state: generation 19463 (cycle)
This commit is contained in:
@@ -3322,7 +3322,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-02T02:11:15.987230+00:00",
|
||||
"generatedAt": "2026-10-02T02:23:34.107200+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 167,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-02T02:22:31.559996+00:00",
|
||||
"generatedAt": "2026-10-02T02:25:23.162210+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-02T02:22:31.559996+00:00",
|
||||
"catalogUpdatedAt": "2026-10-02T02:25:23.162210+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-02T02:22:31.559996+00:00",
|
||||
"generatedAt": "2026-10-02T02:25:23.162210+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6577,6 +6577,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-02T02:22:31.559996+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-02T02:25:23.162210+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-02T02:11:15.894943+00:00",
|
||||
"lastSyncTime": "2026-10-02T02:11:15.645478+00:00",
|
||||
"generatedAt": "2026-10-02T02:23:34.025020+00:00",
|
||||
"lastSyncTime": "2026-10-02T02:23:33.763206+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4989,10 +4989,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 152,
|
||||
"ambiguous_runtime": 153,
|
||||
"参数/模板问题": 3
|
||||
},
|
||||
"failureCount": 155,
|
||||
"failureCount": 156,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -5002,8 +5002,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 155,
|
||||
"unresolvedFailureCount": 155
|
||||
"total": 156,
|
||||
"unresolvedFailureCount": 156
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 61,
|
||||
@@ -5467,18 +5467,18 @@
|
||||
"unresolvedFailureCount": 296
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 119,
|
||||
"attributableFailureCount": 120,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 119,
|
||||
"decisionTotal": 120,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"framework_architecture_unsupported": 19,
|
||||
"platform_infrastructure": 22,
|
||||
"tokenizer_compatibility": 92,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 147,
|
||||
"failureCount": 148,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -5488,20 +5488,20 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 147,
|
||||
"total": 148,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 617,
|
||||
"attributableFailureCount": 618,
|
||||
"decisionFailureRate": 0.9968,
|
||||
"decisionSuccessRate": 0.0032,
|
||||
"decisionTotal": 619,
|
||||
"decisionTotal": 620,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 109,
|
||||
"architecture_compatibility": 43,
|
||||
"backend_operator": 28,
|
||||
"context_length": 34,
|
||||
"framework_architecture_unsupported": 143,
|
||||
"framework_architecture_unsupported": 144,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 211,
|
||||
"repository_structure": 75,
|
||||
@@ -5509,7 +5509,7 @@
|
||||
"tokenizer_compatibility": 180,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 946,
|
||||
"failureCount": 947,
|
||||
"failureRate": 0.9979,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -5519,7 +5519,7 @@
|
||||
"successRate": 0.0021,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 948,
|
||||
"total": 949,
|
||||
"unresolvedFailureCount": 118
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|unknown": {
|
||||
@@ -6021,17 +6021,17 @@
|
||||
"unresolvedFailureCount": 6473
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3638,
|
||||
"attributableFailureCount": 3639,
|
||||
"decisionFailureRate": 0.9727,
|
||||
"decisionSuccessRate": 0.0273,
|
||||
"decisionTotal": 3740,
|
||||
"decisionTotal": 3741,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1594,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 93,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1367,
|
||||
"framework_architecture_unsupported": 1368,
|
||||
"memory_capacity": 725,
|
||||
"model_load": 221,
|
||||
"platform_infrastructure": 875,
|
||||
@@ -6040,14 +6040,14 @@
|
||||
"tokenizer_compatibility": 420,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6157,
|
||||
"failureCount": 6158,
|
||||
"failureRate": 0.9837,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 875,
|
||||
"successCount": 102,
|
||||
"successRate": 0.0163,
|
||||
"total": 6259,
|
||||
"total": 6260,
|
||||
"unresolvedFailureCount": 1644
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -6145,29 +6145,29 @@
|
||||
"unresolvedFailureCount": 31
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 159,
|
||||
"decisionFailureRate": 0.9695,
|
||||
"decisionSuccessRate": 0.0305,
|
||||
"decisionTotal": 164,
|
||||
"attributableFailureCount": 160,
|
||||
"decisionFailureRate": 0.9697,
|
||||
"decisionSuccessRate": 0.0303,
|
||||
"decisionTotal": 165,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 343,
|
||||
"ambiguous_runtime": 344,
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 39,
|
||||
"framework_architecture_unsupported": 40,
|
||||
"memory_capacity": 10,
|
||||
"model_load": 9,
|
||||
"platform_infrastructure": 22,
|
||||
"tokenizer_compatibility": 92,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 537,
|
||||
"failureCount": 539,
|
||||
"failureRate": 0.9908,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 22,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0092,
|
||||
"total": 542,
|
||||
"unresolvedFailureCount": 356
|
||||
"total": 544,
|
||||
"unresolvedFailureCount": 357
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 143,
|
||||
@@ -6198,7 +6198,7 @@
|
||||
"unresolvedFailureCount": 227
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-02T02:11:15.881373+00:00",
|
||||
"generatedAt": "2026-10-02T02:23:34.011283+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 114,
|
||||
@@ -6430,7 +6430,7 @@
|
||||
"decisionSuccessRate": 0.066,
|
||||
"decisionTotal": 106,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 240,
|
||||
"ambiguous_runtime": 241,
|
||||
"backend_operator": 23,
|
||||
"framework_architecture_unsupported": 37,
|
||||
"memory_capacity": 3,
|
||||
@@ -6443,15 +6443,15 @@
|
||||
"日志缺失": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 410,
|
||||
"failureRate": 0.9832,
|
||||
"failureCount": 411,
|
||||
"failureRate": 0.9833,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 7,
|
||||
"successRate": 0.0168,
|
||||
"total": 417,
|
||||
"unresolvedFailureCount": 310
|
||||
"successRate": 0.0167,
|
||||
"total": 418,
|
||||
"unresolvedFailureCount": 311
|
||||
},
|
||||
"Kunlunxin_r-200-8f": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -6534,16 +6534,16 @@
|
||||
"unresolvedFailureCount": 301
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 755,
|
||||
"decisionFailureRate": 0.8882,
|
||||
"decisionSuccessRate": 0.1118,
|
||||
"decisionTotal": 850,
|
||||
"attributableFailureCount": 757,
|
||||
"decisionFailureRate": 0.8885,
|
||||
"decisionSuccessRate": 0.1115,
|
||||
"decisionTotal": 852,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 162,
|
||||
"architecture_compatibility": 44,
|
||||
"backend_operator": 37,
|
||||
"context_length": 39,
|
||||
"framework_architecture_unsupported": 163,
|
||||
"framework_architecture_unsupported": 165,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 233,
|
||||
"repository_structure": 83,
|
||||
@@ -6552,14 +6552,14 @@
|
||||
"参数/模板问题": 228,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1410,
|
||||
"failureRate": 0.9369,
|
||||
"failureCount": 1412,
|
||||
"failureRate": 0.937,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 233,
|
||||
"successCount": 95,
|
||||
"successRate": 0.0631,
|
||||
"total": 1505,
|
||||
"successRate": 0.063,
|
||||
"total": 1507,
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -18307,6 +18307,29 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "qwen3_5_moe_text",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -21642,6 +21665,29 @@
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|param2moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "param2moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -21875,14 +21921,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 2
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "qwen3_5",
|
||||
@@ -21894,7 +21941,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|gptq": {
|
||||
@@ -45789,6 +45836,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none|35": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 35,
|
||||
"modelType": "qwen3_5_moe_text",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -51113,6 +51184,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|param2moe|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "param2moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -51499,14 +51594,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -51519,7 +51615,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|34": {
|
||||
@@ -54622,20 +54718,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17218,
|
||||
"totalRecords": 17439,
|
||||
"terminalRecords": 17221,
|
||||
"totalRecords": 17442,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6172,
|
||||
"attributableFailureCount": 6174,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7147,
|
||||
"decisionTotal": 7149,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4503,
|
||||
"ambiguous_runtime": 4504,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
"context_length": 327,
|
||||
"framework_architecture_unsupported": 2214,
|
||||
"framework_architecture_unsupported": 2216,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 553,
|
||||
"platform_infrastructure": 945,
|
||||
@@ -54646,30 +54742,30 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16243,
|
||||
"failureCount": 16246,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 945,
|
||||
"successCount": 975,
|
||||
"successRate": 0.0566,
|
||||
"total": 17218,
|
||||
"unresolvedFailureCount": 9126
|
||||
"total": 17221,
|
||||
"unresolvedFailureCount": 9127
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 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 Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU 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 Vastai_va16 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 Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU 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。",
|
||||
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Kunlunxin_p-800|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。",
|
||||
@@ -54714,6 +54810,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17439,
|
||||
"summarizedRecords": 17442,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.22.1",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "75430e53a05e357ce89f52b012689184ef24da349f9e68f99c716069afa4110b",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "da16aeea7dcc4801724c54453f90da0499e4d4d4592f381b354441a98a0dcad3",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "9179a264b1d5f92a1e0e76ad6c42ead29f636a532b28efce449a6dc148613cdc",
|
||||
".modelhub_state/official_capabilities.json": "984a8208550c209ec270caa0412bd42417a1a4a7e8256d25e730cd4d1702f394",
|
||||
".modelhub_state/outcome_checkpoint.json": "b26c1d74cefd1e65599be7ac0aaef874e5fdbeeeb158d607a2d407ac6ef7c25f",
|
||||
".modelhub_state/market_intelligence.json": "c017adf14b8bc31648478abb34d7e51ceb5efd43afd0226823562aa46677c8eb",
|
||||
".modelhub_state/official_capabilities.json": "6d5ad9c08085d8cdc8efd579a531be75dc7bc53cc01b78b3e658ed7c414344b8",
|
||||
".modelhub_state/outcome_checkpoint.json": "361184126abe9ec0ee15cbc11b32fbe9ba6e30fe4902eccda30fc27a16e35994",
|
||||
".modelhub_state/queue_cleanup_latest.json": "ec9c714dde635223eb7f5550481af3a4ff97e6326f9bfe9026419293fd2022b3",
|
||||
".modelhub_state/recent_outcomes.jsonl": "510479509b98259dabba51dcb428b1fc70ad3660aa3b639633b84944eb56236a",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "4e3e23ddf1652cfef8f2c59208ed56329745a127921b2d3ac96058e81e3ae680",
|
||||
".modelhub_state/recovery_intents.jsonl": "bf8000684d5427307254e36b5bf3eef5498a7d9b95993874e6ea58d8b861e8e1",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "299888efca9a3f4bdef553dd7edc23cffa988a49f8b425864a0252852914e45f",
|
||||
".modelhub_state/recovery_intents.jsonl": "b5b5aa36ae8af18ad3a2c054051c7ceb08f820c05ef5d68b440f1aa42365a345",
|
||||
".modelhub_state/routing_intelligence.json": "4cab060aa87c62b99c0f5f10e414a79361ce90d66fd3ab7f01b38511e88cd04c",
|
||||
".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
|
||||
".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
|
||||
"ledger/submissions.jsonl": "f07097a81bca05908717470dad5cd368a4b15377940b835023ea1db16579784d",
|
||||
"outcomes/submissions.jsonl": "c9bfabf7c24d53d7870950af01177294ecfbd06f76069da352d69c0a3eafd85c"
|
||||
"outcomes/submissions.jsonl": "da22695ff78e75b502e41706fba0acbbc87fb2540d40f55383c09eae0b7c984d"
|
||||
},
|
||||
"generation": 19462,
|
||||
"generation": 19463,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-02T02:22:32.424868+00:00",
|
||||
"updatedAt": "2026-10-02T02:26:28.590998+00:00",
|
||||
"writerId": "a812d0e025c3474eb16b828a4d987334"
|
||||
}
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T11:58:24.844524+00:00", "modelId": "inclusionAI/Ling-3.0-tiny-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "efcec92f0f61cfcfef2bff75fcc3b460aac2425880772995e6373e3f88061c16", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8408187808, "estimatedRequiredGiB": 46.011, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 41170267110, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 41170267110}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.312611+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610785", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.904005+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.672536+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611191", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T12:43:05.302313+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 4.889, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4375025003, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4375025003}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692571+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "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": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:16.665549+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632117", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:32:15.596901+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:29:42.987166+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632974", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -14,7 +13,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503418+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.393987+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657908", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503463+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020563851}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.392742+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657912", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T08:54:40.814445+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898265436, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2948065280, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898265436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:51:47.515580+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4658219", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601493+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:23:39.684428+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659269", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601408+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703969742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703969742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:23:39.690219+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659268", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T11:46:43.318197+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26540803088, "estimatedRequiredGiB": 29.664, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 26542898184, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13270298624, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26542898184}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T03:45:55.331628+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660328", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T20:39:29.797774+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T12:37:22.515030+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4667091", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -143,7 +141,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:42:14.260331+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7df61fc66119e362f4b324c308b44e18bd70c6e8415d3cf79ad822bc9e6377c3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "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": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:36:01.072109+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4912861", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T18:05:14.493617+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cde1dd013433575dd6e624ec4e742d4992d0b53d429ab95bc4dbe8884fc49e49", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "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": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:57:55.404929+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4913157", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T18:16:51.858895+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434089468, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 62434089468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:12:07.431503+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4913277", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T18:16:51.858863+00:00", "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429250296, "estimatedRequiredGiB": 58.623, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52454809833, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:ornith", "custom_tag:reap", "custom_tag:ream", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52454809833}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:12:07.491666+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4913273", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T18:28:37.152661+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "289bdbc89807736c7fc9eba7819ba7c6f178bbf5fb1f56a5683ad9b7fa830bfd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:17:26.606251+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4913350", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-17T19:13:02.956946+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062180814, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T11:10:16.602977+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4913855", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T19:35:26.664856+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062180814, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T11:29:52.144122+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4914037", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user