state: generation 19123 (cycle)
This commit is contained in:
@@ -3341,7 +3341,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-01T07:18:57.673905+00:00",
|
||||
"generatedAt": "2026-10-01T07:30:39.528232+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 168,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-01T07:29:30.856453+00:00",
|
||||
"generatedAt": "2026-10-01T07:32:36.875626+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-01T07:29:30.856453+00:00",
|
||||
"catalogUpdatedAt": "2026-10-01T07:32:36.875626+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-01T07:29:35.861306+00:00",
|
||||
"generatedAt": "2026-10-01T07:33:24.073623+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -282,7 +282,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:32:24.153061+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:23.773502+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/AlexWortega/llm-cipher-reasoning-loras|2026-09-03T05:28:45+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -837,7 +837,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:45.567355+00:00"
|
||||
"updatedAt": "2026-10-01T07:32:58.949559+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/LiquidAI/LFM2.5-230M-GGUF|2026-09-23T12:19:36+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -903,7 +903,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:32:42.754411+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:24.073623+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-DFlash2-EXL3-5.0bpw|2026-08-24T18:41:19+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -1056,7 +1056,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:56.360501+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:04.248811+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-DSpark-GGUF|2026-09-09T18:25:18+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -1145,7 +1145,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:58.318464+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:06.447777+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-DSpark|2026-09-07T18:16:04+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -1440,7 +1440,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:50.682016+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:02.653375+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/SKYEVAL/Three_Kingdoms_LLM_Arena|2026-09-14T09:18:14+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -1624,7 +1624,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:57.275967+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:05.350756+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B-GGUF|2026-09-09T03:26:23+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -1971,7 +1971,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:32:24.257986+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:23.867324+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF|2026-09-03T03:52:57+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -2060,7 +2060,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:32:24.262214+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:23.868210+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-MTP-ROCmFP4-FAST-GGUF|2026-09-03T03:44:11+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -2401,7 +2401,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:45.364819+00:00"
|
||||
"updatedAt": "2026-10-01T07:32:56.763234+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/chenyumo/moziAI-27B-MTP|2026-09-25T03:59:57+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -2490,7 +2490,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:45.366582+00:00"
|
||||
"updatedAt": "2026-10-01T07:32:56.680098+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/chenyumo/moziAI-35B-A3B-MOE-MTP|2026-09-25T03:56:17+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -2534,7 +2534,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:54.445933+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:03.646690+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/cix/DeepSeek-R1-Distill-Qwen-7B-GGUF|2026-09-11T07:54:02+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -2786,7 +2786,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:45.253511+00:00"
|
||||
"updatedAt": "2026-10-01T07:32:55.447264+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/elejoai/offline-voice-model-packs|2026-09-28T09:46:06+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -3238,7 +3238,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:50.850974+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:02.948123+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/icychick/Qwen3.5-text-0.8B-GGUF|2026-09-14T05:41:13+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -3651,7 +3651,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:42.548301+00:00"
|
||||
"updatedAt": "2026-10-01T07:32:54.854578+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/iyangqing/st-image|2026-09-29T10:26:37+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -3785,7 +3785,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:45.469531+00:00"
|
||||
"updatedAt": "2026-10-01T07:32:58.251301+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/juspay/Kwaipilot-KAT-Dev-CPT-LoRA-Adapter-HyperSwitch|2026-09-24T03:43:48+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -3874,7 +3874,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:45.470792+00:00"
|
||||
"updatedAt": "2026-10-01T07:32:58.248218+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/juspay/Qwen2.5-Coder-32B-Instruct-CPT-LoRA-Adapter-HyperSwitch|2026-09-24T03:41:11+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -3963,7 +3963,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:56.356576+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:04.256218+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_global-batch-size_32_Qwen3-32B|2026-09-09T17:06:17+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -4995,7 +4995,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:31:45.291137+00:00"
|
||||
"updatedAt": "2026-10-01T07:32:55.848819+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/prithivMLmods/JSBAI-Coder-4B-GGUF|2026-09-26T14:36:02+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -5299,7 +5299,7 @@
|
||||
"text-to-image-generation",
|
||||
"visual-multi-modal"
|
||||
],
|
||||
"updatedAt": "2026-09-30T07:32:23.350898+00:00"
|
||||
"updatedAt": "2026-10-01T07:33:23.781222+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/svvkii/qwen2.5-7b-5persona-lora|2026-09-03T09:05:03+00:00|Kunlunxin_p-800": {
|
||||
"taskTypes": [
|
||||
@@ -6704,6 +6704,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-01T07:29:30.856453+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-01T07:32:36.875626+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-01T07:18:57.593981+00:00",
|
||||
"lastSyncTime": "2026-10-01T07:18:57.350445+00:00",
|
||||
"generatedAt": "2026-10-01T07:30:39.438892+00:00",
|
||||
"lastSyncTime": "2026-10-01T07:30:37.858876+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3469,25 +3469,25 @@
|
||||
"decisionSuccessRate": 0.0889,
|
||||
"decisionTotal": 45,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 79,
|
||||
"ambiguous_runtime": 80,
|
||||
"context_length": 8,
|
||||
"framework_architecture_unsupported": 32,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 129,
|
||||
"failureRate": 0.9699,
|
||||
"failureCount": 130,
|
||||
"failureRate": 0.9701,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 4,
|
||||
"successRate": 0.0301,
|
||||
"successRate": 0.0299,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 133,
|
||||
"unresolvedFailureCount": 87
|
||||
"total": 134,
|
||||
"unresolvedFailureCount": 88
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 70,
|
||||
@@ -5225,7 +5225,7 @@
|
||||
"decisionSuccessRate": 0.0398,
|
||||
"decisionTotal": 654,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 130,
|
||||
"ambiguous_runtime": 131,
|
||||
"architecture_compatibility": 20,
|
||||
"backend_operator": 43,
|
||||
"context_length": 46,
|
||||
@@ -5238,18 +5238,18 @@
|
||||
"tokenizer_compatibility": 79,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 770,
|
||||
"failureRate": 0.9673,
|
||||
"failureCount": 771,
|
||||
"failureRate": 0.9674,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 26,
|
||||
"successRate": 0.0327,
|
||||
"successRate": 0.0326,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 796,
|
||||
"unresolvedFailureCount": 139
|
||||
"total": 797,
|
||||
"unresolvedFailureCount": 140
|
||||
},
|
||||
"MetaX_c-500|vllm|unknown": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -5393,7 +5393,7 @@
|
||||
"decisionSuccessRate": 0.24,
|
||||
"decisionTotal": 100,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 75,
|
||||
"ambiguous_runtime": 76,
|
||||
"attention_backend": 2,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 54,
|
||||
@@ -5405,18 +5405,18 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 12
|
||||
},
|
||||
"failureCount": 164,
|
||||
"failureRate": 0.8723,
|
||||
"failureCount": 165,
|
||||
"failureRate": 0.873,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 24,
|
||||
"successRate": 0.1277,
|
||||
"successRate": 0.127,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 188,
|
||||
"unresolvedFailureCount": 87
|
||||
"total": 189,
|
||||
"unresolvedFailureCount": 88
|
||||
},
|
||||
"Mthreads_s4000|vllm|visual-multi-modal": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -6045,7 +6045,7 @@
|
||||
"decisionSuccessRate": 0.0273,
|
||||
"decisionTotal": 3739,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1589,
|
||||
"ambiguous_runtime": 1591,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 93,
|
||||
@@ -6059,15 +6059,15 @@
|
||||
"tokenizer_compatibility": 420,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6150,
|
||||
"failureCount": 6152,
|
||||
"failureRate": 0.9837,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 874,
|
||||
"successCount": 102,
|
||||
"successRate": 0.0163,
|
||||
"total": 6252,
|
||||
"unresolvedFailureCount": 1639
|
||||
"total": 6254,
|
||||
"unresolvedFailureCount": 1641
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 15,
|
||||
@@ -6194,7 +6194,7 @@
|
||||
"decisionSuccessRate": 0.0667,
|
||||
"decisionTotal": 150,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 191,
|
||||
"ambiguous_runtime": 192,
|
||||
"backend_operator": 15,
|
||||
"context_length": 8,
|
||||
"framework_architecture_unsupported": 84,
|
||||
@@ -6206,18 +6206,18 @@
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 29
|
||||
},
|
||||
"failureCount": 363,
|
||||
"failureRate": 0.9732,
|
||||
"failureCount": 364,
|
||||
"failureRate": 0.9733,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0268,
|
||||
"total": 373,
|
||||
"unresolvedFailureCount": 220
|
||||
"successRate": 0.0267,
|
||||
"total": 374,
|
||||
"unresolvedFailureCount": 221
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-01T07:18:57.580625+00:00",
|
||||
"generatedAt": "2026-10-01T07:30:39.425215+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 112,
|
||||
@@ -6225,7 +6225,7 @@
|
||||
"decisionSuccessRate": 0.1642,
|
||||
"decisionTotal": 134,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 147,
|
||||
"ambiguous_runtime": 148,
|
||||
"context_length": 8,
|
||||
"framework_architecture_unsupported": 98,
|
||||
"memory_capacity": 2,
|
||||
@@ -6236,15 +6236,15 @@
|
||||
"日志缺失": 3,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 329,
|
||||
"failureRate": 0.9373,
|
||||
"failureCount": 330,
|
||||
"failureRate": 0.9375,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 22,
|
||||
"successRate": 0.0627,
|
||||
"total": 351,
|
||||
"unresolvedFailureCount": 216
|
||||
"successRate": 0.0625,
|
||||
"total": 352,
|
||||
"unresolvedFailureCount": 217
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 326,
|
||||
@@ -6497,7 +6497,7 @@
|
||||
"decisionSuccessRate": 0.1815,
|
||||
"decisionTotal": 810,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 302,
|
||||
"ambiguous_runtime": 303,
|
||||
"architecture_compatibility": 21,
|
||||
"backend_operator": 43,
|
||||
"context_length": 59,
|
||||
@@ -6512,15 +6512,15 @@
|
||||
"日志缺失": 15,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1431,
|
||||
"failureRate": 0.9068,
|
||||
"failureCount": 1432,
|
||||
"failureRate": 0.9069,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 147,
|
||||
"successRate": 0.0932,
|
||||
"total": 1578,
|
||||
"unresolvedFailureCount": 763
|
||||
"successRate": 0.0931,
|
||||
"total": 1579,
|
||||
"unresolvedFailureCount": 764
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"attributableFailureCount": 80,
|
||||
@@ -6528,7 +6528,7 @@
|
||||
"decisionSuccessRate": 0.36,
|
||||
"decisionTotal": 125,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 121,
|
||||
"ambiguous_runtime": 122,
|
||||
"attention_backend": 2,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 55,
|
||||
@@ -6542,15 +6542,15 @@
|
||||
"日志缺失": 96,
|
||||
"验证失败": 26
|
||||
},
|
||||
"failureCount": 380,
|
||||
"failureRate": 0.8941,
|
||||
"failureCount": 381,
|
||||
"failureRate": 0.8944,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 45,
|
||||
"successRate": 0.1059,
|
||||
"total": 425,
|
||||
"unresolvedFailureCount": 299
|
||||
"successRate": 0.1056,
|
||||
"total": 426,
|
||||
"unresolvedFailureCount": 300
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 755,
|
||||
@@ -6916,10 +6916,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15,
|
||||
"ambiguous_runtime": 16,
|
||||
"context_length": 6
|
||||
},
|
||||
"failureCount": 21,
|
||||
"failureCount": 22,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "llama",
|
||||
@@ -6931,8 +6931,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 21,
|
||||
"unresolvedFailureCount": 15
|
||||
"total": 22,
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -20723,6 +20723,29 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|spark2_5|torchao": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "torchao",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 7,
|
||||
"decisionFailureRate": 0.875,
|
||||
@@ -21361,6 +21384,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|spark2_5|torchao": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "torchao",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -23802,9 +23848,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"参数/模板问题": 12
|
||||
"参数/模板问题": 11
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureCount": 11,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -23816,8 +23862,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 12
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 11
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
@@ -23827,11 +23873,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"ambiguous_runtime": 12,
|
||||
"context_length": 2,
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -23843,8 +23889,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 11
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 12
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -24684,10 +24730,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"ambiguous_runtime": 5,
|
||||
"context_length": 2
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastTerminalAt": "2026-09-30T15:29:22.559035+00:00",
|
||||
@@ -24700,8 +24746,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -28385,9 +28431,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9
|
||||
"ambiguous_runtime": 10
|
||||
},
|
||||
"failureCount": 9,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -28400,8 +28446,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 9
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -49425,6 +49471,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|spark2_5|torchao|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "torchao",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|31": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -50417,6 +50487,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|spark2_5|torchao|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "torchao",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|starcoder2|compressed-tensors|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -54166,15 +54260,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17186,
|
||||
"totalRecords": 17407,
|
||||
"terminalRecords": 17189,
|
||||
"totalRecords": 17410,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6163,
|
||||
"decisionFailureRate": 0.8634,
|
||||
"decisionSuccessRate": 0.1366,
|
||||
"decisionTotal": 7138,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4481,
|
||||
"ambiguous_runtime": 4484,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -54190,30 +54284,30 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16211,
|
||||
"failureCount": 16214,
|
||||
"failureRate": 0.9433,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 944,
|
||||
"successCount": 975,
|
||||
"successRate": 0.0567,
|
||||
"total": 17186,
|
||||
"unresolvedFailureCount": 9104
|
||||
"total": 17189,
|
||||
"unresolvedFailureCount": 9107
|
||||
},
|
||||
"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 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。",
|
||||
"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。",
|
||||
@@ -54258,6 +54352,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17407,
|
||||
"summarizedRecords": 17410,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -106,6 +106,7 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-21T16:50:30.559368+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610379", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-21T16:50:30.559274+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4332638", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Plamo3ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-23T21:42:41.557185+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:28:23.653856+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5003786", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T07:30:37.858876+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9517467172, "estimatedRequiredGiB": 10.647, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9526650722, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9526650722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:28:23.621387+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5003752", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-23T19:23:54.359353+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T16:21:12.358143+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5003636", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-23T03:30:34.863737+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "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": 17788612744}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:16:38.115066+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5003582", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-27T06:27:28.565882+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:16:37.962127+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003581", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569144+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4923523", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569235+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T04:11:57.967213+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-base", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T04:11:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457983", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:11:57.967175+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:09:34+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969052", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
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": "6245fef6664b15410a1e1aeb430a934abb18e3fb22f46acd337f1bf41cdbf53b",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "c1176bcf9c3e0b695bfcb99a7e92aa1a2a176ae9df0fe7bccb5eb9d75922ef55",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "22bb085fa55e2fca3b2dbd216b927c80b2e00f404ea5872addbe30ef425ff228",
|
||||
".modelhub_state/official_capabilities.json": "385441327289cb012e3c326806065b8de4f45ffa7d4cd5ece8899c72f3207332",
|
||||
".modelhub_state/outcome_checkpoint.json": "928ad0a6a6ab5ab2b17264ba92e146050bb5f20e78508c669bec2d21c8533f29",
|
||||
".modelhub_state/market_intelligence.json": "fa42aecd8e7fa66bef7dd77c93a130567b66678de90d2cb24cfb8216f234c0c6",
|
||||
".modelhub_state/official_capabilities.json": "52d9c62150e4b7092f615f3e0560e0d8a16298c6632310d29976b1f2798be551",
|
||||
".modelhub_state/outcome_checkpoint.json": "5f27ad6fdea25f432428e31a3dff78f599c0f19f4e869d3c05dc016f4c0e58d3",
|
||||
".modelhub_state/queue_cleanup_latest.json": "05a1b3ebbbe8095e2f42ed6517a8c002726299deda90003a645472de6c83714e",
|
||||
".modelhub_state/recent_outcomes.jsonl": "73f23566b5b4b8c0176d6e15dac2ca91200b082f28f05f39862b89485e9e092d",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "5978f04fdab6f4f59509c25d7b709fc0f63892edb9ceede291a53efc495578f9",
|
||||
".modelhub_state/recovery_intents.jsonl": "188bd1d2ca22d82d16358612e66f6d83ea2b70efc9a810c577472f5f5d9f9f81",
|
||||
".modelhub_state/recent_outcomes.jsonl": "0e7f888628ed0e3ec89ce2fa68e82953be3cc4ce423be1e83a31648c27034052",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "fea58a8b5bcb1607f9e5dd0e677c3bdacf11b82423e1cdf885633831be1872a6",
|
||||
".modelhub_state/recovery_intents.jsonl": "b1991542ecc16be94a8304645e5c13f8ae2ff065ad343521c01b63cbbeaba815",
|
||||
".modelhub_state/routing_intelligence.json": "1b57ceab4c8d353e140012683aca39b2423393bd05a2d902e1c194a12397923d",
|
||||
".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
|
||||
".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
|
||||
"ledger/submissions.jsonl": "4a8aed84a5d7687009382bed32324177ed1f15bba73de9486bebd7f2ce317229",
|
||||
"outcomes/submissions.jsonl": "c83904cacd322ffa0d9275c4205e46f680e1981410b2fab8d5c731302f1ac368"
|
||||
"outcomes/submissions.jsonl": "7d00daebb77a9a053596571ae6f32fa82b6aac7abefbc3ac9bad69599d8db313"
|
||||
},
|
||||
"generation": 19122,
|
||||
"generation": 19123,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-01T07:29:36.227657+00:00",
|
||||
"updatedAt": "2026-10-01T07:33:32.222316+00:00",
|
||||
"writerId": "a812d0e025c3474eb16b828a4d987334"
|
||||
}
|
||||
|
||||
@@ -126,10 +126,8 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995814+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529500, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.355295+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867726", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995786+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083974016, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.351500+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867728", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995834+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529926, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.357590+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867730", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T22:59:41.110934+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "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": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T14:55:01.762871+00:00", "targetGpu": "MetaX_c-500", "taskId": "4874870", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T23:45:09.312003+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "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": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T15:43:19.147650+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4875870", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-16T05:28:53.501885+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T21:23:14.072183+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4880354", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T07:23:50.803385+00:00", "modelId": "hcnote/SparkMuse-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4453695184, "estimatedRequiredGiB": 4.989, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4463853848, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4114366080, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 4463853848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T23:23:24.114544+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4881705", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-16T16:51:05.849377+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T08:44:19.185430+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4889469", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-16T17:09:11.209752+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:03:09.666793+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4889677", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-16T17:41:50.112754+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:37:59.405066+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4890080", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -368,7 +366,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:22:17.565308+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T14:18:50.561697+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002167", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T23:56:03.457453+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51304360808, "estimatedRequiredGiB": 57.349, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 20341994707, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 51315158961}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T15:54:32.713857+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5003279", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T00:21:56.762809+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51304360808, "estimatedRequiredGiB": 57.349, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 51315158961, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 51315158961}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T16:21:12.297298+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003635", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T00:29:46.753417+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9517467172, "estimatedRequiredGiB": 10.647, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9526650722, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9526650722}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T16:28:23.621387+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5003752", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T00:51:40.462531+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51304360808, "estimatedRequiredGiB": 57.349, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 51315158961, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 51315158961}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T16:50:25.196591+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5004126", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T01:05:23.461251+00:00", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T17:03:32.337763+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5004418", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T01:26:44.660341+00:00", "modelId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 761968600, "estimatedRequiredGiB": 0.854, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 763816934, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 763816934}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T17:25:56.838948+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004736", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user