ambiguous_runtime": 1430,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
@@ -4477,15 +4475,15 @@
|
||||
"tokenizer_compatibility": 408,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5807,
|
||||
"failureCount": 5808,
|
||||
"failureRate": 0.9869,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 77,
|
||||
"successRate": 0.0131,
|
||||
"total": 5884,
|
||||
"unresolvedFailureCount": 1469
|
||||
"total": 5885,
|
||||
"unresolvedFailureCount": 1470
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4599,26 +4597,26 @@
|
||||
"unresolvedFailureCount": 123
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 25,
|
||||
"decisionFailureRate": 0.9259,
|
||||
"decisionSuccessRate": 0.0741,
|
||||
"decisionTotal": 27,
|
||||
"attributableFailureCount": 26,
|
||||
"decisionFailureRate": 0.9286,
|
||||
"decisionSuccessRate": 0.0714,
|
||||
"decisionTotal": 28,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 24,
|
||||
"framework_architecture_unsupported": 25
|
||||
"framework_architecture_unsupported": 26
|
||||
},
|
||||
"failureCount": 49,
|
||||
"failureRate": 0.9608,
|
||||
"failureCount": 50,
|
||||
"failureRate": 0.9615,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0392,
|
||||
"total": 51,
|
||||
"successRate": 0.0385,
|
||||
"total": 52,
|
||||
"unresolvedFailureCount": 24
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T14:14:39.968836+00:00",
|
||||
"generatedAt": "2026-09-20T14:18:03.541951+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 75,
|
||||
@@ -4646,14 +4644,14 @@
|
||||
"unresolvedFailureCount": 108
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 304,
|
||||
"decisionFailureRate": 0.8306,
|
||||
"decisionSuccessRate": 0.1694,
|
||||
"decisionTotal": 366,
|
||||
"attributableFailureCount": 305,
|
||||
"decisionFailureRate": 0.8311,
|
||||
"decisionSuccessRate": 0.1689,
|
||||
"decisionTotal": 367,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 145,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 164,
|
||||
"framework_architecture_unsupported": 165,
|
||||
"memory_capacity": 18,
|
||||
"model_load": 85,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -4663,14 +4661,14 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 893,
|
||||
"failureCount": 894,
|
||||
"failureRate": 0.9351,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 62,
|
||||
"successRate": 0.0649,
|
||||
"total": 955,
|
||||
"total": 956,
|
||||
"unresolvedFailureCount": 588
|
||||
},
|
||||
"Biren_166m": {
|
||||
@@ -4888,7 +4886,7 @@
|
||||
"decisionSuccessRate": 0.1807,
|
||||
"decisionTotal": 797,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 296,
|
||||
"ambiguous_runtime": 297,
|
||||
"architecture_compatibility": 21,
|
||||
"backend_operator": 43,
|
||||
"context_length": 59,
|
||||
@@ -4902,15 +4900,15 @@
|
||||
"日志缺失": 15,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1415,
|
||||
"failureRate": 0.9076,
|
||||
"failureCount": 1416,
|
||||
"failureRate": 0.9077,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 144,
|
||||
"successRate": 0.0924,
|
||||
"total": 1559,
|
||||
"unresolvedFailureCount": 757
|
||||
"successRate": 0.0923,
|
||||
"total": 1560,
|
||||
"unresolvedFailureCount": 758
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"attributableFailureCount": 69,
|
||||
@@ -5620,14 +5618,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
|
||||
"attributableFailureCount": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 2
|
||||
"framework_architecture_unsupported": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "qwen3_5",
|
||||
@@ -5639,7 +5637,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|none": {
|
||||
@@ -11454,14 +11452,15 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"backend_operator": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T13:34:22.859810+00:00",
|
||||
"lastTerminalAt": "2026-09-20T14:18:03.259001+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -11469,8 +11468,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -11552,18 +11551,18 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 3,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"platform_infrastructure": 3,
|
||||
"tokenizer_compatibility": 6
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureCount": 11,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
|
||||
@@ -11575,7 +11574,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 12,
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -13824,6 +13823,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -21942,20 +21965,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15862,
|
||||
"totalRecords": 15967,
|
||||
"terminalRecords": 15864,
|
||||
"totalRecords": 15969,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5754,
|
||||
"decisionFailureRate": 0.8616,
|
||||
"decisionSuccessRate": 0.1384,
|
||||
"decisionTotal": 6678,
|
||||
"attributableFailureCount": 5755,
|
||||
"decisionFailureRate": 0.8617,
|
||||
"decisionSuccessRate": 0.1383,
|
||||
"decisionTotal": 6679,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3760,
|
||||
"ambiguous_runtime": 3761,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
"context_length": 318,
|
||||
"framework_architecture_unsupported": 1984,
|
||||
"framework_architecture_unsupported": 1985,
|
||||
"memory_capacity": 1195,
|
||||
"model_load": 478,
|
||||
"platform_infrastructure": 922,
|
||||
@@ -21966,15 +21989,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14938,
|
||||
"failureRate": 0.9417,
|
||||
"failureCount": 14940,
|
||||
"failureRate": 0.9418,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 924,
|
||||
"successRate": 0.0583,
|
||||
"total": 15862,
|
||||
"unresolvedFailureCount": 8262
|
||||
"successRate": 0.0582,
|
||||
"total": 15864,
|
||||
"unresolvedFailureCount": 8263
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -22019,12 +22042,12 @@
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|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|transformers|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|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 Ascend_910-b3|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 Ascend_910-b3|vllm|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": 15967,
|
||||
"summarizedRecords": 15969,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T14:18:03.259001+00:00", "modelId": "QuantTrio/Kimi-Dev-72B-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:17:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079164", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-20T13:34:22.859864+00:00", "modelId": "AI-ModelScope/granite-20b-code-instruct-8k", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T13:31:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079142", "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": "2026-09-20T13:34:22.859810+00:00", "modelId": "KenDual3090tiNvlink/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T13:31:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079137", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901980+00:00", "modelId": "AI-ModelScope/granite-20b-code-base-8k", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T12:09:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079967", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 64.0, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-13T21:27:15.041934+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4581573", "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_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912761+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152538", "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", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-13T21:09:24.912775+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490277", "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_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912708+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:01:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4336358", "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": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "992b389188f1dca7d2fa6160f3274d20ff5dd1c2e8551779e9a6d1c365545499",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "b8862deb8994239b880fd8e380c3e15113e5d06294e2354acc35329347eb827f",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "bac8de2640d2432ddc67fc5458c6e7743fbf5c53330d86fa9f91e6ab1101b8d4",
|
||||
".modelhub_state/official_capabilities.json": "3cda1b2811e873713d6a1a5f395ac3593ea093b78cf10a50ee169d96468de2de",
|
||||
".modelhub_state/outcome_checkpoint.json": "f1726fa082f227b3030a2656464c04156814bb9c64a6b0e5fc711ccee5f4e39f",
|
||||
".modelhub_state/market_intelligence.json": "5490a7e20175c9c88c2192275120e57e31204c0187dcc27228596f4e95a2e86f",
|
||||
".modelhub_state/official_capabilities.json": "c0c36c859a7ec0e6b689fac1babe1350e818843fd152d7680c4a3e43bf853bc5",
|
||||
".modelhub_state/outcome_checkpoint.json": "4b00d785cc5862e528d9c09b67d593e6c88c8c837839923b1bd4a440c329e0ae",
|
||||
".modelhub_state/queue_cleanup_latest.json": "eb01f106d0cd4018a0346c4a81182d6a9e67f5d4d14db22f5d0c685667977bc3",
|
||||
".modelhub_state/recent_outcomes.jsonl": "306abefa1d94764ce0350dd8b4815acc6ec4602b6d992e6626fe9440d199eebb",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "1dc5ca356c786d9a2dd8258cbea673a28c92d49d05ed52b2e65736c79625bdce",
|
||||
".modelhub_state/recovery_intents.jsonl": "5580d6e970098701e3c6bf3ee7e7eb81088ac2b9444860c412494b63cc4d5df5",
|
||||
".modelhub_state/recent_outcomes.jsonl": "fad94d7ea1d6962f0fe7650d214b0e1aa90a82232ba2448ec1e4c44e89010e61",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "9344d95f6fdfd650f7913666faaf5c72e86c4f7f4e2c26df783f1079cee518f4",
|
||||
".modelhub_state/recovery_intents.jsonl": "c6534fb8773166bb08bfe04025da0673b3b10fd895b6302756af6cce40994fe1",
|
||||
".modelhub_state/routing_intelligence.json": "118dae164974fbee630f675d1810a874d8a3847f8fc8d3df4b9ea0e460e45f4a",
|
||||
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
|
||||
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
||||
"ledger/submissions.jsonl": "ec4279c2ddeba3d2b67abee40458baf34fc1c2c77a6b7db9ee7890ebb6627868",
|
||||
"outcomes/submissions.jsonl": "028356caa29db375b68b280713233e87803e11a617721930266199e42f4fc313"
|
||||
"outcomes/submissions.jsonl": "845736acaaa9080a489453f6db0052e9b03a4365f6f4d52a247d7bde4f975973"
|
||||
},
|
||||
"generation": 10615,
|
||||
"generation": 10616,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-20T14:17:02.563183+00:00",
|
||||
"updatedAt": "2026-09-20T14:18:10.561829+00:00",
|
||||
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
||||
}
|
||||
|
||||
@@ -148,7 +148,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T10:04:06.914723+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T02:01:08.689124+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4750549", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402577+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:37.213099+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751426", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T13:14:20.004672+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:13:27.470794+00:00", "targetGpu": "Vastai_va16", "taskId": "4753071", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:30:05.632354+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:29:20.581004+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4753478", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004708+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.451335+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753714", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004674+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.452554+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753715", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T13:55:40.785159+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1764a9124cd000c7904ba9cee10ecdf5f9bfd4e65fc6896e0120a683f5e606e3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:54:18.783901+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754025", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -978,8 +977,8 @@
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T13:18:18.977292+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T05:16:13.324611+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4971311", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-20T13:34:22.859851+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T05:31:42.868717+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4971506", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-20T13:34:22.859841+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16314185171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T05:31:42.867294+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4971507", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615358}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:16:07.298594+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972201", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T14:18:03.259019+00:00", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615358}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T06:16:07.298594+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972201", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T14:18:03.258951+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:17:57.834294+00:00", "targetGpu": "Biren_166m", "taskId": "4972230", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:19:35.394755+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4972231", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:31:52.552038+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972399", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user