state: generation 16636 (cycle)
This commit is contained in:
@@ -3261,7 +3261,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-26T15:11:58.457911+00:00",
|
||||
"generatedAt": "2026-09-26T15:18:41.811996+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 164,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,7 +396,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-26T15:17:38.059900+00:00",
|
||||
"generatedAt": "2026-09-26T15:19:27.563157+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-26T15:17:38.059900+00:00",
|
||||
"catalogUpdatedAt": "2026-09-26T15:19:27.563157+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-26T15:17:38.374691+00:00",
|
||||
"generatedAt": "2026-09-26T15:19:27.563157+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6478,6 +6478,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-26T15:17:38.059900+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-26T15:19:27.563157+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-26T14:43:50.469743+00:00",
|
||||
"lastSyncTime": "2026-09-26T14:43:50.048411+00:00",
|
||||
"generatedAt": "2026-09-26T15:18:41.730884+00:00",
|
||||
"lastSyncTime": "2026-09-26T15:18:41.474100+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3870,12 +3870,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 24,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 33,
|
||||
"ambiguous_runtime": 34,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 58,
|
||||
"failureCount": 59,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3885,8 +3885,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 58,
|
||||
"unresolvedFailureCount": 34
|
||||
"total": 59,
|
||||
"unresolvedFailureCount": 35
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|feature_emb": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5961,7 +5961,7 @@
|
||||
"decisionSuccessRate": 0.0261,
|
||||
"decisionTotal": 3717,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1573,
|
||||
"ambiguous_runtime": 1574,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 92,
|
||||
@@ -5975,15 +5975,15 @@
|
||||
"tokenizer_compatibility": 415,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6112,
|
||||
"failureCount": 6113,
|
||||
"failureRate": 0.9844,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 869,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0156,
|
||||
"total": 6209,
|
||||
"unresolvedFailureCount": 1623
|
||||
"total": 6210,
|
||||
"unresolvedFailureCount": 1624
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 13,
|
||||
@@ -6133,7 +6133,7 @@
|
||||
"unresolvedFailureCount": 196
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-26T14:43:50.456953+00:00",
|
||||
"generatedAt": "2026-09-26T15:18:41.718675+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6225,7 +6225,7 @@
|
||||
"decisionSuccessRate": 0.0894,
|
||||
"decisionTotal": 817,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 487,
|
||||
"ambiguous_runtime": 488,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 297,
|
||||
@@ -6238,15 +6238,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1588,
|
||||
"failureCount": 1589,
|
||||
"failureRate": 0.9561,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0439,
|
||||
"total": 1661,
|
||||
"unresolvedFailureCount": 828
|
||||
"total": 1662,
|
||||
"unresolvedFailureCount": 829
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -11710,9 +11710,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7
|
||||
"ambiguous_runtime": 8
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "starcoder2",
|
||||
@@ -11724,8 +11724,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -22727,10 +22727,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"ambiguous_runtime": 11,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureCount": 12,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -22742,8 +22742,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 10
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 11
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -23241,18 +23241,18 @@
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 6,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 7,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 6
|
||||
"runtime_memory": 5
|
||||
},
|
||||
"failureCount": 13,
|
||||
"failureCount": 12,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -23264,7 +23264,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
@@ -23853,9 +23853,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-24T05:11:42.061432+00:00",
|
||||
@@ -23868,8 +23868,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -26096,16 +26096,16 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"runtime_memory": 3
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastTerminalAt": "2026-09-25T00:33:39.855270+00:00",
|
||||
@@ -26118,7 +26118,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3small|compressed-tensors": {
|
||||
@@ -34443,9 +34443,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -34458,8 +34458,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -50813,15 +50813,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17037,
|
||||
"totalRecords": 17258,
|
||||
"terminalRecords": 17038,
|
||||
"totalRecords": 17259,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6109,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7074,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4406,
|
||||
"ambiguous_runtime": 4407,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 127,
|
||||
@@ -50837,30 +50837,30 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16072,
|
||||
"failureCount": 16073,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 935,
|
||||
"successCount": 965,
|
||||
"successRate": 0.0566,
|
||||
"total": 17037,
|
||||
"unresolvedFailureCount": 9028
|
||||
"total": 17038,
|
||||
"unresolvedFailureCount": 9029
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -50873,7 +50873,6 @@
|
||||
"组合 Iluvatar_bi-100|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-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 Cambricon_mlu-370-x4|vllm-mlu|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 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 Ascend_910-b4|vllm_tokenizer_patch|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-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -50899,10 +50898,11 @@
|
||||
"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|llamacpp|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 MetaX_c-500|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": 17258,
|
||||
"summarizedRecords": 17259,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -292,9 +292,9 @@
|
||||
{"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", "lastSyncTime": "2026-09-24T20:32:32.162698+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449433, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:10:00.601936+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991870", "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", "lastSyncTime": "2026-09-24T05:11:42.061432+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479058, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "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": 4096479058}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:10:00.507387+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991869", "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", "lastSyncTime": "2026-09-23T14:22:36.780059+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093203965, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093203965}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:49.393439+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991868", "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", "lastSyncTime": "2026-09-26T15:18:41.474100+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "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": 7860673858, "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": 7860673858}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:49.074510+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991864", "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", "lastSyncTime": "2026-09-26T01:14:46.157779+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385522016, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407346497, "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": 4407346497}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:48.974589+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991863", "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", "lastSyncTime": "2026-09-25T09:35:33.057165+00:00", "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858541078}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:37.383882+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991862", "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", "lastSyncTime": "2026-09-26T14:37:53.556324+00:00", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299919, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299919}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:36.977617+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991858", "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", "lastSyncTime": "2026-09-26T01:14:46.157767+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:20.980304+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991857", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-24T04:50:24.455191+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788663867}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:20.778237+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4991855", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-23T18:31:34.566350+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "failed", "status": "success", "submitTime": "2026-09-21T02:09:20.683565+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4991854", "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
@@ -75,7 +75,6 @@
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T18:47:44.095472+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725851", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T18:47:44.088412+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T18:47:44.094485+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725844", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T18:47:44.086665+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725843", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T18:47:44.090923+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725849", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-08T18:47:44.093470+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725852", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/prithivMLmods/MiniCPM5-2B-GGUF", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T19:24:44.852247+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4726325", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.22.1",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "70eebcf0de3b61c9f10b194a72451a99388dcf3ba31f39fd1e98aee131fe47b9",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "1a795043ac87c1289b0c5f909d161a6c1e6ed590e68354dd10393fbaff0df34f",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "17a1d25aca2c94cb7e52472cc37f896ed42677f55bb3e9ae9090aed02a53be81",
|
||||
".modelhub_state/official_capabilities.json": "bb5aa7e13e6a10df10893acd3781965b01e84ae705393861862986ab1e3ee04f",
|
||||
".modelhub_state/outcome_checkpoint.json": "bb5f4a7c01e6de7b1b1c4b972e36989154966bc1b688a0667f37e87c36025a0a",
|
||||
".modelhub_state/market_intelligence.json": "a2d092adcb72619e44fd904aa245b42acad83f71d1d2c100c73a043820b3d1d8",
|
||||
".modelhub_state/official_capabilities.json": "d846c8a19d2f976e1b9c38de687205ae889f0e48ae3d3380bad4f1e94204187e",
|
||||
".modelhub_state/outcome_checkpoint.json": "6aced99b081a177bbdb9c9c101d9cc00e1e9e301f105ec9ae79b5170022b0113",
|
||||
".modelhub_state/queue_cleanup_latest.json": "dec10eb574f7da548f3ba2d81064346ebac4cd728c834ece356077b765895663",
|
||||
".modelhub_state/recent_outcomes.jsonl": "89091a12b8e08339d33a683faebc39b7cc6211664a15bdfffca7e3e3298c5e5e",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "9d7a34b37d43a8efe8d50f88c852d6a5159a1a48a72d1b523e0d3c8b14dc0624",
|
||||
".modelhub_state/recovery_intents.jsonl": "2313d2dbc39779d1cb4e1be5015c3c0c11cb450aad5451af01825d34e89b79bf",
|
||||
".modelhub_state/recent_outcomes.jsonl": "09812b0bf7a27689b79c30da6f01829211d9cb603f54d57682c3c883bee69b4e",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "df84db2f1f375daf3ad7c292ce24f3e0f7eddad2eefe5cc4f3823c405d8001f8",
|
||||
".modelhub_state/recovery_intents.jsonl": "c82e469140e578668c1a915513677c80c1ea6b60b5ac270b3e9c96f51d0a726a",
|
||||
".modelhub_state/routing_intelligence.json": "0ad78dee853e23a16231b973da1190753d5cf4ab1ce5194172c05d0efc98218b",
|
||||
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
|
||||
".modelhub_state/worker_crashes.jsonl": "ccd40ad86ab5068ea1c3520a48fa733cf2e4b357ae5abb95ff00728d5d1b5487",
|
||||
"ledger/submissions.jsonl": "5a902bbdb4b0fedc338dc3cf14738ed63cead69fb69dccf77816db0197e251e8",
|
||||
"outcomes/submissions.jsonl": "7a65ceabb5afa9ee189b1a181f4bf14248e6407caf816a42042457079eff0c5c"
|
||||
"ledger/submissions.jsonl": "cd4aef0faa276c3bded6aed9bc69c5ecee3efddebff8cabaa44ef279e7070065",
|
||||
"outcomes/submissions.jsonl": "019c79b80374859663d7210dde13674f57ae04d2445b8a518e47666b78644ec8"
|
||||
},
|
||||
"generation": 16635,
|
||||
"generation": 16636,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-26T15:17:38.888753+00:00",
|
||||
"updatedAt": "2026-09-26T15:19:31.330376+00:00",
|
||||
"writerId": "08206cb1993a433e83f1d3e297db2d2e"
|
||||
}
|
||||
|
||||
@@ -453,7 +453,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477654+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251901, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.095468+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991859", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477648+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.185982+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991860", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477642+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261938, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261938}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.284265+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991861", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477794+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "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": 7860673858, "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": 7860673858}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:49.074510+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991864", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477787+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479112, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "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": 4096479112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:49.174012+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991865", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477782+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:49.284039+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991866", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T12:58:50.741624+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T04:44:11.759434+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4994057", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user