state: generation 18322 (cycle)
This commit is contained in:
@@ -3280,7 +3280,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-29T08:31:22.010121+00:00",
|
||||
"generatedAt": "2026-09-29T08:42:44.022785+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 165,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-29T08:41:39.458336+00:00",
|
||||
"generatedAt": "2026-09-29T08:44:21.158448+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-29T08:41:39.458336+00:00",
|
||||
"catalogUpdatedAt": "2026-09-29T08:44:21.158448+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-29T08:41:40.057417+00:00",
|
||||
"generatedAt": "2026-09-29T08:44:21.476101+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -2175,7 +2175,7 @@
|
||||
"taskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
"updatedAt": "2026-09-28T08:44:03.475355+00:00"
|
||||
"updatedAt": "2026-09-29T08:44:21.476101+00:00"
|
||||
},
|
||||
"https://modelscope.cn/models/chenyumo/moziAI-35B-A3B-MOE-MTP|2026-09-25T03:56:17+00:00|hygon_k100-ai": {
|
||||
"taskTypes": [
|
||||
@@ -6311,6 +6311,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-29T08:41:39.458336+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-29T08:44:21.158448+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-29T08:31:21.922543+00:00",
|
||||
"lastSyncTime": "2026-09-29T08:31:21.660441+00:00",
|
||||
"generatedAt": "2026-09-29T08:42:43.931135+00:00",
|
||||
"lastSyncTime": "2026-09-29T08:42:43.646924+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -5422,18 +5422,18 @@
|
||||
"unresolvedFailureCount": 296
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 116,
|
||||
"attributableFailureCount": 117,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 116,
|
||||
"decisionTotal": 117,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 16,
|
||||
"framework_architecture_unsupported": 17,
|
||||
"platform_infrastructure": 22,
|
||||
"tokenizer_compatibility": 91,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 144,
|
||||
"failureCount": 145,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -5443,7 +5443,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 144,
|
||||
"total": 145,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -5458,23 +5458,23 @@
|
||||
"context_length": 34,
|
||||
"framework_architecture_unsupported": 143,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 208,
|
||||
"platform_infrastructure": 209,
|
||||
"repository_structure": 75,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 180,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 943,
|
||||
"failureCount": 944,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 208,
|
||||
"platformFailureCount": 209,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 943,
|
||||
"total": 944,
|
||||
"unresolvedFailureCount": 118
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|unknown": {
|
||||
@@ -5989,20 +5989,20 @@
|
||||
"framework_architecture_unsupported": 1363,
|
||||
"memory_capacity": 725,
|
||||
"model_load": 220,
|
||||
"platform_infrastructure": 872,
|
||||
"platform_infrastructure": 873,
|
||||
"repository_structure": 470,
|
||||
"runtime_memory": 66,
|
||||
"tokenizer_compatibility": 417,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6139,
|
||||
"failureCount": 6140,
|
||||
"failureRate": 0.9844,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 872,
|
||||
"platformFailureCount": 873,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0156,
|
||||
"total": 6236,
|
||||
"total": 6237,
|
||||
"unresolvedFailureCount": 1637
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -6100,28 +6100,28 @@
|
||||
"unresolvedFailureCount": 26
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 154,
|
||||
"decisionFailureRate": 0.9686,
|
||||
"decisionSuccessRate": 0.0314,
|
||||
"decisionTotal": 159,
|
||||
"attributableFailureCount": 155,
|
||||
"decisionFailureRate": 0.9688,
|
||||
"decisionSuccessRate": 0.0312,
|
||||
"decisionTotal": 160,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 327,
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 35,
|
||||
"framework_architecture_unsupported": 36,
|
||||
"memory_capacity": 10,
|
||||
"model_load": 9,
|
||||
"platform_infrastructure": 22,
|
||||
"tokenizer_compatibility": 91,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 516,
|
||||
"failureCount": 517,
|
||||
"failureRate": 0.9904,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 22,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0096,
|
||||
"total": 521,
|
||||
"total": 522,
|
||||
"unresolvedFailureCount": 340
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -6153,7 +6153,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-29T08:31:21.909443+00:00",
|
||||
"generatedAt": "2026-09-29T08:42:43.917415+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6488,32 +6488,32 @@
|
||||
"unresolvedFailureCount": 299
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 752,
|
||||
"decisionFailureRate": 0.8899,
|
||||
"decisionSuccessRate": 0.1101,
|
||||
"decisionTotal": 845,
|
||||
"attributableFailureCount": 753,
|
||||
"decisionFailureRate": 0.8901,
|
||||
"decisionSuccessRate": 0.1099,
|
||||
"decisionTotal": 846,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 162,
|
||||
"architecture_compatibility": 44,
|
||||
"backend_operator": 37,
|
||||
"context_length": 39,
|
||||
"framework_architecture_unsupported": 161,
|
||||
"framework_architecture_unsupported": 162,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 230,
|
||||
"platform_infrastructure": 231,
|
||||
"repository_structure": 83,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 274,
|
||||
"参数/模板问题": 228,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1404,
|
||||
"failureRate": 0.9379,
|
||||
"failureCount": 1406,
|
||||
"failureRate": 0.938,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 230,
|
||||
"platformFailureCount": 231,
|
||||
"successCount": 93,
|
||||
"successRate": 0.0621,
|
||||
"total": 1497,
|
||||
"successRate": 0.062,
|
||||
"total": 1499,
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -20980,14 +20980,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "qwen3_5_moe",
|
||||
@@ -20999,7 +20999,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
|
||||
@@ -21193,21 +21193,21 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"platform_infrastructure": 1
|
||||
"platform_infrastructure": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"platformFailureCount": 2,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"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|gptq": {
|
||||
@@ -49128,6 +49128,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|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": "qwen3_5_moe",
|
||||
"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|none|35": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -49441,6 +49465,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -52329,23 +52377,23 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17101,
|
||||
"totalRecords": 17322,
|
||||
"terminalRecords": 17103,
|
||||
"totalRecords": 17324,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6130,
|
||||
"attributableFailureCount": 6131,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7098,
|
||||
"decisionTotal": 7099,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4439,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
"context_length": 322,
|
||||
"framework_architecture_unsupported": 2184,
|
||||
"framework_architecture_unsupported": 2185,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 550,
|
||||
"platform_infrastructure": 941,
|
||||
"platform_infrastructure": 942,
|
||||
"repository_structure": 742,
|
||||
"runtime_memory": 101,
|
||||
"tokenizer_compatibility": 682,
|
||||
@@ -52353,14 +52401,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16133,
|
||||
"failureCount": 16135,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 941,
|
||||
"platformFailureCount": 942,
|
||||
"successCount": 968,
|
||||
"successRate": 0.0566,
|
||||
"total": 17101,
|
||||
"total": 17103,
|
||||
"unresolvedFailureCount": 9062
|
||||
},
|
||||
"warnings": [
|
||||
@@ -52390,6 +52438,7 @@
|
||||
"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。",
|
||||
"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 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -52414,11 +52463,10 @@
|
||||
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17322,
|
||||
"summarizedRecords": 17324,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -116,7 +116,6 @@
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "modelId": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "submitTime": "2026-09-14T06:58:38.810772+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844797", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "modelId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "submitTime": "2026-09-14T06:58:38.815931+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844799", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-35B-A3B-preview", "modelId": "Edge0/Edge0-35B-A3B-preview", "submitTime": "2026-09-14T08:26:23.557278+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4846122", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
||||
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-14T09:49:08.451908+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4847129", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
|
||||
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "submitTime": "2026-09-14T10:42:38.360078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4847818", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
|
||||
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "submitTime": "2026-09-14T10:59:43.480777+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4847964", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
|
||||
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "submitTime": "2026-09-14T12:34:59.173731+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849005", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
|
||||
@@ -133,7 +132,6 @@
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-14T22:08:21.042712+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4858025", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
|
||||
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "modelId": "hcnote/SparkMuse-4B", "submitTime": "2026-09-14T22:58:26.649925+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860053", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
|
||||
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "submitTime": "2026-09-15T03:41:36.846485+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4865835", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
|
||||
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-15T03:41:36.837802+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4865837", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "modelId": "hcnote/SparkMuse-4B", "submitTime": "2026-09-15T04:40:55.430493+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866583", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "submitTime": "2026-09-15T04:40:55.428522+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866580", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-15T04:40:55.432907+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866582", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.22.1",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "10602ef448924874f2b166d7a4ee8194f1ab428e833025b9d2f151b9b8dc6b7c",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "f22d1fa80a8e886e1c2c6612a9635c04f6afd676758689ffa5a05a02ef2f6cdf",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "67122b165d91dd90e6338192b156cb484fb2553c665e963de7006b8de6603aee",
|
||||
".modelhub_state/official_capabilities.json": "57c30db73ae7fbe63bcaeb6bbead7075b2f1c6c6c3563316868c8feacd5ca4cb",
|
||||
".modelhub_state/outcome_checkpoint.json": "21a020491380eae51f8ff18672afb2b69f5157dd7d8cd53032c1cb95df758f31",
|
||||
".modelhub_state/market_intelligence.json": "46242a7c96c843ed2717c9cbccfe0a7ca426b52c5ae92d64897bcbe53673ad90",
|
||||
".modelhub_state/official_capabilities.json": "a0744ffd7013eaa8bdc3be15a70afbc7100a65c9236887c069aacbf93b0226d8",
|
||||
".modelhub_state/outcome_checkpoint.json": "b5ce70cbd2ab45a66d44e74aa2894965c1fd6c2eeea7e51d42da5aa846189fce",
|
||||
".modelhub_state/queue_cleanup_latest.json": "37a7b727a3aa5ec1301790759b43b6c0491f74c98e8259c115c42cca3fa0c585",
|
||||
".modelhub_state/recent_outcomes.jsonl": "4b5c4a762b4dbd70f9146d7ca2646ab162c72c38064fe2776db10f1d122b9201",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "badf4223e8468638a294894ec5ea5ff1b01b92961d7c42ee1257a308c278dddb",
|
||||
".modelhub_state/recovery_intents.jsonl": "7062d53b60540eb68a64a1b1f9253d19aa8f22ccd3d6cfedb2e014f645d8d137",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "079d839b774de1e6a62624e0ff843589bf08064ca4f33d6de79f30b987444793",
|
||||
".modelhub_state/recovery_intents.jsonl": "c4ba2a4eed33f5638a64a39843a030b26565361621397a23d2983efe36b3e06c",
|
||||
".modelhub_state/routing_intelligence.json": "aea169fcd28ee89ddb8a2c374f7bebe61ebeeecce81dcae8cc03517271315c3a",
|
||||
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
|
||||
".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06",
|
||||
"ledger/submissions.jsonl": "9085d1757bf93efbcb3b6b8f1b69d99cc603e76f5bb36f177a01ea81db170dcf",
|
||||
"outcomes/submissions.jsonl": "7431e3c6dc57e3b6bfe6cbe8d8518a040603a8b5ea5e8f72321867cab776b933"
|
||||
"ledger/submissions.jsonl": "cb921e0a34a27d153b262ce1c26f06d7545d246ad43afbe9f83f3a9f5c07051d",
|
||||
"outcomes/submissions.jsonl": "02b99d7008963fda9d364b177ae0241183d7175e0dc5b64ab4292801b257ae38"
|
||||
},
|
||||
"generation": 18321,
|
||||
"generation": 18322,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-29T08:41:40.552942+00:00",
|
||||
"updatedAt": "2026-09-29T08:44:26.821210+00:00",
|
||||
"writerId": "9d958b95ce4146c9939da0f14b9201ff"
|
||||
}
|
||||
|
||||
@@ -31,7 +31,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228798+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:08:47.402496+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678379", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228865+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "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": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:15:16.244457+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678529", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012291+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.107095+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678756", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012329+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "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": 9023443508, "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": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.111002+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678760", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T06:07:37.712071+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.438, "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": 9339955920, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:math", "custom_tag:stem", "custom_tag:mtp", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9339955920}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:55:23.563817+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679536", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T17:31:43.302628+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9fba363aef42aed2b52f3be34868ab5830a7c956f45e65fceed6561122eb8743", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T09:29:07.790789+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4691709", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T18:00:51.826326+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8bb72add25c6bbefdaaa3d4fc9d420176b02cfa13433975a607b2e5a23d944d6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T09:53:15.317620+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4692145", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -368,7 +367,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191922+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.641997+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981867", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.192054+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.613984+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981862", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.192037+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.661284+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981869", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191983+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "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": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.650053+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981868", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191935+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.664252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981866", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.192015+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.668818+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981871", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191969+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "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": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "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": 25613691403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.612449+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981865", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user