state: generation 12265 (intent)

This commit is contained in:
2026-10-27 18:21:23 +00:00
parent 0d61117648
commit 899bebee52
6 changed files with 198 additions and 178 deletions

View File

@@ -823,7 +823,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-27T18:15:07.455375+00:00",
"generatedAt": "2026-10-27T18:21:18.964396+00:00",
"summary": {
"activeBlockCount": 40,
"byGpuFramework": {

View File

@@ -452,7 +452,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-27T18:18:49.448403+00:00",
"generatedAt": "2026-10-27T18:21:21.662643+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
@@ -469,7 +469,7 @@
"recentSuccessRate": 1.0,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 1,
"running": 0,
"selectionWeight": 2.4999999996428555,
"stale": false,
"submissionEligible": true,
@@ -491,7 +491,7 @@
"recentSuccessRate": 1.0,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"running": 1,
"running": 0,
"selectionWeight": 2.5,
"stale": false,
"submissionEligible": true,
@@ -500,34 +500,12 @@
},
"Biren_166m": {
"available": true,
"backlogHours": 0.01350090267663245,
"backlogHours": 0.013500981175957556,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343977,
"recentSuccessRate": 1.0,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"running": 1,
"selectionWeight": 2.5,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.5,
"waiting": 774
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 0.013500981175957556,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 2.4999999996428555,
"queueFactor": 1.0,
"queueWeight": 1.0,
@@ -542,6 +520,28 @@
"throughputPerHour": 57329.166666666664,
"waiting": 774
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 0.01350090267663245,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 2.5,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343977,
"recentSuccessRate": 1.0,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"running": 0,
"selectionWeight": 2.5,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.5,
"waiting": 774
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 0.013500981175957556,
@@ -557,7 +557,7 @@
"recentSuccessRate": 1.0,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 0,
"running": 1,
"selectionWeight": 2.4999999996428555,
"stale": false,
"submissionEligible": true,
@@ -566,100 +566,122 @@
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 0.01350090267663245,
"backlogHours": 0.013500981175957556,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 24,
"qualityFactor": 2.5,
"qualityFactor": 2.4999999996428555,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343977,
"recentSuccess": 343975,
"recentSuccessRate": 1.0,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"running": 0,
"selectionWeight": 2.5,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 1,
"selectionWeight": 2.4999999996428555,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.5,
"throughputPerHour": 57329.166666666664,
"waiting": 774
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 0.013500981175957556,
"backlogHours": 0.01350090267663245,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 2.4999999996428555,
"qualityFactor": 2.5,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343975,
"recentSuccess": 343977,
"recentSuccessRate": 1.0,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 0,
"selectionWeight": 2.4999999996428555,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"running": 1,
"selectionWeight": 2.5,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.166666666664,
"throughputPerHour": 57329.5,
"waiting": 774
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 0.01350090267663245,
"backlogHours": 0.013500981175957556,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 2.5,
"qualityFactor": 2.4999999996428555,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343977,
"recentSuccess": 343975,
"recentSuccessRate": 1.0,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 1,
"selectionWeight": 2.5,
"selectionWeight": 2.4999999996428555,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.5,
"throughputPerHour": 57329.166666666664,
"waiting": 774
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 0.01350090267663245,
"backlogHours": 0.013500981175957556,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"qualityFactor": 2.4999999996428555,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343977,
"recentSuccess": 343975,
"recentSuccessRate": 1.0,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"running": 0,
"selectionWeight": 2.5,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 1,
"selectionWeight": 2.4999999996428555,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.5,
"throughputPerHour": 57329.166666666664,
"waiting": 774
},
"MetaX_c-500": {
"available": true,
"backlogHours": 0.01350090267663245,
"backlogHours": 0.013500981175957556,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.4999999996428555,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343975,
"recentSuccessRate": 1.0,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 1,
"selectionWeight": 2.4999999996428555,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.166666666664,
"waiting": 774
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 0.01350090267663245,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 1.0,
"queueWeight": 1.0,
@@ -674,48 +696,26 @@
"throughputPerHour": 57329.5,
"waiting": 774
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 0.013500981175957556,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.4999999996428555,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343975,
"recentSuccessRate": 1.0,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 0,
"selectionWeight": 2.4999999996428555,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.166666666664,
"waiting": 774
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 0.013500981175957556,
"backlogHours": 0.01350090267663245,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 2.4999999996428555,
"qualityFactor": 2.5,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343975,
"recentSuccess": 343977,
"recentSuccessRate": 1.0,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 0,
"selectionWeight": 2.4999999996428555,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"running": 1,
"selectionWeight": 2.5,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.166666666664,
"throughputPerHour": 57329.5,
"waiting": 774
},
"Vastai_va16": {
@@ -742,30 +742,30 @@
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 0.01350090267663245,
"backlogHours": 0.013500981175957556,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"qualityFactor": 2.4999999996428555,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 343977,
"recentSuccess": 343975,
"recentSuccessRate": 1.0,
"recentTerminal": 343977,
"recentWilsonLowerBound": 0.9999888319361562,
"recentTerminal": 343975,
"recentWilsonLowerBound": 0.9999888318712216,
"running": 0,
"selectionWeight": 2.5,
"selectionWeight": 2.4999999996428555,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 57329.5,
"throughputPerHour": 57329.166666666664,
"waiting": 774
}
},
"queueAttemptedAt": "2026-10-27T18:11:20.252017+00:00",
"queueAttemptedAt": "2026-10-27T18:21:21.662643+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-27T18:11:20.252017+00:00",
"queueUpdatedAt": "2026-10-27T18:21:21.662643+00:00",
"supportedGpus": [
"Cambricon_mlu-370-x4",
"Vastai_va16",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-27T18:18:49.448403+00:00",
"catalogUpdatedAt": "2026-10-27T18:21:21.662643+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-27T18:19:27.692336+00:00",
"generatedAt": "2026-10-27T18:21:22.965689+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -714,12 +714,6 @@
],
"updatedAt": "2026-10-27T18:16:58.079081+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-30B-A3B-Thinking-2507-MNN|2026-10-21T05:16:27+00:00|Vastai_va16": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-10-27T10:18:41.974945+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-30B-A3B-Thinking-2507-MNN|2026-10-21T05:16:27+00:00|hygon_k100-ai": {
"taskTypes": [
"text-generation",
@@ -867,14 +861,6 @@
],
"updatedAt": "2026-10-27T18:11:21.465726+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Instruct-MNN|2026-10-21T05:16:38+00:00|Cambricon_mlu-370-x8": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-27T10:18:42.001009+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Instruct-MNN|2026-10-21T05:16:38+00:00|Iluvatar_bi-100": {
"taskTypes": [
"text-generation",
@@ -966,7 +952,7 @@
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-10-27T10:18:41.982722+00:00"
"updatedAt": "2026-10-27T18:21:22.932672+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Thinking-MNN|2026-10-21T05:16:44+00:00|Cambricon_mlu-370-x4": {
"taskTypes": [
@@ -976,6 +962,14 @@
],
"updatedAt": "2026-10-27T18:09:16.985924+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Thinking-MNN|2026-10-21T05:16:44+00:00|Cambricon_mlu-370-x8": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-27T18:21:22.965689+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Thinking-MNN|2026-10-21T05:16:44+00:00|Iluvatar_bi-100": {
"taskTypes": [
"text-generation",
@@ -997,6 +991,15 @@
],
"updatedAt": "2026-10-27T18:13:17.816368+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Thinking-MNN|2026-10-21T05:16:44+00:00|Iluvatar_mrv-100": {
"taskTypes": [
"asr",
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-27T18:21:22.898051+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Thinking-MNN|2026-10-21T05:16:44+00:00|Kunlunxin_p-800": {
"taskTypes": [
"text-generation"
@@ -1024,13 +1027,11 @@
],
"updatedAt": "2026-10-27T18:16:58.061290+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Thinking-MNN|2026-10-21T05:16:44+00:00|hygon_k100-ai": {
"https://modelscope.cn/models/MNN/Qwen3-VL-30B-A3B-Thinking-MNN|2026-10-21T05:16:44+00:00|Vastai_va16": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
"text-generation"
],
"updatedAt": "2026-10-27T10:18:42.022026+00:00"
"updatedAt": "2026-10-27T18:21:22.757562+00:00"
},
"https://modelscope.cn/models/MNN/Qwen3.5-35B-A3B-Base-MNN|2026-10-21T05:16:50+00:00|Ascend_910-b3": {
"taskTypes": [
@@ -6475,6 +6476,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-27T18:18:49.448403+00:00",
"taskTreeUpdatedAt": "2026-10-27T18:21:21.662643+00:00",
"version": 1
}

View File

@@ -85,6 +85,25 @@
{"agentVersion": "2026.10.27.1", "batchId": "2cbda3c6e1fd462d891d059a1872ef50", "completedAt": "2026-10-27T16:09:58.407117+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-27T16:05:54.335528+00:00", "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "intentId": "a3b246b3f9564bdbbc26ea217fd9289d", "lastModified": "2026-10-26T14:47:31+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nanbeige4.3-33B-NVFP4", "reason": null, "reconciledAt": "2026-10-27T18:15:55.091631+00:00", "repoId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "targetGpu": "Ascend_910-b3", "taskId": "5829196", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "3999d7270e3d453d9d9838ee22289fdc", "completedAt": "2026-10-27T16:45:53.282389+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-27T16:44:56.752536+00:00", "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "intentId": "1ba0b366c3d34e108da46f82315f13b4", "lastModified": "2026-10-26T16:45:37+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-27T18:15:55.091245+00:00", "repoId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Ascend_910-b3", "taskId": "5829779", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "205f8290646141f1b2c50438a301c4bf", "completedAt": "2026-10-27T17:16:59.343990+00:00", "configFingerprint": "599b696754d742f615413500a637d0fa5409f7e104beb786ffc6c086b45b60ad", "configSource": "modelhub_live", "createdAt": "2026-10-27T17:16:11.458588+00:00", "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "intentId": "346132390e944052a036ae77e8244fc3", "lastModified": "2026-10-25T09:23:51+00:00", "modelAddress": "https://modelscope.cn/models/alkaid55555/rewrite2-4b-gguf", "reason": null, "reconciledAt": "2026-10-27T18:15:55.092291+00:00", "repoId": "alkaid55555/rewrite2-4b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "hygon_k100-ai", "taskId": "5830169", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "90b1e01bca1e1739418f9e81796d177e5c987058003884d48e912c8953d3412b", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.024796+00:00", "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "intentId": "937bb72777344d6cb09b68d8b5375d31", "lastModified": "2026-10-25T09:23:51+00:00", "modelAddress": "https://modelscope.cn/models/alkaid55555/rewrite2-4b-gguf", "repoId": "alkaid55555/rewrite2-4b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "65308d51d989632c3706640032866b6c4c44d20b1c28a46a785d6885ec3a08db", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.024883+00:00", "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "intentId": "a62d5e59b421418d883bbd46d6b9c8d0", "lastModified": "2026-10-20T18:58:17+00:00", "modelAddress": "https://modelscope.cn/models/incoai/Qwen3.8-Flash-Next-DFlash2-GGUF", "repoId": "incoai/Qwen3.8-Flash-Next-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.024944+00:00", "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "intentId": "ad77401cd7dd480cb0527789ec1c5197", "lastModified": "2026-10-26T17:22:30+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "repoId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025002+00:00", "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "intentId": "760de4adedc04ec39ad25666aa7370fa", "lastModified": "2026-10-26T15:32:01+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/LFM2-8B-A1B-AWQ-8bit", "repoId": "cpatonn-mirror/LFM2-8B-A1B-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025055+00:00", "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "intentId": "2fdaf714593445e7a1be9ec35fd81010", "lastModified": "2026-10-21T15:22:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Orchestrator-8B-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025107+00:00", "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "intentId": "42a31a754ce244aab4de104129afaa2f", "lastModified": "2026-10-26T15:58:59+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025160+00:00", "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "intentId": "01378a2e2b9e497584cc624a29a1c3e7", "lastModified": "2026-10-21T14:48:26+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2-8B-A1B-AWQ-8bit", "repoId": "cyankiwi/LFM2-8B-A1B-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025225+00:00", "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "intentId": "42480ce79ccd4aa1b9f9a55ac23c549b", "lastModified": "2026-10-21T14:27:09+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-2-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-2-30B-A3B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025285+00:00", "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "intentId": "2670e7d64f44476d9691c4f99c1fc784", "lastModified": "2026-10-23T05:34:56+00:00", "modelAddress": "https://modelscope.cn/models/GMUnitX/DeepSeek-R1-Distill-Qwen-1.5B-MPVDHS", "repoId": "GMUnitX/DeepSeek-R1-Distill-Qwen-1.5B-MPVDHS", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025336+00:00", "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "intentId": "1993de82acac4ac2baac1476b0f48c5b", "lastModified": "2026-10-21T15:39:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Dev-72B-AWQ-8bit", "repoId": "cyankiwi/Kimi-Dev-72B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025390+00:00", "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "intentId": "028e7b32fa8e4f019458871ef32fc22c", "lastModified": "2026-10-21T12:16:18+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-122B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-122B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025443+00:00", "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "intentId": "b73d64ec98ae4f39adfd3dfc512d27de", "lastModified": "2026-10-21T16:52:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4-70B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4-70B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025493+00:00", "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "intentId": "d835be2db6d14f7793c79d8c2a00a13f", "lastModified": "2026-10-22T01:39:23+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint", "repoId": "RecursiveSI/flint", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025543+00:00", "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "intentId": "064c885dfc774efe96ba67427810871a", "lastModified": "2026-10-26T17:03:50+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "repoId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025601+00:00", "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "intentId": "779f271f655b4ecdaef1e6c3489760e3", "lastModified": "2026-10-26T15:02:56+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Hermes-4-70B-AWQ-4bit", "repoId": "cpatonn-mirror/Hermes-4-70B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025657+00:00", "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "intentId": "b20db72707374f789a711566de573bfc", "lastModified": "2026-10-26T13:34:47+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-8bit", "repoId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025713+00:00", "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "intentId": "0a6f24e926fd46da9ee8e50435aa9ea8", "lastModified": "2026-10-21T13:46:58+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "repoId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025769+00:00", "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "intentId": "9f1eea2f8b6244d48c660fa7da734194", "lastModified": "2026-10-21T16:43:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Dev-72B-AWQ-4bit", "repoId": "cyankiwi/Kimi-Dev-72B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "54e2b86d321c4038ae1502b288d9b0b3", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:21:23.025829+00:00", "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "intentId": "8f19d5f99ceb4461a1d9ff90d41eda40", "lastModified": "2026-10-21T16:17:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "repoId": "cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "d07252667e074759824c56b7c1635a59", "completedAt": "2026-10-27T18:20:18.188545+00:00", "configFingerprint": "f00da8ce83a940abb8266270de5e2f8af77ceb93ee04f5f9bcdacaf63f31283e", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:19:27.805350+00:00", "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "intentId": "39038113e33f484da1d1389aea308aa4", "repoId": "incoai/Qwen3.8-Flash-Next-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "d07252667e074759824c56b7c1635a59", "completedAt": "2026-10-27T18:20:18.188543+00:00", "configFingerprint": "2b76d0c709b61c2cc2e02d0648be931ceeb588fbec9197808d2ec3b6e9133262", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:19:27.805251+00:00", "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "intentId": "6b325745f30141cb9b9dd1c60df2d875", "repoId": "alkaid55555/rewrite2-4b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"agentVersion": "2026.10.28.1", "batchId": "d07252667e074759824c56b7c1635a59", "completedAt": "2026-10-27T18:20:18.188541+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-10-27T18:19:27.805151+00:00", "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "intentId": "5e825849421a4ae9ac4d2a3914ff6bf5", "repoId": "RecursiveSI/flint", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}

View File

@@ -2,23 +2,23 @@
"agentVersion": "2026.10.28.1",
"checksums": {
".modelhub_state/account_capacity.json": "75992f8fc87bd43463ad6a2225d42d2ca55bf3279439823531261e6ae705f09c",
".modelhub_state/architecture_compatibility_blacklist.json": "d6886be7cd58999ac6fc759e56c6f80ba3dffa77e3d2ec0f5994c28b9951e694",
".modelhub_state/architecture_compatibility_blacklist.json": "c11b0b25b291b0beebf92f24e96656e0e89cd6c7e1b66f354858ea24ca111c82",
".modelhub_state/architecture_history_backfill.json": "3d540298447c4305031831a11786480aa96821e37ff7b9b66e91598e2a49f6ff",
".modelhub_state/market_intelligence.json": "495250e9c04cb703c24f3a05409981638ec108fe637fd260f8af0ec529b67d55",
".modelhub_state/official_capabilities.json": "b917b23b92f204e1f8fd434dc14de139fd9d827699cbee6a07d399d3f5673c72",
".modelhub_state/market_intelligence.json": "c2d9611939d5cbe4f0de1581ce86351fda4810a39c0b9d1d19fe7c3083641fa6",
".modelhub_state/official_capabilities.json": "863cac016ba6aa62109dfc3db6fc6652ff1008b00cc5fe28d6a68a749a684362",
".modelhub_state/outcome_checkpoint.json": "c95db5ddcd14347d83e3dd710e8da909358d61dd4f1c26d66a306942f4adf08a",
".modelhub_state/recent_outcomes.jsonl": "3d26db0469cff4d1588eb937ce38bf4508ae9b1ba95c90c41d5a0f33ff9f88b0",
".modelhub_state/recovery_active_tasks.jsonl": "722d702264533ee6096db1e31716e79011f2a6afd8c4eecc750dabbba0c299c6",
".modelhub_state/recovery_intents.jsonl": "3726b417cc2d6d743952f2678a6e2a790aef614693108438b262ef680f078553",
".modelhub_state/recovery_intents.jsonl": "c23ad1858f7b9df6958ee7b4c9660681d7ce1a8b7f748f5156e848570da89653",
".modelhub_state/routing_intelligence.json": "491e99d1eca802062967bf077fabf7e96c6800fdd2563faa20f4e2545aa562dd",
".modelhub_state/submission_exclusions.jsonl": "6abc2deecdbf65ba90b13943522589c9115414654045dae163413b447c2edae1",
".modelhub_state/worker_crashes.jsonl": "e7dea628c569977a7ab60a9bc69ee94dea2dc732d7c8397e37338a52aa80d97d",
"ledger/submissions.jsonl": "f4b88c89a06944f92a9d621d07f8a58e0b2f269eaf641d887eefc4435b87d5ae",
"outcomes/submissions.jsonl": "189de7fa2b5aa9de907a0670608914d4f9919187334e3eb9c212ba4931cb1885"
"outcomes/submissions.jsonl": "7fefd9316ad721adcb42956fcc61ffe434e44a5bf57a3b80a2925387fdba2c83"
},
"generation": 12264,
"phase": "result",
"generation": 12265,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-10-27T18:20:18.283317+00:00",
"updatedAt": "2026-10-27T18:21:23.090114+00:00",
"writerId": "b60d613251844af6b43636e34287be85"
}

View File

@@ -1149,54 +1149,54 @@
{"framework": null, "lastSyncTime": "2026-10-26T07:42:03.480036+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-quantized.w8a8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4332423", "taskType": "text-generation"}
{"framework": null, "lastSyncTime": "2026-10-26T07:42:03.480059+00:00", "modelId": "z-lab/Qwen3.8-27B-DFlash2-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4332399", "taskType": "text-generation"}
{"framework": null, "lastSyncTime": "2026-10-27T09:07:39.875389+00:00", "modelId": "cyankiwi/Nex-N2-mini-AWQ-INT4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4079930", "taskType": "text-generation"}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3459874983, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 3459874983, "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.061571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824135", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852073, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852073, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852073, "repositoryOnDiskBytes": 18115852073}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.081308+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824139", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "pfnet/plamo-13b-instruct", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200349563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:apache-2.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200349563, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200349563, "repositoryOnDiskBytes": 26200349563}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.175285+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824144", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852009, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852009, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852009, "repositoryOnDiskBytes": 18115852009}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.063227+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824134", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "pfnet/plamo-13b-instruct-nc", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200357986, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200357986, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200357986, "repositoryOnDiskBytes": 26200357986}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.082935+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824140", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115815143, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1c0587b0b0cf71b0", "recursiveRepositoryBytes": 18115815143, "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.034492+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824161", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115840957, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115840957, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5d1bf83368e103ed", "recursiveRepositoryBytes": 18115840957, "repositoryOnDiskBytes": 18115840957}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.094407+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824143", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.6-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4451626120, "estimatedRequiredGiB": 4.992, "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": 4466699746, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4466699746, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:792a878136ace20b", "recursiveRepositoryBytes": 4466699746, "repositoryOnDiskBytes": 4466699746}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.064273+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824136", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432699381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5432699381, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432699381, "repositoryOnDiskBytes": 5432699381}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.132633+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824141", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883380, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883380, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883380, "repositoryOnDiskBytes": 23398883380}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.059560+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824137", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.6-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.208, "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": 8239287196, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8239287196, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 8239287196, "repositoryOnDiskBytes": 8239287196}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.110784+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824138", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883380, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883380, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883380, "repositoryOnDiskBytes": 23398883380}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.203946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824145", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Jan-v1-4B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432695293, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5432695293, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432695293, "repositoryOnDiskBytes": 5432695293}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.169601+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824142", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292650823, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14292650823, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cefd4b27e758b1de", "recursiveRepositoryBytes": 14292650823, "repositoryOnDiskBytes": 14292650823}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.182449+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824146", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 24697709480, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24697709480, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:59dd59959c7fd772", "recursiveRepositoryBytes": 24697709480, "repositoryOnDiskBytes": 24697709480}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.239218+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824147", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20682426913, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:d631cfb7fc7f8ffa", "recursiveRepositoryBytes": 20682426913, "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.206139+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824150", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 11.802, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 10560388030, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10560388030, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b91e1843aeaeb7f4", "recursiveRepositoryBytes": 10560388030, "repositoryOnDiskBytes": 10560388030}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.236296+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824149", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 19.185, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 17166416942, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17166416942, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b0b0c9a002005922", "recursiveRepositoryBytes": 17166416942, "repositoryOnDiskBytes": 17166416942}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.256695+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824148", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077977948, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11077977948, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:abf2795564ed82d1", "recursiveRepositoryBytes": 11077977948, "repositoryOnDiskBytes": 11077977948}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.252703+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824152", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 9688084066, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.254577+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824151", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.285428+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824153", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921104, "estimatedRequiredGiB": 11.048, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9885904129, "modelscopeLicense": null, "modelscopeParams": 8190735360, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9885904129, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b478ca1d5cf05e4", "recursiveRepositoryBytes": 9885904129, "repositoryOnDiskBytes": 9885904129}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.382051+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824159", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145039537, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8145039537, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:06e1b44940b82d27", "recursiveRepositoryBytes": 8145039537, "repositoryOnDiskBytes": 8145039537}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.350896+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824155", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.295226+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824166", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4750755304, "estimatedRequiredGiB": 5.331, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 4769740524, "modelscopeLicense": "other", "modelscopeParams": 3975229440, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4769740524, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:402c90eb0b5de1c4", "recursiveRepositoryBytes": 4769740524, "repositoryOnDiskBytes": 4769740524}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.330346+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824154", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8857194176, "estimatedRequiredGiB": 9.918, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 8874757118, "modelscopeLicense": "other", "modelscopeParams": 3057874704, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8874757118, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b63fa8ce792e9ecf", "recursiveRepositoryBytes": 8874757118, "repositoryOnDiskBytes": 8874757118}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.408272+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824160", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26176736582, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 26176736582, "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.375810+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824156", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/granite-4.0-h-tiny-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5504236472, "estimatedRequiredGiB": 6.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 5514064765, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7093177920, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5514064765, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 5514064765, "repositoryOnDiskBytes": 5514064765}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.393599+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824158", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 9688084066, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.406836+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824165", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-2-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20746036464, "estimatedRequiredGiB": 23.21, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20767786487, "modelscopeLicense": "other", "modelscopeParams": 6674513776, "modelscopeTags": ["license:other", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade-2", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20767786487, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:4e040710ef43272e", "recursiveRepositoryBytes": 20767786487, "repositoryOnDiskBytes": 20767786487}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.380443+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824157", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "GMUnitX/DeepSeek-R1-Distill-Qwen-1.5B-MPVDHS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7108390440, "estimatedRequiredGiB": 7.957, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 7119857588, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:Apache License 2.0", "model_type:Qwen2", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7119857588, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7119857588, "repositoryOnDiskBytes": 7119857588}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.390118+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824167", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3202498032, "estimatedRequiredGiB": 3.6, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 3221469377, "modelscopeLicense": "other", "modelscopeParams": 2323722240, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3221469377, "quantizationMethod": "modelopt", "quantizationSignature": "modelopt:7f111f5ecf2660ff", "recursiveRepositoryBytes": 3221469377, "repositoryOnDiskBytes": 3221469377}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.432938+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824162", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385576, "estimatedRequiredGiB": 13.343, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11938806923, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11938806923, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:c2062c64dee96c04", "recursiveRepositoryBytes": 11938806923, "repositoryOnDiskBytes": 11938806923}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.479452+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824164", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.786, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125281593, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14125281593, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:bd5110bb37ff4e58", "recursiveRepositoryBytes": 14125281593, "repositoryOnDiskBytes": 14125281593}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.481928+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824163", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24430419208, "estimatedRequiredGiB": 27.35, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 24472753002, "modelscopeLicense": "mit", "modelscopeParams": 35107181936, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24472753002, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cc806b483ebd2e69", "recursiveRepositoryBytes": 24472753002, "repositoryOnDiskBytes": 24472753002}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.147215+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824226", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "XingChen-AGI/Xing4.0-29B-Intent-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169542243, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33169542243, "quantizationMethod": "fp8", "quantizationSignature": "fp8:0da8624bcb5e84df", "recursiveRepositoryBytes": 33169542243, "repositoryOnDiskBytes": 33169542243}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.137559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824223", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "XingChen-AGI/Xing4.0-29B-Intent", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434092643, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 62434092643, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 62434092643, "repositoryOnDiskBytes": 62434092643}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.139261+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824235", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "nanbeige/Nanbeige4.3-33B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 66238009168, "estimatedRequiredGiB": 74.051, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 66260067498, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 66260067498, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 66260067498, "repositoryOnDiskBytes": 66260067498}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.132903+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824233", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064318294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064318294, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b74ddfdc145e58ff", "recursiveRepositoryBytes": 33064318294, "repositoryOnDiskBytes": 33064318294}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.135642+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824236", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/GLM-4.5-Air-AWQ-4bit", "modelProfile": {"architectures": ["Glm4MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 63400571960, "estimatedRequiredGiB": 70.884, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "glm4_moe", "modelscopeFileSize": 63425670208, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 63425670208, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e5192b47c94517b2", "recursiveRepositoryBytes": 63425670208, "repositoryOnDiskBytes": 63425670208}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.257369+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824227", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.145395+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824224", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "primitive-ai/Nanbeige4.3-33B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35526734272, "estimatedRequiredGiB": 39.728, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 35548056552, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35548056552, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:423cd90dc537dded", "recursiveRepositoryBytes": 35548056552, "repositoryOnDiskBytes": 35548056552}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.149342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824221", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Kimi-Dev-72B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 79588295928, "estimatedRequiredGiB": 88.967, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 79606715854, "modelscopeLicense": "mit", "modelscopeParams": 72706203648, "modelscopeTags": ["license:mit", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code", "custom_tag:swebench", "custom_tag:software", "custom_tag:issue-resolving"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 79606715854, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:08953c0a152f288b", "recursiveRepositoryBytes": 79606715854, "repositoryOnDiskBytes": 79606715854}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.152800+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824225", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.140846+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824222", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-8bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39756453136, "estimatedRequiredGiB": 44.442, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 39766281934, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 39766281934, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e379a948ff56dd79", "recursiveRepositoryBytes": 39766281934, "repositoryOnDiskBytes": 39766281934}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.373627+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824238", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064355224, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064355224, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064355224, "repositoryOnDiskBytes": 33064355224}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.363858+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824229", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-24B-A2B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47944143456, "estimatedRequiredGiB": 53.605, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 47964602717, "modelscopeLicense": "other", "modelscopeParams": 23971587712, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 47964602717, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 47964602717, "repositoryOnDiskBytes": 47964602717}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.368106+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824228", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064339297, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064339297, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064339297, "repositoryOnDiskBytes": 33064339297}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.362612+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824230", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935099+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3459874983, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 3459874983, "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.061571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824135", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935294+00:00", "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852073, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852073, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852073, "repositoryOnDiskBytes": 18115852073}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.081308+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824139", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935186+00:00", "modelId": "pfnet/plamo-13b-instruct", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200349563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:apache-2.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200349563, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200349563, "repositoryOnDiskBytes": 26200349563}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.175285+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824144", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935020+00:00", "modelId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852009, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852009, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852009, "repositoryOnDiskBytes": 18115852009}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.063227+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824134", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935283+00:00", "modelId": "pfnet/plamo-13b-instruct-nc", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200357986, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200357986, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200357986, "repositoryOnDiskBytes": 26200357986}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.082935+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824140", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935254+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115815143, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1c0587b0b0cf71b0", "recursiveRepositoryBytes": 18115815143, "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.034492+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824161", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935328+00:00", "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115840957, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115840957, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5d1bf83368e103ed", "recursiveRepositoryBytes": 18115840957, "repositoryOnDiskBytes": 18115840957}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.094407+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824143", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935066+00:00", "modelId": "XHToken/Spark-X2.6-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4451626120, "estimatedRequiredGiB": 4.992, "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": 4466699746, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4466699746, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:792a878136ace20b", "recursiveRepositoryBytes": 4466699746, "repositoryOnDiskBytes": 4466699746}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.064273+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824136", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935142+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432699381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5432699381, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432699381, "repositoryOnDiskBytes": 5432699381}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.132633+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824141", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935087+00:00", "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883380, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883380, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883380, "repositoryOnDiskBytes": 23398883380}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.059560+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824137", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935230+00:00", "modelId": "XHToken/Spark-X2.6-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.208, "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": 8239287196, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8239287196, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 8239287196, "repositoryOnDiskBytes": 8239287196}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.110784+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824138", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935080+00:00", "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883380, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883380, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883380, "repositoryOnDiskBytes": 23398883380}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.203946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824145", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935206+00:00", "modelId": "cpatonn-mirror/Jan-v1-4B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432695293, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5432695293, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432695293, "repositoryOnDiskBytes": 5432695293}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.169601+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824142", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935266+00:00", "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292650823, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14292650823, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cefd4b27e758b1de", "recursiveRepositoryBytes": 14292650823, "repositoryOnDiskBytes": 14292650823}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.182449+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824146", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935057+00:00", "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 24697709480, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24697709480, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:59dd59959c7fd772", "recursiveRepositoryBytes": 24697709480, "repositoryOnDiskBytes": 24697709480}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.239218+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824147", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935093+00:00", "modelId": "cpatonn-mirror/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20682426913, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:d631cfb7fc7f8ffa", "recursiveRepositoryBytes": 20682426913, "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.206139+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824150", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935009+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 11.802, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 10560388030, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10560388030, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b91e1843aeaeb7f4", "recursiveRepositoryBytes": 10560388030, "repositoryOnDiskBytes": 10560388030}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.236296+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824149", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935322+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 19.185, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 17166416942, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17166416942, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b0b0c9a002005922", "recursiveRepositoryBytes": 17166416942, "repositoryOnDiskBytes": 17166416942}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.256695+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824148", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935289+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077977948, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11077977948, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:abf2795564ed82d1", "recursiveRepositoryBytes": 11077977948, "repositoryOnDiskBytes": 11077977948}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.252703+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824152", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935278+00:00", "modelId": "cpatonn-mirror/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 9688084066, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.254577+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824151", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935224+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.285428+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824153", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935218+00:00", "modelId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921104, "estimatedRequiredGiB": 11.048, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9885904129, "modelscopeLicense": null, "modelscopeParams": 8190735360, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9885904129, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b478ca1d5cf05e4", "recursiveRepositoryBytes": 9885904129, "repositoryOnDiskBytes": 9885904129}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.382051+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824159", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935170+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145039537, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8145039537, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:06e1b44940b82d27", "recursiveRepositoryBytes": 8145039537, "repositoryOnDiskBytes": 8145039537}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.350896+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824155", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935128+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.295226+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824166", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935200+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4750755304, "estimatedRequiredGiB": 5.331, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 4769740524, "modelscopeLicense": "other", "modelscopeParams": 3975229440, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4769740524, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:402c90eb0b5de1c4", "recursiveRepositoryBytes": 4769740524, "repositoryOnDiskBytes": 4769740524}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.330346+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824154", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935272+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8857194176, "estimatedRequiredGiB": 9.918, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 8874757118, "modelscopeLicense": "other", "modelscopeParams": 3057874704, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8874757118, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b63fa8ce792e9ecf", "recursiveRepositoryBytes": 8874757118, "repositoryOnDiskBytes": 8874757118}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.408272+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824160", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935260+00:00", "modelId": "cyankiwi/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26176736582, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 26176736582, "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.375810+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824156", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935047+00:00", "modelId": "cyankiwi/granite-4.0-h-tiny-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5504236472, "estimatedRequiredGiB": 6.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 5514064765, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7093177920, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5514064765, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 5514064765, "repositoryOnDiskBytes": 5514064765}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.393599+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824158", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935163+00:00", "modelId": "cyankiwi/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 9688084066, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.406836+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824165", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935072+00:00", "modelId": "cyankiwi/Nemotron-Cascade-2-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20746036464, "estimatedRequiredGiB": 23.21, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20767786487, "modelscopeLicense": "other", "modelscopeParams": 6674513776, "modelscopeTags": ["license:other", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade-2", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20767786487, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:4e040710ef43272e", "recursiveRepositoryBytes": 20767786487, "repositoryOnDiskBytes": 20767786487}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.380443+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824157", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.934983+00:00", "modelId": "GMUnitX/DeepSeek-R1-Distill-Qwen-1.5B-MPVDHS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7108390440, "estimatedRequiredGiB": 7.957, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 7119857588, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:Apache License 2.0", "model_type:Qwen2", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7119857588, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7119857588, "repositoryOnDiskBytes": 7119857588}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.390118+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824167", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935317+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3202498032, "estimatedRequiredGiB": 3.6, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 3221469377, "modelscopeLicense": "other", "modelscopeParams": 2323722240, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3221469377, "quantizationMethod": "modelopt", "quantizationSignature": "modelopt:7f111f5ecf2660ff", "recursiveRepositoryBytes": 3221469377, "repositoryOnDiskBytes": 3221469377}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.432938+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824162", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935136+00:00", "modelId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385576, "estimatedRequiredGiB": 13.343, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11938806923, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11938806923, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:c2062c64dee96c04", "recursiveRepositoryBytes": 11938806923, "repositoryOnDiskBytes": 11938806923}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.479452+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824164", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935194+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.786, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125281593, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14125281593, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:bd5110bb37ff4e58", "recursiveRepositoryBytes": 14125281593, "repositoryOnDiskBytes": 14125281593}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.481928+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824163", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935312+00:00", "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24430419208, "estimatedRequiredGiB": 27.35, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 24472753002, "modelscopeLicense": "mit", "modelscopeParams": 35107181936, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24472753002, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cc806b483ebd2e69", "recursiveRepositoryBytes": 24472753002, "repositoryOnDiskBytes": 24472753002}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.147215+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824226", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935115+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-Intent-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169542243, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33169542243, "quantizationMethod": "fp8", "quantizationSignature": "fp8:0da8624bcb5e84df", "recursiveRepositoryBytes": 33169542243, "repositoryOnDiskBytes": 33169542243}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.137559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824223", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935156+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-Intent", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434092643, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 62434092643, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 62434092643, "repositoryOnDiskBytes": 62434092643}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.139261+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824235", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935236+00:00", "modelId": "nanbeige/Nanbeige4.3-33B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 66238009168, "estimatedRequiredGiB": 74.051, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 66260067498, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 66260067498, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 66260067498, "repositoryOnDiskBytes": 66260067498}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.132903+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824233", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935300+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064318294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064318294, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b74ddfdc145e58ff", "recursiveRepositoryBytes": 33064318294, "repositoryOnDiskBytes": 33064318294}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.135642+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824236", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935029+00:00", "modelId": "cyankiwi/GLM-4.5-Air-AWQ-4bit", "modelProfile": {"architectures": ["Glm4MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 63400571960, "estimatedRequiredGiB": 70.884, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "glm4_moe", "modelscopeFileSize": 63425670208, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 63425670208, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e5192b47c94517b2", "recursiveRepositoryBytes": 63425670208, "repositoryOnDiskBytes": 63425670208}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.257369+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824227", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935037+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.145395+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824224", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935121+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35526734272, "estimatedRequiredGiB": 39.728, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 35548056552, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35548056552, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:423cd90dc537dded", "recursiveRepositoryBytes": 35548056552, "repositoryOnDiskBytes": 35548056552}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.149342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824221", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935242+00:00", "modelId": "cpatonn-mirror/Kimi-Dev-72B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 79588295928, "estimatedRequiredGiB": 88.967, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 79606715854, "modelscopeLicense": "mit", "modelscopeParams": 72706203648, "modelscopeTags": ["license:mit", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code", "custom_tag:swebench", "custom_tag:software", "custom_tag:issue-resolving"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 79606715854, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:08953c0a152f288b", "recursiveRepositoryBytes": 79606715854, "repositoryOnDiskBytes": 79606715854}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.152800+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824225", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935249+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.140846+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824222", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935149+00:00", "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-8bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39756453136, "estimatedRequiredGiB": 44.442, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 39766281934, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 39766281934, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e379a948ff56dd79", "recursiveRepositoryBytes": 39766281934, "repositoryOnDiskBytes": 39766281934}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.373627+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824238", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935212+00:00", "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064355224, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064355224, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064355224, "repositoryOnDiskBytes": 33064355224}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.363858+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824229", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935108+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47944143456, "estimatedRequiredGiB": 53.605, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 47964602717, "modelscopeLicense": "other", "modelscopeParams": 23971587712, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 47964602717, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 47964602717, "repositoryOnDiskBytes": 47964602717}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.368106+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824228", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935306+00:00", "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064339297, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064339297, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064339297, "repositoryOnDiskBytes": 33064339297}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.362612+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824230", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "pfnet/plamo-13b-instruct", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200349563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:apache-2.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200349563, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200349563, "repositoryOnDiskBytes": 26200349563}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T11:09:55.619795+00:00", "targetGpu": "MetaX_c-500", "taskId": "5824879", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292650823, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14292650823, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cefd4b27e758b1de", "recursiveRepositoryBytes": 14292650823, "repositoryOnDiskBytes": 14292650823}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T12:21:38.039985+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5825974", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "pfnet/plamo-13b-instruct-nc", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200357986, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200357986, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200357986, "repositoryOnDiskBytes": 26200357986}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T13:23:26.475444+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826874", "taskType": "text-generation", "verifyResult": null}