state: generation 8704 (intent)
This commit is contained in:
@@ -1741,7 +1741,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-17T11:26:45.797269+00:00",
|
||||
"generatedAt": "2026-09-17T11:27:49.103368+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 84,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-17T11:24:55.465166+00:00",
|
||||
"generatedAt": "2026-09-17T11:27:56.357631+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-17T11:19:12.396728+00:00",
|
||||
"lastSyncTime": "2026-09-17T11:19:10.946767+00:00",
|
||||
"generatedAt": "2026-09-17T11:27:49.059245+00:00",
|
||||
"lastSyncTime": "2026-09-17T11:27:46.524225+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2415,30 +2415,30 @@
|
||||
"unresolvedFailureCount": 58
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 61,
|
||||
"decisionFailureRate": 0.8714,
|
||||
"decisionSuccessRate": 0.1286,
|
||||
"decisionTotal": 70,
|
||||
"attributableFailureCount": 62,
|
||||
"decisionFailureRate": 0.8611,
|
||||
"decisionSuccessRate": 0.1389,
|
||||
"decisionTotal": 72,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"backend_operator": 30,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 7,
|
||||
"repository_structure": 1,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 81,
|
||||
"failureRate": 0.9,
|
||||
"failureCount": 82,
|
||||
"failureRate": 0.8913,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 9,
|
||||
"successRate": 0.1,
|
||||
"successCount": 10,
|
||||
"successRate": 0.1087,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 90,
|
||||
"total": 92,
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
@@ -2557,18 +2557,18 @@
|
||||
"unresolvedFailureCount": 35
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 55,
|
||||
"attributableFailureCount": 56,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 55,
|
||||
"decisionTotal": 56,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 7,
|
||||
"platform_infrastructure": 7,
|
||||
"tokenizer_compatibility": 45,
|
||||
"tokenizer_compatibility": 46,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 68,
|
||||
"failureCount": 69,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -2578,7 +2578,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 68,
|
||||
"total": 69,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -2837,14 +2837,14 @@
|
||||
"unresolvedFailureCount": 907
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 394,
|
||||
"decisionFailureRate": 0.9586,
|
||||
"decisionSuccessRate": 0.0414,
|
||||
"decisionTotal": 411,
|
||||
"attributableFailureCount": 395,
|
||||
"decisionFailureRate": 0.9564,
|
||||
"decisionSuccessRate": 0.0436,
|
||||
"decisionTotal": 413,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 230,
|
||||
"backend_operator": 38,
|
||||
"framework_architecture_unsupported": 295,
|
||||
"framework_architecture_unsupported": 296,
|
||||
"memory_capacity": 7,
|
||||
"model_load": 31,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -2853,14 +2853,14 @@
|
||||
"tokenizer_compatibility": 9,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 666,
|
||||
"failureRate": 0.9751,
|
||||
"failureCount": 667,
|
||||
"failureRate": 0.9737,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 17,
|
||||
"successRate": 0.0249,
|
||||
"total": 683,
|
||||
"successCount": 18,
|
||||
"successRate": 0.0263,
|
||||
"total": 685,
|
||||
"unresolvedFailureCount": 270
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2929,27 +2929,27 @@
|
||||
"unresolvedFailureCount": 13
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 58,
|
||||
"attributableFailureCount": 59,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 58,
|
||||
"decisionTotal": 59,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 64,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 9,
|
||||
"model_load": 1,
|
||||
"platform_infrastructure": 7,
|
||||
"tokenizer_compatibility": 45,
|
||||
"tokenizer_compatibility": 46,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 137,
|
||||
"failureCount": 138,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 7,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 137,
|
||||
"total": 138,
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -2972,7 +2972,7 @@
|
||||
"unresolvedFailureCount": 8
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-17T11:19:12.391620+00:00",
|
||||
"generatedAt": "2026-09-17T11:27:49.051382+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 56,
|
||||
@@ -3185,28 +3185,28 @@
|
||||
"unresolvedFailureCount": 131
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 61,
|
||||
"decisionFailureRate": 0.7722,
|
||||
"decisionSuccessRate": 0.2278,
|
||||
"decisionTotal": 79,
|
||||
"attributableFailureCount": 62,
|
||||
"decisionFailureRate": 0.7654,
|
||||
"decisionSuccessRate": 0.2346,
|
||||
"decisionTotal": 81,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"backend_operator": 30,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 7,
|
||||
"repository_structure": 1,
|
||||
"参数/模板问题": 19,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 139,
|
||||
"failureRate": 0.8854,
|
||||
"failureCount": 140,
|
||||
"failureRate": 0.8805,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 18,
|
||||
"successRate": 0.1146,
|
||||
"total": 157,
|
||||
"successCount": 19,
|
||||
"successRate": 0.1195,
|
||||
"total": 159,
|
||||
"unresolvedFailureCount": 78
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -3237,28 +3237,28 @@
|
||||
"unresolvedFailureCount": 90
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 67,
|
||||
"decisionFailureRate": 0.9853,
|
||||
"decisionSuccessRate": 0.0147,
|
||||
"decisionTotal": 68,
|
||||
"attributableFailureCount": 68,
|
||||
"decisionFailureRate": 0.9855,
|
||||
"decisionSuccessRate": 0.0145,
|
||||
"decisionTotal": 69,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 12,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 9,
|
||||
"tokenizer_compatibility": 50,
|
||||
"tokenizer_compatibility": 51,
|
||||
"参数/模板问题": 18,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 127,
|
||||
"failureCount": 128,
|
||||
"failureRate": 0.9922,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 9,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0078,
|
||||
"total": 128,
|
||||
"total": 129,
|
||||
"unresolvedFailureCount": 51
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -5869,6 +5869,27 @@
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 1,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -6097,6 +6118,29 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|spark2_5|fp8": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "fp8",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|spark2_5|none": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -6555,14 +6599,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"tokenizer_compatibility": 1
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "starcoder2",
|
||||
@@ -6574,7 +6618,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors": {
|
||||
@@ -11442,6 +11486,28 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 1,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -11728,6 +11794,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|spark2_5|fp8|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "fp8",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|spark2_5|none|31": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -12421,14 +12511,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"tokenizer_compatibility": 1
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
@@ -12441,7 +12531,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors|28": {
|
||||
@@ -12878,34 +12968,34 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2126,
|
||||
"totalRecords": 2229,
|
||||
"terminalRecords": 2129,
|
||||
"totalRecords": 2232,
|
||||
"totals": {
|
||||
"attributableFailureCount": 697,
|
||||
"decisionFailureRate": 0.8845,
|
||||
"decisionSuccessRate": 0.1155,
|
||||
"decisionTotal": 788,
|
||||
"attributableFailureCount": 699,
|
||||
"decisionFailureRate": 0.8837,
|
||||
"decisionSuccessRate": 0.1163,
|
||||
"decisionTotal": 791,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 522,
|
||||
"backend_operator": 49,
|
||||
"framework_architecture_unsupported": 465,
|
||||
"framework_architecture_unsupported": 466,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 85,
|
||||
"platform_infrastructure": 10,
|
||||
"repository_structure": 8,
|
||||
"runtime_memory": 18,
|
||||
"tokenizer_compatibility": 60,
|
||||
"tokenizer_compatibility": 61,
|
||||
"参数/模板问题": 133,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 2035,
|
||||
"failureRate": 0.9572,
|
||||
"failureCount": 2037,
|
||||
"failureRate": 0.9568,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 10,
|
||||
"successCount": 91,
|
||||
"successRate": 0.0428,
|
||||
"total": 2126,
|
||||
"successCount": 92,
|
||||
"successRate": 0.0432,
|
||||
"total": 2129,
|
||||
"unresolvedFailureCount": 1328
|
||||
},
|
||||
"warnings": [
|
||||
@@ -12916,11 +13006,11 @@
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 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。",
|
||||
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -12946,6 +13036,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2229,
|
||||
"summarizedRecords": 2232,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -858,6 +858,7 @@
|
||||
{"batchId": "53f3db5388d74fe6bf4bf0dc53b4f28e", "completedAt": "2026-09-17T10:12:21.420441+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:12:04.815444+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2235e852e97c42219d7968bcfa91a0a5", "lastModified": "2026-08-20T03:16:06+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-6bit", "reason": null, "reconciledAt": "2026-09-17T11:21:05.851838+00:00", "repoId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4913275", "taskType": "text-generation"}
|
||||
{"batchId": "695b34068dbe4d95b7f9caaa76899832", "completedAt": "2026-09-17T10:17:43.417267+00:00", "configFingerprint": "289bdbc89807736c7fc9eba7819ba7c6f178bbf5fb1f56a5683ad9b7fa830bfd", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:17:25.671043+00:00", "framework": "llamacpp", "intentId": "68be738624f14eeaabd336bfd47c4afe", "lastModified": "2026-09-15T17:45:24+00:00", "modelAddress": "https://modelscope.cn/models/RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "reason": null, "reconciledAt": "2026-09-17T11:21:05.851604+00:00", "repoId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4913350", "taskType": "text-generation"}
|
||||
{"batchId": "daeb14c26abd4648a4bb985321b158c8", "completedAt": "2026-09-17T11:10:25.999930+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-17T11:10:15.723589+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e4100d6a521b4d6d9680f77771199959", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "reconciledAt": "2026-09-17T11:21:05.852474+00:00", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4913855", "taskType": "text-generation"}
|
||||
{"batchId": "3aed3a83a2c44d80b4f4dcd609349a5a", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-17T11:29:51.205749+00:00", "framework": "vllm", "intentId": "70eeb0029c374496bc2bbc4a75d064eb", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
|
||||
{"batchId": "dc557ed173284456b65de02d89689bdd", "completedAt": "2026-09-17T07:00:50.030789+00:00", "configFingerprint": "5ec090e92fba0f8471f90bb0af176a745ebf9604ae8d9957761f2bdcf7b7b894", "configSource": "modelhub_live", "createdAt": "2026-09-17T07:00:42.703320+00:00", "framework": "llamacpp", "intentId": "1e106c48321a4cdea39458e2629ff129", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "534b216536f14acab0831df3cca7c8b7", "completedAt": "2026-09-17T06:49:28.237705+00:00", "configFingerprint": "4ecf9a1a055b517fbf32a3498eaaf4a2d63b1c33abbcc170dd75fdec6cec9dc6", "configSource": "modelhub_live", "createdAt": "2026-09-17T06:49:18.457343+00:00", "framework": "llamacpp", "intentId": "b99b4231abe54ea698f0d5b126b52b6e", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "88766ff730f64477804cc1605a44aaef", "completedAt": "2026-09-17T06:47:36.731565+00:00", "configFingerprint": "1ab708db1a2ba32a19914fb2b2a3e2674a900769ee64ff9790813f664f2605cb", "configSource": "modelhub_live", "createdAt": "2026-09-17T06:47:30.033650+00:00", "framework": "llamacpp", "intentId": "ab6c54fec18f414bae4f6b66156c2c6a", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "bcc32553df3e6036fbe9a22fe5fec50c44c6592c7d2512fcddefd0c59fa07df3",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "b7d6e78f7610c021ab3ad248980257c9f0f2c8d6e563d9d59c7f1a1af9540d2f",
|
||||
".modelhub_state/architecture_history_backfill.json": "80a6b82263a283903d54b9d294713d0bd1612ac08dba528d7072d0b1d8c78eec",
|
||||
".modelhub_state/market_intelligence.json": "6f91fdae408bdfec29c5d2b1a7b30dd6823675ecbd47913a56baa0aa64cdd14d",
|
||||
".modelhub_state/official_capabilities.json": "967989658fa78f37ccd5fd83a6af2c5daff02068d3fea36459bb891d32bc915c",
|
||||
".modelhub_state/outcome_checkpoint.json": "a22aa6c742f2f540b6b5bd1e864b2f533ed415758f142cbcb7095dafad162c5f",
|
||||
".modelhub_state/market_intelligence.json": "30c9a2f951cd214123cc22a0376638dbc1a70241c6ef46d34b6161a7615d34ac",
|
||||
".modelhub_state/official_capabilities.json": "70ad3703ac823014be4efbb605618111292e32ead4a33e90ce86b2a57c30511d",
|
||||
".modelhub_state/outcome_checkpoint.json": "f59e57ce8d8e6351ec0109a2a22bf44b99978a49daf4ebbe62b59544422d3394",
|
||||
".modelhub_state/queue_cleanup_latest.json": "4be02869ade05ead6def3f33db6297b95930841c24c0c7cab3372f7790acadd8",
|
||||
".modelhub_state/recent_outcomes.jsonl": "f2439edacbf20ab25f86c625582a3bfbc20d75a2a2f8b28eda92ed33a42057c5",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "26d4108b64c1f39556f3eebad0744595256f9fb21ffa63a51c8554b28d0cb44d",
|
||||
".modelhub_state/recovery_intents.jsonl": "b1a37286d52ef77b2afbed658a525ebc96e68ab6b358e1914118fd5cf89b9269",
|
||||
".modelhub_state/recovery_intents.jsonl": "c54c3b3d354da5eb8b95560e2a9567b66a25080f29fdb227d96bdf8c0f158f2a",
|
||||
".modelhub_state/routing_intelligence.json": "2aef60eeaeb2e5f23d4fb0e426f3833e052a224a17699023c2281974d9b658a8",
|
||||
".modelhub_state/submission_exclusions.jsonl": "a0cb4e822e4b6d26c26c3bf22698cacbab31f2df5f3402ecf04fdfb3a3577ef7",
|
||||
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
|
||||
"ledger/submissions.jsonl": "beb73b6fce365412ad3f6e6dc5e969bbc63493a731136420108b953b9f354615",
|
||||
"outcomes/submissions.jsonl": "4628f4e4f84ea885bbe7a18e9af71239d049c83fda9c77d5c727739647d47baa"
|
||||
"outcomes/submissions.jsonl": "3eca274ab0eda5f0b22ee23d3dea80dc3428d4dce3ac8aeb29a5cebdd11ed74d"
|
||||
},
|
||||
"generation": 8703,
|
||||
"phase": "cycle",
|
||||
"generation": 8704,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-17T11:26:45.890251+00:00",
|
||||
"updatedAt": "2026-09-17T11:29:51.290087+00:00",
|
||||
"writerId": "eccb3e0018f640d19e578c271a207b5c"
|
||||
}
|
||||
|
||||
@@ -40,7 +40,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503337+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081293776, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504091, "modelscopeLicense": "llama3", "modelscopeParams": 8030261312, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.396277+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657902", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503433+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39365175520, "estimatedRequiredGiB": 44.029, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 39396646235, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 39396646235}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.385964+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657900", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503369+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.392602+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657901", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503449+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.390810+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657904", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503472+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19509024201, "estimatedRequiredGiB": 21.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19530936726, "modelscopeLicense": null, "modelscopeParams": 5419330688, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19530936726}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.419799+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657897", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503494+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.417747+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657896", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503479+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 451270785, "estimatedRequiredGiB": 0.534, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 478002291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 119465472, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 478002291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.487200+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657899", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -90,7 +89,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:52:41.332095+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "5f7f0613db77a9df3302ec352997953a9eba59a0aa6b38bb4fbb9466fb50fd7b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:50:14.422978+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4695252", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T21:18:24.608680+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ea2321217291fd0be7b6ccbad7b7c81bf62a9ac5c888c7ee1e080e1ea85862ae", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T13:14:08.050211+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4695580", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-07T23:16:42.601405+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T15:08:53.697776+00:00", "targetGpu": "Vastai_va16", "taskId": "4698268", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T23:43:05.101242+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T15:35:43.483187+00:00", "targetGpu": "MetaX_c-500", "taskId": "4698954", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T00:12:24.015192+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T16:06:40.552870+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4699585", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T01:37:35.725250+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0e96112008e09ac1841408e47a35f72b68023fca4efc76695e6eb96ba540ba1c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T17:27:44.564043+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701029", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T04:10:28.996444+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T19:56:19.088834+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4703149", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -324,7 +322,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218190+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.857970+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749149", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218240+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.862038+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749144", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218183+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.847614+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749143", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454674+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043809570, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043809570}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.091512+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749457", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454453+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.051663+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749456", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454574+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.093785+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749466", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454659+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.090459+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749455", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user