state: generation 22036 (cycle)
This commit is contained in:
@@ -64,7 +64,7 @@
|
|||||||
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
|
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
|
||||||
"architectureSignature": "model_type:mini_k3",
|
"architectureSignature": "model_type:mini_k3",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
"evidenceCount": 4,
|
"evidenceCount": 5,
|
||||||
"expiresAt": "2026-10-21T19:37:12.459191+00:00",
|
"expiresAt": "2026-10-21T19:37:12.459191+00:00",
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"latestFailureAt": "2026-09-21T19:37:12.459191+00:00",
|
"latestFailureAt": "2026-09-21T19:37:12.459191+00:00",
|
||||||
@@ -73,12 +73,14 @@
|
|||||||
"modelType": "mini_k3",
|
"modelType": "mini_k3",
|
||||||
"sourceModelIds": [
|
"sourceModelIds": [
|
||||||
"nkkbr/Mini-K3-1H-decay-g2-v2_C",
|
"nkkbr/Mini-K3-1H-decay-g2-v2_C",
|
||||||
|
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B",
|
||||||
"nkkbr/Mini-K3-1H-attnres-block6-v1_C",
|
"nkkbr/Mini-K3-1H-attnres-block6-v1_C",
|
||||||
"nkkbr/Mini-K3-1H-attnres-standard-v1_B",
|
"nkkbr/Mini-K3-1H-attnres-standard-v1_B",
|
||||||
"nkkbr/Mini-K3-1H-decay-g16-v2_B"
|
"nkkbr/Mini-K3-1H-decay-g16-v2_B"
|
||||||
],
|
],
|
||||||
"sourceTaskIds": [
|
"sourceTaskIds": [
|
||||||
"5006360",
|
"5006360",
|
||||||
|
"5006359",
|
||||||
"5006364",
|
"5006364",
|
||||||
"5006357",
|
"5006357",
|
||||||
"5006356"
|
"5006356"
|
||||||
@@ -1837,7 +1839,7 @@
|
|||||||
"architectures": [
|
"architectures": [
|
||||||
"qwen3_5moeforconditionalgeneration"
|
"qwen3_5moeforconditionalgeneration"
|
||||||
],
|
],
|
||||||
"evidenceCount": 3,
|
"evidenceCount": 2,
|
||||||
"expiresAt": "2026-10-21T18:14:20.635969+00:00",
|
"expiresAt": "2026-10-21T18:14:20.635969+00:00",
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"latestFailureAt": "2026-09-21T18:14:20.635969+00:00",
|
"latestFailureAt": "2026-09-21T18:14:20.635969+00:00",
|
||||||
@@ -1846,13 +1848,11 @@
|
|||||||
"modelType": "qwen3_5_moe",
|
"modelType": "qwen3_5_moe",
|
||||||
"sourceModelIds": [
|
"sourceModelIds": [
|
||||||
"ornith-ai/Ornith-1.5-35B-A3B-NVFP4",
|
"ornith-ai/Ornith-1.5-35B-A3B-NVFP4",
|
||||||
"primitive-ai/Nex-N2.5-mini-NVFP4",
|
"primitive-ai/Nex-N2.5-mini-NVFP4"
|
||||||
"mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit"
|
|
||||||
],
|
],
|
||||||
"sourceTaskIds": [
|
"sourceTaskIds": [
|
||||||
"5005325",
|
"5005325",
|
||||||
"5003204",
|
"5003204"
|
||||||
"5000547"
|
|
||||||
],
|
],
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
"targetGpu": "Iluvatar_bi-150",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
@@ -2900,7 +2900,7 @@
|
|||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-10-08T02:39:47.707093+00:00",
|
"generatedAt": "2026-10-08T02:59:39.035434+00:00",
|
||||||
"summary": {
|
"summary": {
|
||||||
"activeBlockCount": 145,
|
"activeBlockCount": 145,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"generatedAt": "2026-10-08T02:39:47.609367+00:00",
|
"generatedAt": "2026-10-08T02:59:38.938558+00:00",
|
||||||
"lastSyncTime": "2026-10-08T02:39:47.345829+00:00",
|
"lastSyncTime": "2026-10-08T02:59:38.470354+00:00",
|
||||||
"recentLimit": 300,
|
"recentLimit": 300,
|
||||||
"report": {
|
"report": {
|
||||||
"architectureCompatibilityBlocks": {
|
"architectureCompatibilityBlocks": {
|
||||||
@@ -68,7 +68,7 @@
|
|||||||
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
|
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
|
||||||
"architectureSignature": "model_type:mini_k3",
|
"architectureSignature": "model_type:mini_k3",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
"evidenceCount": 4,
|
"evidenceCount": 5,
|
||||||
"expiresAt": "2026-10-21T19:37:12.459191+00:00",
|
"expiresAt": "2026-10-21T19:37:12.459191+00:00",
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"latestFailureAt": "2026-09-21T19:37:12.459191+00:00",
|
"latestFailureAt": "2026-09-21T19:37:12.459191+00:00",
|
||||||
@@ -77,12 +77,14 @@
|
|||||||
"modelType": "mini_k3",
|
"modelType": "mini_k3",
|
||||||
"sourceModelIds": [
|
"sourceModelIds": [
|
||||||
"nkkbr/Mini-K3-1H-decay-g2-v2_C",
|
"nkkbr/Mini-K3-1H-decay-g2-v2_C",
|
||||||
|
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B",
|
||||||
"nkkbr/Mini-K3-1H-attnres-block6-v1_C",
|
"nkkbr/Mini-K3-1H-attnres-block6-v1_C",
|
||||||
"nkkbr/Mini-K3-1H-attnres-standard-v1_B",
|
"nkkbr/Mini-K3-1H-attnres-standard-v1_B",
|
||||||
"nkkbr/Mini-K3-1H-decay-g16-v2_B"
|
"nkkbr/Mini-K3-1H-decay-g16-v2_B"
|
||||||
],
|
],
|
||||||
"sourceTaskIds": [
|
"sourceTaskIds": [
|
||||||
"5006360",
|
"5006360",
|
||||||
|
"5006359",
|
||||||
"5006364",
|
"5006364",
|
||||||
"5006357",
|
"5006357",
|
||||||
"5006356"
|
"5006356"
|
||||||
@@ -1841,7 +1843,7 @@
|
|||||||
"architectures": [
|
"architectures": [
|
||||||
"qwen3_5moeforconditionalgeneration"
|
"qwen3_5moeforconditionalgeneration"
|
||||||
],
|
],
|
||||||
"evidenceCount": 3,
|
"evidenceCount": 2,
|
||||||
"expiresAt": "2026-10-21T18:14:20.635969+00:00",
|
"expiresAt": "2026-10-21T18:14:20.635969+00:00",
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"latestFailureAt": "2026-09-21T18:14:20.635969+00:00",
|
"latestFailureAt": "2026-09-21T18:14:20.635969+00:00",
|
||||||
@@ -1850,13 +1852,11 @@
|
|||||||
"modelType": "qwen3_5_moe",
|
"modelType": "qwen3_5_moe",
|
||||||
"sourceModelIds": [
|
"sourceModelIds": [
|
||||||
"ornith-ai/Ornith-1.5-35B-A3B-NVFP4",
|
"ornith-ai/Ornith-1.5-35B-A3B-NVFP4",
|
||||||
"primitive-ai/Nex-N2.5-mini-NVFP4",
|
"primitive-ai/Nex-N2.5-mini-NVFP4"
|
||||||
"mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit"
|
|
||||||
],
|
],
|
||||||
"sourceTaskIds": [
|
"sourceTaskIds": [
|
||||||
"5005325",
|
"5005325",
|
||||||
"5003204",
|
"5003204"
|
||||||
"5000547"
|
|
||||||
],
|
],
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
"targetGpu": "Iluvatar_bi-150",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
@@ -3025,29 +3025,29 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
|
||||||
"attributableFailureCount": 51,
|
"attributableFailureCount": 52,
|
||||||
"decisionFailureRate": 0.9273,
|
"decisionFailureRate": 0.9286,
|
||||||
"decisionSuccessRate": 0.0727,
|
"decisionSuccessRate": 0.0714,
|
||||||
"decisionTotal": 55,
|
"decisionTotal": 56,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 93,
|
"ambiguous_runtime": 93,
|
||||||
"context_length": 9,
|
"context_length": 9,
|
||||||
"framework_architecture_unsupported": 41,
|
"framework_architecture_unsupported": 42,
|
||||||
"memory_capacity": 1,
|
"memory_capacity": 1,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"参数/模板问题": 8
|
"参数/模板问题": 8
|
||||||
},
|
},
|
||||||
"failureCount": 153,
|
"failureCount": 154,
|
||||||
"failureRate": 0.9745,
|
"failureRate": 0.9747,
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 4,
|
"successCount": 4,
|
||||||
"successRate": 0.0255,
|
"successRate": 0.0253,
|
||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 157,
|
"total": 158,
|
||||||
"unresolvedFailureCount": 101
|
"unresolvedFailureCount": 101
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm|text-generation": {
|
"Ascend_910-b3|vllm|text-generation": {
|
||||||
@@ -3342,10 +3342,10 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 1,
|
"decisionTotal": 1,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 135,
|
"ambiguous_runtime": 136,
|
||||||
"memory_capacity": 1
|
"memory_capacity": 1
|
||||||
},
|
},
|
||||||
"failureCount": 136,
|
"failureCount": 137,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
@@ -3355,8 +3355,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Biren_166m",
|
"targetGpu": "Biren_166m",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 136,
|
"total": 137,
|
||||||
"unresolvedFailureCount": 135
|
"unresolvedFailureCount": 136
|
||||||
},
|
},
|
||||||
"Biren_166m|vllm|text-generation": {
|
"Biren_166m|vllm|text-generation": {
|
||||||
"attributableFailureCount": 50,
|
"attributableFailureCount": 50,
|
||||||
@@ -5757,7 +5757,7 @@
|
|||||||
"decisionSuccessRate": 0.0275,
|
"decisionSuccessRate": 0.0275,
|
||||||
"decisionTotal": 182,
|
"decisionTotal": 182,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 384,
|
"ambiguous_runtime": 385,
|
||||||
"backend_operator": 9,
|
"backend_operator": 9,
|
||||||
"framework_architecture_unsupported": 49,
|
"framework_architecture_unsupported": 49,
|
||||||
"memory_capacity": 10,
|
"memory_capacity": 10,
|
||||||
@@ -5766,26 +5766,26 @@
|
|||||||
"tokenizer_compatibility": 96,
|
"tokenizer_compatibility": 96,
|
||||||
"参数/模板问题": 13
|
"参数/模板问题": 13
|
||||||
},
|
},
|
||||||
"failureCount": 601,
|
"failureCount": 602,
|
||||||
"failureRate": 0.9917,
|
"failureRate": 0.9918,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 27,
|
"platformFailureCount": 27,
|
||||||
"successCount": 5,
|
"successCount": 5,
|
||||||
"successRate": 0.0083,
|
"successRate": 0.0082,
|
||||||
"total": 606,
|
"total": 607,
|
||||||
"unresolvedFailureCount": 397
|
"unresolvedFailureCount": 398
|
||||||
},
|
},
|
||||||
"vllm_tokenizer_patch": {
|
"vllm_tokenizer_patch": {
|
||||||
"attributableFailureCount": 163,
|
"attributableFailureCount": 164,
|
||||||
"decisionFailureRate": 0.9422,
|
"decisionFailureRate": 0.9425,
|
||||||
"decisionSuccessRate": 0.0578,
|
"decisionSuccessRate": 0.0575,
|
||||||
"decisionTotal": 173,
|
"decisionTotal": 174,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 208,
|
"ambiguous_runtime": 208,
|
||||||
"backend_operator": 15,
|
"backend_operator": 15,
|
||||||
"context_length": 9,
|
"context_length": 9,
|
||||||
"framework_architecture_unsupported": 105,
|
"framework_architecture_unsupported": 106,
|
||||||
"memory_capacity": 2,
|
"memory_capacity": 2,
|
||||||
"model_load": 24,
|
"model_load": 24,
|
||||||
"platform_infrastructure": 3,
|
"platform_infrastructure": 3,
|
||||||
@@ -5794,28 +5794,28 @@
|
|||||||
"tokenizer_compatibility": 2,
|
"tokenizer_compatibility": 2,
|
||||||
"参数/模板问题": 71
|
"参数/模板问题": 71
|
||||||
},
|
},
|
||||||
"failureCount": 445,
|
"failureCount": 446,
|
||||||
"failureRate": 0.978,
|
"failureRate": 0.9781,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 3,
|
"platformFailureCount": 3,
|
||||||
"successCount": 10,
|
"successCount": 10,
|
||||||
"successRate": 0.022,
|
"successRate": 0.0219,
|
||||||
"total": 455,
|
"total": 456,
|
||||||
"unresolvedFailureCount": 279
|
"unresolvedFailureCount": 279
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-10-08T02:39:47.594502+00:00",
|
"generatedAt": "2026-10-08T02:59:38.924222+00:00",
|
||||||
"gpuSummaries": {
|
"gpuSummaries": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"attributableFailureCount": 123,
|
"attributableFailureCount": 124,
|
||||||
"decisionFailureRate": 0.8483,
|
"decisionFailureRate": 0.8493,
|
||||||
"decisionSuccessRate": 0.1517,
|
"decisionSuccessRate": 0.1507,
|
||||||
"decisionTotal": 145,
|
"decisionTotal": 146,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 162,
|
"ambiguous_runtime": 162,
|
||||||
"context_length": 9,
|
"context_length": 9,
|
||||||
"framework_architecture_unsupported": 108,
|
"framework_architecture_unsupported": 109,
|
||||||
"memory_capacity": 2,
|
"memory_capacity": 2,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"repository_structure": 1,
|
"repository_structure": 1,
|
||||||
@@ -5824,14 +5824,14 @@
|
|||||||
"日志缺失": 3,
|
"日志缺失": 3,
|
||||||
"验证失败": 27
|
"验证失败": 27
|
||||||
},
|
},
|
||||||
"failureCount": 356,
|
"failureCount": 357,
|
||||||
"failureRate": 0.9418,
|
"failureRate": 0.942,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 22,
|
"successCount": 22,
|
||||||
"successRate": 0.0582,
|
"successRate": 0.058,
|
||||||
"total": 378,
|
"total": 379,
|
||||||
"unresolvedFailureCount": 232
|
"unresolvedFailureCount": 232
|
||||||
},
|
},
|
||||||
"Ascend_910-b4": {
|
"Ascend_910-b4": {
|
||||||
@@ -5868,7 +5868,7 @@
|
|||||||
"decisionSuccessRate": 0.1147,
|
"decisionSuccessRate": 0.1147,
|
||||||
"decisionTotal": 218,
|
"decisionTotal": 218,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 279,
|
"ambiguous_runtime": 280,
|
||||||
"backend_operator": 4,
|
"backend_operator": 4,
|
||||||
"context_length": 10,
|
"context_length": 10,
|
||||||
"framework_architecture_unsupported": 125,
|
"framework_architecture_unsupported": 125,
|
||||||
@@ -5882,15 +5882,15 @@
|
|||||||
"日志缺失": 62,
|
"日志缺失": 62,
|
||||||
"验证失败": 27
|
"验证失败": 27
|
||||||
},
|
},
|
||||||
"failureCount": 777,
|
"failureCount": 778,
|
||||||
"failureRate": 0.9688,
|
"failureRate": 0.9689,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 2,
|
"platformFailureCount": 2,
|
||||||
"successCount": 25,
|
"successCount": 25,
|
||||||
"successRate": 0.0312,
|
"successRate": 0.0311,
|
||||||
"total": 802,
|
"total": 803,
|
||||||
"unresolvedFailureCount": 582
|
"unresolvedFailureCount": 583
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x4": {
|
"Cambricon_mlu-370-x4": {
|
||||||
"attributableFailureCount": 759,
|
"attributableFailureCount": 759,
|
||||||
@@ -6638,14 +6638,14 @@
|
|||||||
"unresolvedFailureCount": 2
|
"unresolvedFailureCount": 2
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none": {
|
||||||
"attributableFailureCount": 4,
|
"attributableFailureCount": 5,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 4,
|
"decisionTotal": 5,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 4
|
"framework_architecture_unsupported": 5
|
||||||
},
|
},
|
||||||
"failureCount": 4,
|
"failureCount": 5,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"modelType": "mini_k3",
|
"modelType": "mini_k3",
|
||||||
@@ -6657,7 +6657,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 4,
|
"total": 5,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none": {
|
||||||
@@ -9333,9 +9333,9 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 6
|
"ambiguous_runtime": 7
|
||||||
},
|
},
|
||||||
"failureCount": 6,
|
"failureCount": 7,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"modelType": "mini_k3",
|
"modelType": "mini_k3",
|
||||||
@@ -9347,8 +9347,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Biren_166m",
|
"targetGpu": "Biren_166m",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 6,
|
"total": 7,
|
||||||
"unresolvedFailureCount": 6
|
"unresolvedFailureCount": 7
|
||||||
},
|
},
|
||||||
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none": {
|
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
@@ -25559,18 +25559,18 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
|
||||||
"attributableFailureCount": 7,
|
"attributableFailureCount": 8,
|
||||||
"consecutiveFailures": 7,
|
"consecutiveFailures": 8,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 7,
|
"decisionTotal": 8,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 5,
|
"ambiguous_runtime": 5,
|
||||||
"context_length": 3,
|
"context_length": 3,
|
||||||
"framework_architecture_unsupported": 4
|
"framework_architecture_unsupported": 5
|
||||||
},
|
},
|
||||||
"failureCount": 12,
|
"failureCount": 13,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -25582,7 +25582,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 12,
|
"total": 13,
|
||||||
"unresolvedFailureCount": 5
|
"unresolvedFailureCount": 5
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm|text-generation": {
|
"Ascend_910-b3|vllm|text-generation": {
|
||||||
@@ -25697,9 +25697,9 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 16
|
"ambiguous_runtime": 17
|
||||||
},
|
},
|
||||||
"failureCount": 16,
|
"failureCount": 17,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -25711,8 +25711,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Biren_166m",
|
"targetGpu": "Biren_166m",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 16,
|
"total": 17,
|
||||||
"unresolvedFailureCount": 16
|
"unresolvedFailureCount": 17
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x4|vllm-customized|text-generation": {
|
"Cambricon_mlu-370-x4|vllm-customized|text-generation": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
@@ -25950,19 +25950,19 @@
|
|||||||
"unresolvedFailureCount": 18
|
"unresolvedFailureCount": 18
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
|
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
|
||||||
"attributableFailureCount": 7,
|
"attributableFailureCount": 6,
|
||||||
"consecutiveFailures": 7,
|
"consecutiveFailures": 6,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 7,
|
"decisionTotal": 6,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 3,
|
"ambiguous_runtime": 3,
|
||||||
"framework_architecture_unsupported": 5,
|
"framework_architecture_unsupported": 4,
|
||||||
"model_load": 1,
|
"model_load": 1,
|
||||||
"tokenizer_compatibility": 1
|
"tokenizer_compatibility": 1
|
||||||
},
|
},
|
||||||
"failureCount": 10,
|
"failureCount": 9,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -25974,7 +25974,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
"targetGpu": "Iluvatar_bi-150",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 10,
|
"total": 9,
|
||||||
"unresolvedFailureCount": 3
|
"unresolvedFailureCount": 3
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|vllm|text-generation": {
|
"Iluvatar_bi-150|vllm|text-generation": {
|
||||||
@@ -26422,15 +26422,15 @@
|
|||||||
"unresolvedFailureCount": 2
|
"unresolvedFailureCount": 2
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none": {
|
||||||
"attributableFailureCount": 4,
|
"attributableFailureCount": 5,
|
||||||
"consecutiveFailures": 4,
|
"consecutiveFailures": 5,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 4,
|
"decisionTotal": 5,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 4
|
"framework_architecture_unsupported": 5
|
||||||
},
|
},
|
||||||
"failureCount": 4,
|
"failureCount": 5,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"lastTerminalAt": "2026-10-07T23:00:29.672674+00:00",
|
"lastTerminalAt": "2026-10-07T23:00:29.672674+00:00",
|
||||||
@@ -26443,7 +26443,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 4,
|
"total": 5,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
|
||||||
@@ -26703,12 +26703,12 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 6
|
"ambiguous_runtime": 7
|
||||||
},
|
},
|
||||||
"failureCount": 6,
|
"failureCount": 7,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"lastTerminalAt": "2026-10-08T02:39:47.345710+00:00",
|
"lastTerminalAt": "2026-10-08T02:59:38.470312+00:00",
|
||||||
"modelType": "mini_k3",
|
"modelType": "mini_k3",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
@@ -26718,8 +26718,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Biren_166m",
|
"targetGpu": "Biren_166m",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 6,
|
"total": 7,
|
||||||
"unresolvedFailureCount": 6
|
"unresolvedFailureCount": 7
|
||||||
},
|
},
|
||||||
"Biren_166m|vllm_fix_tokenizer|text-generation|muse_glimmer|none": {
|
"Biren_166m|vllm_fix_tokenizer|text-generation|muse_glimmer|none": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
@@ -27421,31 +27421,6 @@
|
|||||||
"total": 2,
|
"total": 2,
|
||||||
"unresolvedFailureCount": 2
|
"unresolvedFailureCount": 2
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|lfm2|none": {
|
|
||||||
"attributableFailureCount": 0,
|
|
||||||
"consecutiveFailures": 0,
|
|
||||||
"decisionFailureRate": 0.0,
|
|
||||||
"decisionSuccessRate": 0.0,
|
|
||||||
"decisionTotal": 0,
|
|
||||||
"failureBreakdown": {
|
|
||||||
"ambiguous_runtime": 1
|
|
||||||
},
|
|
||||||
"failureCount": 1,
|
|
||||||
"failureRate": 1.0,
|
|
||||||
"framework": "vllm_fix_tokenizer",
|
|
||||||
"lastTerminalAt": "2026-09-21T20:22:53.859210+00:00",
|
|
||||||
"modelType": "lfm2",
|
|
||||||
"pendingCount": 0,
|
|
||||||
"pendingRate": 0.0,
|
|
||||||
"platformFailureCount": 0,
|
|
||||||
"quantizationMethod": "none",
|
|
||||||
"successCount": 0,
|
|
||||||
"successRate": 0.0,
|
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
|
||||||
"taskType": "text-generation",
|
|
||||||
"total": 1,
|
|
||||||
"unresolvedFailureCount": 1
|
|
||||||
},
|
|
||||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
|
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
"consecutiveFailures": 0,
|
"consecutiveFailures": 0,
|
||||||
@@ -27797,31 +27772,6 @@
|
|||||||
"total": 1,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
|
|
||||||
"attributableFailureCount": 1,
|
|
||||||
"consecutiveFailures": 1,
|
|
||||||
"decisionFailureRate": 1.0,
|
|
||||||
"decisionSuccessRate": 0.0,
|
|
||||||
"decisionTotal": 1,
|
|
||||||
"failureBreakdown": {
|
|
||||||
"framework_architecture_unsupported": 1
|
|
||||||
},
|
|
||||||
"failureCount": 1,
|
|
||||||
"failureRate": 1.0,
|
|
||||||
"framework": "vllm_tokenizer_patch",
|
|
||||||
"lastTerminalAt": "2026-09-21T20:22:53.859255+00:00",
|
|
||||||
"modelType": "qwen3_5_moe",
|
|
||||||
"pendingCount": 0,
|
|
||||||
"pendingRate": 0.0,
|
|
||||||
"platformFailureCount": 0,
|
|
||||||
"quantizationMethod": "none",
|
|
||||||
"successCount": 0,
|
|
||||||
"successRate": 0.0,
|
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
|
||||||
"taskType": "text-generation",
|
|
||||||
"total": 1,
|
|
||||||
"unresolvedFailureCount": 0
|
|
||||||
},
|
|
||||||
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": {
|
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
"consecutiveFailures": 1,
|
"consecutiveFailures": 1,
|
||||||
@@ -29714,14 +29664,14 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none|30": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none|30": {
|
||||||
"attributableFailureCount": 4,
|
"attributableFailureCount": 5,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 4,
|
"decisionTotal": 5,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 4
|
"framework_architecture_unsupported": 5
|
||||||
},
|
},
|
||||||
"failureCount": 4,
|
"failureCount": 5,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"loadSizeLog2Bucket": 30,
|
"loadSizeLog2Bucket": 30,
|
||||||
@@ -29734,7 +29684,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 4,
|
"total": 5,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none|34": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none|34": {
|
||||||
@@ -34127,9 +34077,9 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 6
|
"ambiguous_runtime": 7
|
||||||
},
|
},
|
||||||
"failureCount": 6,
|
"failureCount": 7,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"loadSizeLog2Bucket": 30,
|
"loadSizeLog2Bucket": 30,
|
||||||
@@ -34142,8 +34092,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Biren_166m",
|
"targetGpu": "Biren_166m",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 6,
|
"total": 7,
|
||||||
"unresolvedFailureCount": 6
|
"unresolvedFailureCount": 7
|
||||||
},
|
},
|
||||||
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none|34": {
|
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none|34": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
@@ -58368,20 +58318,20 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"terminalRecords": 17485,
|
"terminalRecords": 17487,
|
||||||
"totalRecords": 17867,
|
"totalRecords": 17869,
|
||||||
"totals": {
|
"totals": {
|
||||||
"attributableFailureCount": 6273,
|
"attributableFailureCount": 6274,
|
||||||
"decisionFailureRate": 0.865,
|
"decisionFailureRate": 0.865,
|
||||||
"decisionSuccessRate": 0.135,
|
"decisionSuccessRate": 0.135,
|
||||||
"decisionTotal": 7252,
|
"decisionTotal": 7253,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 4583,
|
"ambiguous_runtime": 4584,
|
||||||
"architecture_compatibility": 212,
|
"architecture_compatibility": 212,
|
||||||
"attention_backend": 3,
|
"attention_backend": 3,
|
||||||
"backend_operator": 130,
|
"backend_operator": 130,
|
||||||
"context_length": 327,
|
"context_length": 327,
|
||||||
"framework_architecture_unsupported": 2291,
|
"framework_architecture_unsupported": 2292,
|
||||||
"memory_capacity": 1206,
|
"memory_capacity": 1206,
|
||||||
"model_load": 571,
|
"model_load": 571,
|
||||||
"platform_infrastructure": 955,
|
"platform_infrastructure": 955,
|
||||||
@@ -58392,15 +58342,15 @@
|
|||||||
"日志缺失": 719,
|
"日志缺失": 719,
|
||||||
"验证失败": 676
|
"验证失败": 676
|
||||||
},
|
},
|
||||||
"failureCount": 16506,
|
"failureCount": 16508,
|
||||||
"failureRate": 0.944,
|
"failureRate": 0.944,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 955,
|
"platformFailureCount": 955,
|
||||||
"successCount": 979,
|
"successCount": 979,
|
||||||
"successRate": 0.056,
|
"successRate": 0.056,
|
||||||
"total": 17485,
|
"total": 17487,
|
||||||
"unresolvedFailureCount": 9278
|
"unresolvedFailureCount": 9279
|
||||||
},
|
},
|
||||||
"warnings": [
|
"warnings": [
|
||||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
@@ -58409,14 +58359,14 @@
|
|||||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||||
"组合 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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||||
@@ -58462,6 +58412,6 @@
|
|||||||
]
|
]
|
||||||
},
|
},
|
||||||
"storageMode": "decision_state_only",
|
"storageMode": "decision_state_only",
|
||||||
"summarizedRecords": 17867,
|
"summarizedRecords": 17869,
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -111,6 +111,7 @@
|
|||||||
{"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": "vllm-customized", "lastSyncTime": "2026-09-29T17:54:53.270719+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.098010+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5012909", "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": "vllm-customized", "lastSyncTime": "2026-09-29T17:54:53.270719+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.098010+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5012909", "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": ["lfm2"], "framework": "vllm", "lastSyncTime": "2026-09-26T07:10:36.169057+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.087107+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5012911", "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": ["lfm2"], "framework": "vllm", "lastSyncTime": "2026-09-26T07:10:36.169057+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.087107+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5012911", "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_vl"], "framework": "vllm", "lastSyncTime": "2026-09-24T13:58:31.054930+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918174}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.085801+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5012910", "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_vl"], "framework": "vllm", "lastSyncTime": "2026-09-24T13:58:31.054930+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918174}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.085801+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5012910", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T02:59:38.470312+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:22:37.692361+00:00", "targetGpu": "Biren_166m", "taskId": "5012842", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T02:39:47.345710+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042625829}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:18:37.506182+00:00", "targetGpu": "Biren_166m", "taskId": "5012785", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T02:39:47.345710+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042625829}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:18:37.506182+00:00", "targetGpu": "Biren_166m", "taskId": "5012785", "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": "2026-09-22T04:40:48.058549+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T04:40:08+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4332831", "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": "2026-09-22T04:40:48.058549+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T04:40:08+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4332831", "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": ["mini_k3"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T23:17:42.455387+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T02:44:31.355275+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5011150", "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": ["mini_k3"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T23:17:42.455387+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T02:44:31.355275+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5011150", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -146,6 +147,7 @@
|
|||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164621+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.653471+00:00", "targetGpu": "Biren_166m", "taskId": "5006368", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164621+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.653471+00:00", "targetGpu": "Biren_166m", "taskId": "5006368", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T23:00:29.672674+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.459191+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006360", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T23:00:29.672674+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.459191+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006360", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T02:59:38.470354+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.449585+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006359", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T19:02:02.168317+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.447446+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006364", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T19:02:02.168317+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.447446+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006364", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T02:21:33.753335+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.388268+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006357", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T02:21:33.753335+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.388268+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006357", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T02:39:47.345789+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.384898+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006356", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T02:39:47.345789+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.384898+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006356", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -296,5 +298,3 @@
|
|||||||
{"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": "2026-09-21T20:22:53.859276+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"tokenizer_compatibility": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-20T13:30:42.155893+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.445988+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000556", "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": "2026-09-21T20:22:53.859276+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"tokenizer_compatibility": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-20T13:30:42.155893+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.445988+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000556", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T20:22:53.859237+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.443643+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000551", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T20:22:53.859237+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.443643+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000551", "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": "2026-09-21T20:22:53.859288+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"tokenizer_compatibility": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-20T13:30:42.155893+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 5254590634}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.440298+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000546", "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": "2026-09-21T20:22:53.859288+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"tokenizer_compatibility": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-20T13:30:42.155893+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 5254590634}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.440298+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000546", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T20:22:53.859210+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 4}, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T12:46:14.462925+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.438280+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000549", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T20:22:53.859255+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "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": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "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:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.436494+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000547", "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
@@ -228,15 +228,12 @@
|
|||||||
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "submitTime": "2026-09-21T23:42:59.365888+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009079", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "submitTime": "2026-09-21T23:42:59.365888+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009079", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
||||||
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-21T23:42:59.367573+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009080", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-21T23:42:59.367573+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009080", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
||||||
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "submitTime": "2026-09-21T23:42:59.369315+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009078", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "submitTime": "2026-09-21T23:42:59.369315+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009078", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
||||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-21T23:44:30.789761+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009101", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
|
||||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "submitTime": "2026-09-21T23:46:25.882874+00:00", "targetGpu": "MetaX_c-500", "taskId": "5009122", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
|
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "submitTime": "2026-09-21T23:46:25.882874+00:00", "targetGpu": "MetaX_c-500", "taskId": "5009122", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
|
||||||
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "submitTime": "2026-09-21T23:50:56.149099+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009164", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "submitTime": "2026-09-21T23:50:56.149099+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009164", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
||||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "submitTime": "2026-09-21T23:54:44.050989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009242", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
|
||||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "submitTime": "2026-09-21T23:58:44.401705+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009282", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
|
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "submitTime": "2026-09-21T23:58:44.401705+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009282", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
|
||||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-22T00:00:45.685170+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009297", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
|
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-22T00:00:45.685170+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009297", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
|
||||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-22T00:04:31.388498+00:00", "targetGpu": "Vastai_va16", "taskId": "5009346", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
|
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-22T00:04:31.388498+00:00", "targetGpu": "Vastai_va16", "taskId": "5009346", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
|
||||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "submitTime": "2026-09-22T00:12:27.759306+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009429", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "submitTime": "2026-09-22T00:12:27.759306+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009429", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
||||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "submitTime": "2026-09-22T00:12:27.760772+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009428", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
|
||||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-22T00:12:27.762342+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-22T00:12:27.762342+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
||||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-22T00:14:29.516370+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009448", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-22T00:14:29.516370+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009448", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
||||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "submitTime": "2026-09-22T00:18:55.082195+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009522", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "submitTime": "2026-09-22T00:18:55.082195+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009522", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
||||||
|
|||||||
@@ -2,24 +2,24 @@
|
|||||||
"agentVersion": "2026.09.04.4",
|
"agentVersion": "2026.09.04.4",
|
||||||
"checksums": {
|
"checksums": {
|
||||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||||
".modelhub_state/architecture_compatibility_blacklist.json": "eb1c1085c74144b722b92714f6189b12a3e7c95cca5135e6b1de86e706a21781",
|
".modelhub_state/architecture_compatibility_blacklist.json": "36e7a9467feda347f17f8ae56cbb8ffa294dea59eb992a5b00671f6e03d0446b",
|
||||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||||
".modelhub_state/market_intelligence.json": "025adc0d3134eb3971aeddac963d7af6253b0b656c60826da3dfcad66ec8cca2",
|
".modelhub_state/market_intelligence.json": "f8e9746455ffe5b24ef685a4de2ef7721bb67e8d1f90d01af6ce8e3cbf6540e5",
|
||||||
".modelhub_state/official_capabilities.json": "71277c2b956db5f2bc4f974127f84fa0762d594adda589a021e588829945646a",
|
".modelhub_state/official_capabilities.json": "94141c4ba7e1f3d6cc69f56c57c996481cdb701ca51b3bfdcba09bf9b228682a",
|
||||||
".modelhub_state/outcome_checkpoint.json": "78d461287361ec2e724bb2004f39d9d5369c80129b64ea128cff0315207fc190",
|
".modelhub_state/outcome_checkpoint.json": "07a97640b3f1492e2efadeeb16d54c316244d11258ad5bc1d3ae271edbcf818e",
|
||||||
".modelhub_state/queue_cleanup_latest.json": "568ae8813ea4bc8c494aef8be02f77b1c9756ab49dd7d307b81483e6cca30468",
|
".modelhub_state/queue_cleanup_latest.json": "568ae8813ea4bc8c494aef8be02f77b1c9756ab49dd7d307b81483e6cca30468",
|
||||||
".modelhub_state/recent_outcomes.jsonl": "179bf16a431eb302e0a9fd89863c0438fd55d6d15ae85621a4b8fa0b67be097a",
|
".modelhub_state/recent_outcomes.jsonl": "02efc3df01d483297d069ce832cd156b5aa08594eb683261888019db3e1a0fee",
|
||||||
".modelhub_state/recovery_active_tasks.jsonl": "ce3a2bc21e8246ed0922db5689493ca7ee9cfe93b7de44819283556b2e25e110",
|
".modelhub_state/recovery_active_tasks.jsonl": "a8a448e09690d07bbf4c29374150713f6bb460e3fa5ad558534d494b29dfc9e6",
|
||||||
".modelhub_state/recovery_intents.jsonl": "038a708bdcc04f4547b8acfcb5d124cc9a9dc61cd1da4f7faf3f078116a952a5",
|
".modelhub_state/recovery_intents.jsonl": "4e9ed1cb27784ea47972c946479b9d740e02dadd92459d0f26c8b62f5ce61fde",
|
||||||
".modelhub_state/routing_intelligence.json": "a312187abffa011156b64da1fed551d1816329b725ab3f38c5221900b7cc793e",
|
".modelhub_state/routing_intelligence.json": "a312187abffa011156b64da1fed551d1816329b725ab3f38c5221900b7cc793e",
|
||||||
".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
|
".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
|
||||||
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
|
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
|
||||||
"ledger/submissions.jsonl": "a5ffd96aa1416d3dab44905eb08f3835ee446c4428c463815a4e3ee62fd3188f",
|
"ledger/submissions.jsonl": "8c343b64dbb7821cc9c14d0d825bb4720aacda83a13fbd87476d14a51c5e4b5b",
|
||||||
"outcomes/submissions.jsonl": "17ab042e9fdf8b3199f13cd02f2b78e0072373ce654358b81c6bfb07eefd6bdd"
|
"outcomes/submissions.jsonl": "119be017afc4556753022369ce45b6403006b66ca82501a91d190fed62caed4f"
|
||||||
},
|
},
|
||||||
"generation": 22035,
|
"generation": 22036,
|
||||||
"phase": "cycle",
|
"phase": "cycle",
|
||||||
"schemaVersion": 1,
|
"schemaVersion": 1,
|
||||||
"updatedAt": "2026-10-08T02:58:37.634671+00:00",
|
"updatedAt": "2026-10-08T03:07:05.004365+00:00",
|
||||||
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
|
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -219,7 +219,6 @@
|
|||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563180+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563180+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057389+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.641656+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006191", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057389+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.641656+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006191", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057480+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.638009+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006194", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057480+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.638009+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006194", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600649+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.449585+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006359", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:53:42.966069+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:52:49.754157+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5006513", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:53:42.966069+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:52:49.754157+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5006513", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:53:42.966089+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042625829}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:52:49.745051+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006517", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:53:42.966089+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042625829}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:52:49.745051+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006517", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:53:42.966032+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:52:49.746330+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006515", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:53:42.966032+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:52:49.746330+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006515", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -313,7 +312,6 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:16:35.758306+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031556216, "estimatedRequiredGiB": 2.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039918195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:14:31.254072+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5012734", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:16:35.758306+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031556216, "estimatedRequiredGiB": 2.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039918195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:14:31.254072+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5012734", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T13:16:35.758272+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:16:28.475085+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5012757", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T13:16:35.758272+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:16:28.475085+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5012757", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:24:17.269104+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:20:37.680892+00:00", "targetGpu": "MetaX_c-500", "taskId": "5012814", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:24:17.269104+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:20:37.680892+00:00", "targetGpu": "MetaX_c-500", "taskId": "5012814", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T13:24:17.269090+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:22:37.692361+00:00", "targetGpu": "Biren_166m", "taskId": "5012842", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:24:17.269070+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030769952, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039132310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:22:37.690620+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5012841", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:24:17.269070+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030769952, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039132310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:22:37.690620+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5012841", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:24:17.269118+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:22:37.689299+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5012840", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:24:17.269118+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:22:37.689299+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5012840", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:34:05.154403+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:32:05.479742+00:00", "targetGpu": "MetaX_c-500", "taskId": "5012980", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:34:05.154403+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:32:05.479742+00:00", "targetGpu": "MetaX_c-500", "taskId": "5012980", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -948,7 +946,7 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T02:39:47.345805+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T18:27:23.556638+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5359383", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T02:39:47.345805+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T18:27:23.556638+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5359383", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T02:39:47.345682+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T18:27:23.585910+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5359387", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T02:39:47.345682+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T18:27:23.585910+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5359387", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:39:47.345749+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T18:33:40.054937+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5359448", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:39:47.345749+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T18:33:40.054937+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5359448", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "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": 809580753, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T18:56:45.046241+00:00", "targetGpu": "MetaX_c-500", "taskId": "5359832", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T02:59:38.470341+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "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": 809580753, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T18:56:45.046241+00:00", "targetGpu": "MetaX_c-500", "taskId": "5359832", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T19:18:39.454725+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5360137", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T19:18:39.454725+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5360137", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": 809580753, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T19:29:02.366207+00:00", "targetGpu": "Biren_166m", "taskId": "5360289", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": 809580753, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T19:29:02.366207+00:00", "targetGpu": "Biren_166m", "taskId": "5360289", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T19:29:02.583748+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360295", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T19:29:02.583748+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360295", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
|||||||
Reference in New Issue
Block a user