state: generation 10851 (cycle)
This commit is contained in:
@@ -2146,7 +2146,7 @@
|
|||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-20T19:53:02.825174+00:00",
|
"generatedAt": "2026-09-20T19:56:30.479591+00:00",
|
||||||
"summary": {
|
"summary": {
|
||||||
"activeBlockCount": 105,
|
"activeBlockCount": 105,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
|
|||||||
@@ -425,7 +425,7 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"frameworkUpdatedAt": null,
|
"frameworkUpdatedAt": null,
|
||||||
"generatedAt": "2026-09-20T19:55:28.776698+00:00",
|
"generatedAt": "2026-09-20T19:56:36.630449+00:00",
|
||||||
"gpuStats": {
|
"gpuStats": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"available": true,
|
"available": true,
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"catalogUpdatedAt": "2026-09-20T19:55:28.776698+00:00",
|
"catalogUpdatedAt": "2026-09-20T19:56:36.630449+00:00",
|
||||||
"configuredTaskTypes": [
|
"configuredTaskTypes": [
|
||||||
"text-generation"
|
"text-generation"
|
||||||
],
|
],
|
||||||
@@ -56,7 +56,7 @@
|
|||||||
"time-series-forecasting"
|
"time-series-forecasting"
|
||||||
],
|
],
|
||||||
"errors": [],
|
"errors": [],
|
||||||
"generatedAt": "2026-09-20T19:55:28.776698+00:00",
|
"generatedAt": "2026-09-20T19:56:36.630449+00:00",
|
||||||
"gpuCatalog": {
|
"gpuCatalog": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
@@ -6383,6 +6383,6 @@
|
|||||||
"updateTime": "2025-12-22 08:59:53"
|
"updateTime": "2025-12-22 08:59:53"
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"taskTreeUpdatedAt": "2026-09-20T19:55:28.776698+00:00",
|
"taskTreeUpdatedAt": "2026-09-20T19:56:36.630449+00:00",
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"generatedAt": "2026-09-20T19:49:27.002621+00:00",
|
"generatedAt": "2026-09-20T19:56:30.417799+00:00",
|
||||||
"lastSyncTime": "2026-09-20T19:49:26.756443+00:00",
|
"lastSyncTime": "2026-09-20T19:56:29.962443+00:00",
|
||||||
"recentLimit": 300,
|
"recentLimit": 300,
|
||||||
"report": {
|
"report": {
|
||||||
"architectureCompatibilityBlocks": {
|
"architectureCompatibilityBlocks": {
|
||||||
@@ -3096,18 +3096,18 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|transformers|text-generation": {
|
"Iluvatar_bi-150|transformers|text-generation": {
|
||||||
"attributableFailureCount": 19,
|
"attributableFailureCount": 20,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 19,
|
"decisionTotal": 20,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 7,
|
"ambiguous_runtime": 7,
|
||||||
"framework_architecture_unsupported": 6,
|
"framework_architecture_unsupported": 6,
|
||||||
"memory_capacity": 5,
|
"memory_capacity": 5,
|
||||||
"model_load": 2,
|
"model_load": 2,
|
||||||
"tokenizer_compatibility": 6
|
"tokenizer_compatibility": 7
|
||||||
},
|
},
|
||||||
"failureCount": 26,
|
"failureCount": 27,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "transformers",
|
"framework": "transformers",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
@@ -3117,7 +3117,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
"targetGpu": "Iluvatar_bi-150",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 26,
|
"total": 27,
|
||||||
"unresolvedFailureCount": 7
|
"unresolvedFailureCount": 7
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|unknown|asr": {
|
"Iluvatar_bi-150|unknown|asr": {
|
||||||
@@ -4533,18 +4533,18 @@
|
|||||||
"unresolvedFailureCount": 72
|
"unresolvedFailureCount": 72
|
||||||
},
|
},
|
||||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
||||||
"attributableFailureCount": 24,
|
"attributableFailureCount": 25,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 24,
|
"decisionTotal": 25,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 12,
|
"ambiguous_runtime": 12,
|
||||||
"framework_architecture_unsupported": 14,
|
"framework_architecture_unsupported": 14,
|
||||||
"model_load": 3,
|
"model_load": 3,
|
||||||
"runtime_memory": 7,
|
"runtime_memory": 8,
|
||||||
"参数/模板问题": 8
|
"参数/模板问题": 8
|
||||||
},
|
},
|
||||||
"failureCount": 44,
|
"failureCount": 45,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm-patch-tokenizer",
|
"framework": "vllm-patch-tokenizer",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
@@ -4554,7 +4554,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "hygon_k100-ai",
|
"targetGpu": "hygon_k100-ai",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 44,
|
"total": 45,
|
||||||
"unresolvedFailureCount": 20
|
"unresolvedFailureCount": 20
|
||||||
},
|
},
|
||||||
"hygon_k100-ai|vllm|text-generation": {
|
"hygon_k100-ai|vllm|text-generation": {
|
||||||
@@ -4656,25 +4656,25 @@
|
|||||||
"unresolvedFailureCount": 114
|
"unresolvedFailureCount": 114
|
||||||
},
|
},
|
||||||
"transformers": {
|
"transformers": {
|
||||||
"attributableFailureCount": 20,
|
"attributableFailureCount": 21,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 20,
|
"decisionTotal": 21,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 42,
|
"ambiguous_runtime": 42,
|
||||||
"framework_architecture_unsupported": 7,
|
"framework_architecture_unsupported": 7,
|
||||||
"memory_capacity": 5,
|
"memory_capacity": 5,
|
||||||
"model_load": 2,
|
"model_load": 2,
|
||||||
"tokenizer_compatibility": 6
|
"tokenizer_compatibility": 7
|
||||||
},
|
},
|
||||||
"failureCount": 62,
|
"failureCount": 63,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 0,
|
"successCount": 0,
|
||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"total": 62,
|
"total": 63,
|
||||||
"unresolvedFailureCount": 42
|
"unresolvedFailureCount": 42
|
||||||
},
|
},
|
||||||
"unknown": {
|
"unknown": {
|
||||||
@@ -4779,25 +4779,25 @@
|
|||||||
"unresolvedFailureCount": 48
|
"unresolvedFailureCount": 48
|
||||||
},
|
},
|
||||||
"vllm-patch-tokenizer": {
|
"vllm-patch-tokenizer": {
|
||||||
"attributableFailureCount": 24,
|
"attributableFailureCount": 25,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 24,
|
"decisionTotal": 25,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 12,
|
"ambiguous_runtime": 12,
|
||||||
"framework_architecture_unsupported": 14,
|
"framework_architecture_unsupported": 14,
|
||||||
"model_load": 3,
|
"model_load": 3,
|
||||||
"runtime_memory": 7,
|
"runtime_memory": 8,
|
||||||
"参数/模板问题": 8
|
"参数/模板问题": 8
|
||||||
},
|
},
|
||||||
"failureCount": 44,
|
"failureCount": 45,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 0,
|
"successCount": 0,
|
||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"total": 44,
|
"total": 45,
|
||||||
"unresolvedFailureCount": 20
|
"unresolvedFailureCount": 20
|
||||||
},
|
},
|
||||||
"vllm_0_17_0_corex_4_4_0": {
|
"vllm_0_17_0_corex_4_4_0": {
|
||||||
@@ -4870,7 +4870,7 @@
|
|||||||
"unresolvedFailureCount": 32
|
"unresolvedFailureCount": 32
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-20T19:49:26.994192+00:00",
|
"generatedAt": "2026-09-20T19:56:30.408875+00:00",
|
||||||
"gpuSummaries": {
|
"gpuSummaries": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"attributableFailureCount": 78,
|
"attributableFailureCount": 78,
|
||||||
@@ -5032,10 +5032,10 @@
|
|||||||
"unresolvedFailureCount": 551
|
"unresolvedFailureCount": 551
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150": {
|
"Iluvatar_bi-150": {
|
||||||
"attributableFailureCount": 735,
|
"attributableFailureCount": 736,
|
||||||
"decisionFailureRate": 0.8314,
|
"decisionFailureRate": 0.8316,
|
||||||
"decisionSuccessRate": 0.1686,
|
"decisionSuccessRate": 0.1684,
|
||||||
"decisionTotal": 884,
|
"decisionTotal": 885,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 614,
|
"ambiguous_runtime": 614,
|
||||||
"architecture_compatibility": 15,
|
"architecture_compatibility": 15,
|
||||||
@@ -5047,19 +5047,19 @@
|
|||||||
"platform_infrastructure": 21,
|
"platform_infrastructure": 21,
|
||||||
"repository_structure": 99,
|
"repository_structure": 99,
|
||||||
"runtime_memory": 12,
|
"runtime_memory": 12,
|
||||||
"tokenizer_compatibility": 52,
|
"tokenizer_compatibility": 53,
|
||||||
"参数/模板问题": 319,
|
"参数/模板问题": 319,
|
||||||
"日志缺失": 155,
|
"日志缺失": 155,
|
||||||
"验证失败": 30
|
"验证失败": 30
|
||||||
},
|
},
|
||||||
"failureCount": 1874,
|
"failureCount": 1875,
|
||||||
"failureRate": 0.9263,
|
"failureRate": 0.9264,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 21,
|
"platformFailureCount": 21,
|
||||||
"successCount": 149,
|
"successCount": 149,
|
||||||
"successRate": 0.0737,
|
"successRate": 0.0736,
|
||||||
"total": 2023,
|
"total": 2024,
|
||||||
"unresolvedFailureCount": 1118
|
"unresolvedFailureCount": 1118
|
||||||
},
|
},
|
||||||
"Iluvatar_mrv-100": {
|
"Iluvatar_mrv-100": {
|
||||||
@@ -5252,10 +5252,10 @@
|
|||||||
"unresolvedFailureCount": 1303
|
"unresolvedFailureCount": 1303
|
||||||
},
|
},
|
||||||
"hygon_k100-ai": {
|
"hygon_k100-ai": {
|
||||||
"attributableFailureCount": 689,
|
"attributableFailureCount": 690,
|
||||||
"decisionFailureRate": 0.9583,
|
"decisionFailureRate": 0.9583,
|
||||||
"decisionSuccessRate": 0.0417,
|
"decisionSuccessRate": 0.0417,
|
||||||
"decisionTotal": 719,
|
"decisionTotal": 720,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 299,
|
"ambiguous_runtime": 299,
|
||||||
"architecture_compatibility": 32,
|
"architecture_compatibility": 32,
|
||||||
@@ -5266,20 +5266,20 @@
|
|||||||
"model_load": 59,
|
"model_load": 59,
|
||||||
"platform_infrastructure": 4,
|
"platform_infrastructure": 4,
|
||||||
"repository_structure": 116,
|
"repository_structure": 116,
|
||||||
"runtime_memory": 60,
|
"runtime_memory": 61,
|
||||||
"tokenizer_compatibility": 79,
|
"tokenizer_compatibility": 79,
|
||||||
"参数/模板问题": 376,
|
"参数/模板问题": 376,
|
||||||
"日志缺失": 66,
|
"日志缺失": 66,
|
||||||
"验证失败": 27
|
"验证失败": 27
|
||||||
},
|
},
|
||||||
"failureCount": 1461,
|
"failureCount": 1462,
|
||||||
"failureRate": 0.9799,
|
"failureRate": 0.9799,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 4,
|
"platformFailureCount": 4,
|
||||||
"successCount": 30,
|
"successCount": 30,
|
||||||
"successRate": 0.0201,
|
"successRate": 0.0201,
|
||||||
"total": 1491,
|
"total": 1492,
|
||||||
"unresolvedFailureCount": 768
|
"unresolvedFailureCount": 768
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
@@ -7922,14 +7922,14 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none": {
|
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 2,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 1,
|
"decisionTotal": 2,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"tokenizer_compatibility": 1
|
"tokenizer_compatibility": 2
|
||||||
},
|
},
|
||||||
"failureCount": 1,
|
"failureCount": 2,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "transformers",
|
"framework": "transformers",
|
||||||
"modelType": "qwen3_5_moe",
|
"modelType": "qwen3_5_moe",
|
||||||
@@ -7941,7 +7941,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
"targetGpu": "Iluvatar_bi-150",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 1,
|
"total": 2,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3": {
|
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3": {
|
||||||
@@ -12080,6 +12080,29 @@
|
|||||||
"total": 1,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none": {
|
||||||
|
"attributableFailureCount": 1,
|
||||||
|
"decisionFailureRate": 1.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 1,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"runtime_memory": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm-patch-tokenizer",
|
||||||
|
"modelType": "qwen2",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 0,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "hygon_k100-ai",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
|
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
|
||||||
"attributableFailureCount": 3,
|
"attributableFailureCount": 3,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
@@ -12501,18 +12524,18 @@
|
|||||||
"unresolvedFailureCount": 3
|
"unresolvedFailureCount": 3
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||||
"attributableFailureCount": 7,
|
"attributableFailureCount": 6,
|
||||||
"consecutiveFailures": 3,
|
"consecutiveFailures": 3,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 0.7778,
|
"decisionFailureRate": 0.75,
|
||||||
"decisionSuccessRate": 0.2222,
|
"decisionSuccessRate": 0.25,
|
||||||
"decisionTotal": 9,
|
"decisionTotal": 8,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 3,
|
"ambiguous_runtime": 3,
|
||||||
"framework_architecture_unsupported": 7
|
"framework_architecture_unsupported": 6
|
||||||
},
|
},
|
||||||
"failureCount": 10,
|
"failureCount": 9,
|
||||||
"failureRate": 0.8333,
|
"failureRate": 0.8182,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
"lastTerminalAt": "2026-09-17T10:44:59.509445+00:00",
|
"lastTerminalAt": "2026-09-17T10:44:59.509445+00:00",
|
||||||
@@ -12520,10 +12543,10 @@
|
|||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 2,
|
"successCount": 2,
|
||||||
"successRate": 0.1667,
|
"successRate": 0.1818,
|
||||||
"targetGpu": "Cambricon_mlu-370-x4",
|
"targetGpu": "Cambricon_mlu-370-x4",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 12,
|
"total": 11,
|
||||||
"unresolvedFailureCount": 3
|
"unresolvedFailureCount": 3
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||||
@@ -12587,14 +12610,14 @@
|
|||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 4,
|
"ambiguous_runtime": 4,
|
||||||
"framework_architecture_unsupported": 5,
|
"framework_architecture_unsupported": 5,
|
||||||
"memory_capacity": 5,
|
"memory_capacity": 4,
|
||||||
"tokenizer_compatibility": 6
|
"tokenizer_compatibility": 7
|
||||||
},
|
},
|
||||||
"failureCount": 20,
|
"failureCount": 20,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "transformers",
|
"framework": "transformers",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
"lastTerminalAt": "2026-09-20T17:24:32.660503+00:00",
|
"lastTerminalAt": "2026-09-20T19:56:29.962428+00:00",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
@@ -12712,19 +12735,18 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||||
"attributableFailureCount": 11,
|
"attributableFailureCount": 10,
|
||||||
"consecutiveFailures": 1,
|
"consecutiveFailures": 1,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 0.6471,
|
"decisionFailureRate": 0.625,
|
||||||
"decisionSuccessRate": 0.3529,
|
"decisionSuccessRate": 0.375,
|
||||||
"decisionTotal": 17,
|
"decisionTotal": 16,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 1,
|
"ambiguous_runtime": 1,
|
||||||
"framework_architecture_unsupported": 10,
|
"framework_architecture_unsupported": 10
|
||||||
"tokenizer_compatibility": 1
|
|
||||||
},
|
},
|
||||||
"failureCount": 12,
|
"failureCount": 11,
|
||||||
"failureRate": 0.6667,
|
"failureRate": 0.6471,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
|
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
|
||||||
@@ -12732,10 +12754,10 @@
|
|||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 6,
|
"successCount": 6,
|
||||||
"successRate": 0.3333,
|
"successRate": 0.3529,
|
||||||
"targetGpu": "Iluvatar_mrv-100",
|
"targetGpu": "Iluvatar_mrv-100",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 18,
|
"total": 17,
|
||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800|unknown|text-generation": {
|
"Kunlunxin_p-800|unknown|text-generation": {
|
||||||
@@ -13103,17 +13125,18 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
||||||
"attributableFailureCount": 3,
|
"attributableFailureCount": 4,
|
||||||
"consecutiveFailures": 3,
|
"consecutiveFailures": 4,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 3,
|
"decisionTotal": 4,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 1,
|
"framework_architecture_unsupported": 1,
|
||||||
"model_load": 2
|
"model_load": 2,
|
||||||
|
"runtime_memory": 1
|
||||||
},
|
},
|
||||||
"failureCount": 3,
|
"failureCount": 4,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm-patch-tokenizer",
|
"framework": "vllm-patch-tokenizer",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -13125,7 +13148,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "hygon_k100-ai",
|
"targetGpu": "hygon_k100-ai",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 3,
|
"total": 4,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"hygon_k100-ai|vllm|text-generation": {
|
"hygon_k100-ai|vllm|text-generation": {
|
||||||
@@ -14108,18 +14131,18 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none": {
|
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 2,
|
||||||
"consecutiveFailures": 1,
|
"consecutiveFailures": 2,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 1,
|
"decisionTotal": 2,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"tokenizer_compatibility": 1
|
"tokenizer_compatibility": 2
|
||||||
},
|
},
|
||||||
"failureCount": 1,
|
"failureCount": 2,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "transformers",
|
"framework": "transformers",
|
||||||
"lastTerminalAt": "2026-09-20T17:24:32.660503+00:00",
|
"lastTerminalAt": "2026-09-20T19:56:29.962428+00:00",
|
||||||
"modelType": "qwen3_5_moe",
|
"modelType": "qwen3_5_moe",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
@@ -14129,7 +14152,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
"targetGpu": "Iluvatar_bi-150",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 1,
|
"total": 2,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3": {
|
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3": {
|
||||||
@@ -15510,6 +15533,31 @@
|
|||||||
"total": 2,
|
"total": 2,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none": {
|
||||||
|
"attributableFailureCount": 1,
|
||||||
|
"consecutiveFailures": 1,
|
||||||
|
"decisionFailureRate": 1.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 1,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"runtime_memory": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm-patch-tokenizer",
|
||||||
|
"lastTerminalAt": "2026-09-20T19:56:29.962443+00:00",
|
||||||
|
"modelType": "qwen2",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 0,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "hygon_k100-ai",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none": {
|
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
"consecutiveFailures": 1,
|
"consecutiveFailures": 1,
|
||||||
@@ -19285,14 +19333,14 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none|33": {
|
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none|33": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 2,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 1,
|
"decisionTotal": 2,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"tokenizer_compatibility": 1
|
"tokenizer_compatibility": 2
|
||||||
},
|
},
|
||||||
"failureCount": 1,
|
"failureCount": 2,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "transformers",
|
"framework": "transformers",
|
||||||
"loadSizeLog2Bucket": 33,
|
"loadSizeLog2Bucket": 33,
|
||||||
@@ -19305,7 +19353,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
"targetGpu": "Iluvatar_bi-150",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 1,
|
"total": 2,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3|33": {
|
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3|33": {
|
||||||
@@ -25581,6 +25629,30 @@
|
|||||||
"total": 1,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none|34": {
|
||||||
|
"attributableFailureCount": 1,
|
||||||
|
"decisionFailureRate": 1.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 1,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"runtime_memory": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm-patch-tokenizer",
|
||||||
|
"loadSizeLog2Bucket": 34,
|
||||||
|
"modelType": "qwen2",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 0,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "hygon_k100-ai",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
|
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
|
||||||
"attributableFailureCount": 3,
|
"attributableFailureCount": 3,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
@@ -25871,13 +25943,13 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"terminalRecords": 15943,
|
"terminalRecords": 15945,
|
||||||
"totalRecords": 16077,
|
"totalRecords": 16079,
|
||||||
"totals": {
|
"totals": {
|
||||||
"attributableFailureCount": 5789,
|
"attributableFailureCount": 5791,
|
||||||
"decisionFailureRate": 0.8615,
|
"decisionFailureRate": 0.8615,
|
||||||
"decisionSuccessRate": 0.1385,
|
"decisionSuccessRate": 0.1385,
|
||||||
"decisionTotal": 6720,
|
"decisionTotal": 6722,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 3799,
|
"ambiguous_runtime": 3799,
|
||||||
"architecture_compatibility": 212,
|
"architecture_compatibility": 212,
|
||||||
@@ -25889,20 +25961,20 @@
|
|||||||
"model_load": 484,
|
"model_load": 484,
|
||||||
"platform_infrastructure": 922,
|
"platform_infrastructure": 922,
|
||||||
"repository_structure": 734,
|
"repository_structure": 734,
|
||||||
"runtime_memory": 81,
|
"runtime_memory": 82,
|
||||||
"tokenizer_compatibility": 655,
|
"tokenizer_compatibility": 656,
|
||||||
"参数/模板问题": 3110,
|
"参数/模板问题": 3110,
|
||||||
"日志缺失": 719,
|
"日志缺失": 719,
|
||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 15012,
|
"failureCount": 15014,
|
||||||
"failureRate": 0.9416,
|
"failureRate": 0.9416,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 922,
|
"platformFailureCount": 922,
|
||||||
"successCount": 931,
|
"successCount": 931,
|
||||||
"successRate": 0.0584,
|
"successRate": 0.0584,
|
||||||
"total": 15943,
|
"total": 15945,
|
||||||
"unresolvedFailureCount": 8301
|
"unresolvedFailureCount": 8301
|
||||||
},
|
},
|
||||||
"warnings": [
|
"warnings": [
|
||||||
@@ -25948,12 +26020,12 @@
|
|||||||
"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 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 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 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 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 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。"
|
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
"storageMode": "decision_state_only",
|
"storageMode": "decision_state_only",
|
||||||
"summarizedRecords": 16077,
|
"summarizedRecords": 16079,
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -13,6 +13,7 @@
|
|||||||
{"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": 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": "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}
|
{"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}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T19:56:29.962428+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T11:44:01.235722+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4978143", "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"], "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600461+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T11:23:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4523512", "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"], "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600461+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T11:23:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4523512", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T10:06:20.452855+00:00", "modelId": "KoboldAI/fairseq-dense-13B-Janeway", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079951", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T10:06:20.452855+00:00", "modelId": "KoboldAI/fairseq-dense-13B-Janeway", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079951", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-20T09:38:38.259110+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560061", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-20T09:38:38.259110+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560061", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -129,6 +130,7 @@
|
|||||||
{"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": "2026-09-20T19:47:52.978239+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959304, "estimatedRequiredGiB": 18.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16801630203, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8389956608, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16801630203}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:52.295134+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969090", "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": "2026-09-20T19:47:52.978239+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959304, "estimatedRequiredGiB": 18.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16801630203, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8389956608, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16801630203}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:52.295134+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969090", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T19:19:40.458840+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:52.134762+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969081", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T19:19:40.458840+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:52.134762+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969081", "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-patch-tokenizer", "lastSyncTime": "2026-09-20T18:53:01.473075+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "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": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:52.043508+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969075", "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-patch-tokenizer", "lastSyncTime": "2026-09-20T18:53:01.473075+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "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": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:52.043508+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969075", "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": "2026-09-20T19:56:29.962443+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.939142+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969070", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Cohere2ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266177+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730845002, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730845002}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.937617+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969071", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Cohere2ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266177+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730845002, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730845002}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.937617+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969071", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T16:44:23.353846+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.842110+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969064", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T16:44:23.353846+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.842110+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969064", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T17:09:45.266185+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.693959+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969057", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T17:09:45.266185+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.693959+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969057", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -296,5 +298,3 @@
|
|||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-15T01:43:44.814965+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T01:39:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4570941", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-15T01:43:44.814965+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T01:39:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4570941", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T01:43:44.814946+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T01:37:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4591253", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T01:43:44.814946+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T01:37:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4591253", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T01:34:13.208356+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T01:27:22+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4584699", "taskType": "text-generation", "verifyResult": 1}
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T01:34:13.208356+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T01:27:22+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4584699", "taskType": "text-generation", "verifyResult": 1}
|
||||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-15T01:15:42.313690+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T01:15:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4588142", "taskType": "text-generation", "verifyResult": -1}
|
|
||||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T00:56:25.725574+00:00", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:53:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4332632", "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",
|
"agentVersion": "2026.09.20.2",
|
||||||
"checksums": {
|
"checksums": {
|
||||||
".modelhub_state/architecture_compatibility_blacklist.json": "47850a76d1268235ef0789eda9b7caa2af9eb4f595d93e2a7aad617eca50dcf2",
|
".modelhub_state/architecture_compatibility_blacklist.json": "6870a78e3e8c4cdf7921e00e9a3069e1f10023dd58382dc6fa58862fdf971cf2",
|
||||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||||
".modelhub_state/market_intelligence.json": "d12b020d3b68e291e91a41f3b3da4457ae329ea4aa6e5c4ce1327130d5fa9b96",
|
".modelhub_state/market_intelligence.json": "3e7915ef897f553895fee3a28597680cf6ab2e34912e0bc724abb1d6049c4c3b",
|
||||||
".modelhub_state/official_capabilities.json": "1c5b3037fa59a48f7e4f57aa248d6d054b655b205e00ffc9ac9dcd62500d8338",
|
".modelhub_state/official_capabilities.json": "0a081fb46a8f30707240444e4a9b61e8865046c9a2078fb0c7cee52b88bda66a",
|
||||||
".modelhub_state/outcome_checkpoint.json": "5a4693524f6444d73ef95e7cac0ee62265a7f7f45bacea90c74295f3a971dc49",
|
".modelhub_state/outcome_checkpoint.json": "4fd4f1cb0b13defb71ac7574c667d0936d5c0e21d4d3259a3820214c2f763dfd",
|
||||||
".modelhub_state/queue_cleanup_latest.json": "51060760318808c95c5f937aac9389cef4379d95a33f6213764b0f798b1c6bb9",
|
".modelhub_state/queue_cleanup_latest.json": "51060760318808c95c5f937aac9389cef4379d95a33f6213764b0f798b1c6bb9",
|
||||||
".modelhub_state/recent_outcomes.jsonl": "7c1b422f06fbcb3d6542a99fca8ef48396ea3b58bd6d8f5c7e4de37780a97056",
|
".modelhub_state/recent_outcomes.jsonl": "5c873ffa8b44292015073e04b41602a36cb5b5f43eaa3564a5b9b4f3d8a9454f",
|
||||||
".modelhub_state/recovery_active_tasks.jsonl": "444248711c6abe67ead20b16b611a15b1c8db7ac3e8e0873658d9fcf0e69699b",
|
".modelhub_state/recovery_active_tasks.jsonl": "a7140bb6418479453e679c6ecf8ebbb4eb466db294fbda367ba8460f1b60a817",
|
||||||
".modelhub_state/recovery_intents.jsonl": "20a7c1011dc93ec9bd4bc6faa8214ee3840014e3c020542a6f2ad20642c45ab9",
|
".modelhub_state/recovery_intents.jsonl": "05d6df8ce442ac7d6ffab37f9e0717387a22f6bb9f8b75aa33b9509c65532571",
|
||||||
".modelhub_state/routing_intelligence.json": "c33a7fbab3e566aa23f9641b71cfeeaa0ee35eeddce5e0c594ef70fe2cf316b9",
|
".modelhub_state/routing_intelligence.json": "c33a7fbab3e566aa23f9641b71cfeeaa0ee35eeddce5e0c594ef70fe2cf316b9",
|
||||||
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
|
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
|
||||||
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
||||||
"ledger/submissions.jsonl": "f2f7d4daeb4b84ce99dbf54171ce91a4acf63001daeaf75c957d4e883665e240",
|
"ledger/submissions.jsonl": "f2f7d4daeb4b84ce99dbf54171ce91a4acf63001daeaf75c957d4e883665e240",
|
||||||
"outcomes/submissions.jsonl": "eb1f4c950e94f6f670b9cfd1cedc6be832b0ac1598ab4ab73dd31da731c720d5"
|
"outcomes/submissions.jsonl": "a728429aab9620cefd304aea6fb87cea9a579c327ce9b2c359b2ea3ed81863c3"
|
||||||
},
|
},
|
||||||
"generation": 10850,
|
"generation": 10851,
|
||||||
"phase": "cycle",
|
"phase": "cycle",
|
||||||
"schemaVersion": 1,
|
"schemaVersion": 1,
|
||||||
"updatedAt": "2026-09-20T19:55:29.206798+00:00",
|
"updatedAt": "2026-09-20T19:56:37.534111+00:00",
|
||||||
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -491,7 +491,6 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647537+00:00", "modelId": "JANGQ-AI/DeepSeek-V4-Flash-JANGTQ-K", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 85870266317, "estimatedRequiredGiB": 95.98, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 85881510108, "modelscopeLicense": "mit", "modelscopeParams": 21758832856, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek", "custom_tag:deepseek-v4", "custom_tag:dsv4", "custom_tag:mixture-of-experts", "custom_tag:mla", "custom_tag:mhc", "custom_tag:sparse-indexer", "custom_tag:million-token-context", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:quantized", "custom_tag:jangtq", "custom_tag:jang"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 85881510108}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.889837+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969069", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647537+00:00", "modelId": "JANGQ-AI/DeepSeek-V4-Flash-JANGTQ-K", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 85870266317, "estimatedRequiredGiB": 95.98, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 85881510108, "modelscopeLicense": "mit", "modelscopeParams": 21758832856, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek", "custom_tag:deepseek-v4", "custom_tag:dsv4", "custom_tag:mixture-of-experts", "custom_tag:mla", "custom_tag:mhc", "custom_tag:sparse-indexer", "custom_tag:million-token-context", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:quantized", "custom_tag:jangtq", "custom_tag:jang"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 85881510108}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.889837+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969069", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647587+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.964, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16073634582, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16073634582}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.948761+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4969074", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647587+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.964, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16073634582, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16073634582}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.948761+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4969074", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647454+00:00", "modelId": "OpenBMB/MiniCPM5-1B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2161290912, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171355326, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171355326}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.958506+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969073", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647454+00:00", "modelId": "OpenBMB/MiniCPM5-1B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2161290912, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171355326, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171355326}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.958506+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969073", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647761+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.939142+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969070", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647868+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Base", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697936, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345547190, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345547190}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.956000+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969072", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647868+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Base", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697936, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345547190, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345547190}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.956000+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969072", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647532+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.136770+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969080", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647532+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.136770+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969080", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647657+00:00", "modelId": "aisingapore/Llama-SEA-LION-v2-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.961, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16071447395, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16071447395}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.096766+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969079", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647657+00:00", "modelId": "aisingapore/Llama-SEA-LION-v2-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.961, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16071447395, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16071447395}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.096766+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969079", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -954,9 +953,8 @@
|
|||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552441+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "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": 7985124576}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:20:03.373586+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977833", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552441+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "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": 7985124576}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:20:03.373586+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977833", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:47:52.978262+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T11:39:31.087174+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978074", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:47:52.978262+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T11:39:31.087174+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978074", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T19:47:52.978218+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-20T11:39:31.092445+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4978075", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T19:47:52.978218+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-20T11:39:31.092445+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4978075", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:44:01.235722+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4978143", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:53:02.766146+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T11:51:59.601108+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978230", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:53:02.766146+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T11:51:59.601108+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978230", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "pending", "submitTime": "2026-09-20T11:52:06.534997+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4978249", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:56:29.962409+00:00", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T11:52:06.534997+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4978249", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "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": 9093251763}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:54:11.089175+00:00", "targetGpu": "Biren_166m", "taskId": "4978283", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "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": 9093251763}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:54:11.089175+00:00", "targetGpu": "Biren_166m", "taskId": "4978283", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860632064, "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": 7860632064}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:12:07.582993+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978470", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860632064, "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": 7860632064}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:12:07.582993+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978470", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:12:07.735021+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4978493", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:12:07.735021+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4978493", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
|||||||
Reference in New Issue
Block a user