CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 5205 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 14:31:42 +00:00
parent 0fb2af0ef8
commit 84159bc65c
10 changed files with 1958 additions and 1940 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1311,7 +1311,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T14:28:50.891377+00:00",
"generatedAt": "2026-09-10T14:31:41.197464+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -75,7 +75,7 @@
"7": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 370,
"listingErrors": 371,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 7,
"nextAccountIndex": 8,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T14:28:50.866502+00:00",
"updatedAt": "2026-09-10T14:31:41.171964+00:00",
"version": 1
}

2
.modelhub_state/market_intelligence.json
View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T14:26:54.882963+00:00",
"generatedAt": "2026-09-10T14:29:58.729933+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1518
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

110
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T13:55:41.106863+00:00",
"lastSyncTime": "2026-09-10T13:55:40.785159+00:00",
"generatedAt": "2026-09-10T14:29:51.879825+00:00",
"lastSyncTime": "2026-09-10T14:29:51.626253+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1905,29 +1905,29 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 44,
"decisionFailureRate": 0.9778,
"decisionSuccessRate": 0.0222,
"decisionTotal": 45,
"attributableFailureCount": 45,
"decisionFailureRate": 0.9783,
"decisionSuccessRate": 0.0217,
"decisionTotal": 46,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 25,
"backend_operator": 26,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 9
},
"failureCount": 60,
"failureRate": 0.9836,
"failureCount": 61,
"failureRate": 0.9839,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0164,
"successRate": 0.0161,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 61,
"total": 62,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2316,13 +2316,13 @@
"unresolvedFailureCount": 846
},
"vllm": {
"attributableFailureCount": 238,
"attributableFailureCount": 239,
"decisionFailureRate": 0.9958,
"decisionSuccessRate": 0.0042,
"decisionTotal": 239,
"decisionTotal": 240,
"failureBreakdown": {
"ambiguous_runtime": 172,
"backend_operator": 31,
"backend_operator": 32,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
"model_load": 18,
@@ -2332,14 +2332,14 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 435,
"failureCount": 436,
"failureRate": 0.9977,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0023,
"total": 436,
"total": 437,
"unresolvedFailureCount": 196
},
"vllm-mlu": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T13:55:41.102757+00:00",
"generatedAt": "2026-09-10T14:29:51.875466+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2650,27 +2650,27 @@
"unresolvedFailureCount": 86
},
"MetaX_c-500": {
"attributableFailureCount": 44,
"decisionFailureRate": 0.8148,
"decisionSuccessRate": 0.1852,
"decisionTotal": 54,
"attributableFailureCount": 45,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 55,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 25,
"backend_operator": 26,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 116,
"failureRate": 0.9206,
"failureCount": 117,
"failureRate": 0.9213,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0794,
"total": 126,
"successRate": 0.0787,
"total": 127,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -3545,14 +3545,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"backend_operator": 1
"backend_operator": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma2",
@@ -3564,7 +3564,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
@@ -6404,6 +6404,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|gemma2|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|gemma2|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7099,16 +7123,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1594,
"totalRecords": 1681,
"terminalRecords": 1595,
"totalRecords": 1682,
"totals": {
"attributableFailureCount": 418,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 469,
"attributableFailureCount": 419,
"decisionFailureRate": 0.8915,
"decisionSuccessRate": 0.1085,
"decisionTotal": 470,
"failureBreakdown": {
"ambiguous_runtime": 351,
"backend_operator": 38,
"backend_operator": 39,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 48,
@@ -7119,21 +7143,21 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1543,
"failureCount": 1544,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.032,
"total": 1594,
"total": 1595,
"unresolvedFailureCount": 1122
},
"warnings": [
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7141,7 +7165,7 @@
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7162,6 +7186,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1681,
"summarizedRecords": 1682,
"version": 1
}

1081
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1148
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

4
ledger/submissions.jsonl
View File

@@ -401,9 +401,7 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-09T00:13:45.027681+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730589", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-09T00:13:45.019303+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730588", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-09T00:13:45.021813+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730584", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-09T00:13:45.142420+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730593", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-09T00:13:45.146237+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730594", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-09T00:13:45.155081+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730595", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-09T00:13:45.139430+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730592", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-09T00:13:45.141151+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730591", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-09T02:14:39.291294+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4732363", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
@@ -587,6 +585,8 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.824770+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729512", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.913002+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729521", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-08T23:02:52.084632+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729528", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-09T00:13:45.142420+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730593", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-09T00:13:45.155081+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730595", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-05T13:47:55.466466+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649912", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-06T15:28:09.684321+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669863", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-08T06:46:11.531728+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712811", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}

22
manifest.json
View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "c4562257b498db2debcdc3e330627909b08a6ff7c9b57836e74fe5ed99ff5f67",
".modelhub_state/architecture_history_backfill.json": "0d96a0132f27c8ea17d7d8b1e50ad1e1c03dd3ef5167e9e136e734e8a186616d",
".modelhub_state/market_intelligence.json": "91f8a33be64783d3d0d2ee176062cc30721867291006b8394eac2cc153a72b62",
".modelhub_state/official_capabilities.json": "1b5a2e44c4742e4d2cb5f4de0f31609f58a2ae0c09ee12e33e76248a7ed376b7",
".modelhub_state/outcome_checkpoint.json": "d79ff94dd9fec12a5a24b8e266d0495598f6e28e81ba9e6cc1a21f22ed64138e",
".modelhub_state/architecture_compatibility_blacklist.json": "a599ade62419f03c62da027d70438bca8a801969858fa9bf973ca33039e3790f",
".modelhub_state/architecture_history_backfill.json": "67d0268dd2d6de6ea17a24b92daf36e6b8c0e6d347ed2d13fc509a3304242fff",
".modelhub_state/market_intelligence.json": "a4f1b302360e73858ee60446d649fd03c6261e3b1d20940a9c88dcfd198bc48e",
".modelhub_state/official_capabilities.json": "21f6cde77764b581b601ecf2d7cdb680896dd9f894d02774807ca672d620c1b5",
".modelhub_state/outcome_checkpoint.json": "604f294555cb52386bf53b427e93234b3955d0ec0630748784fc337fb8706afb",
".modelhub_state/queue_cleanup_latest.json": "a596175137b8adfa14ee62a71c9a7bc915b25b1d8f0f57451a25c2e257396039",
".modelhub_state/recent_outcomes.jsonl": "4da993fbb735ac37a77285e48f6ba2899ccd6e04775137b67015e8410168648a",
".modelhub_state/recovery_active_tasks.jsonl": "1c1ef245595bf4da7c9947523ff40f4f1722751185bae6477aa79d5d1bd5eac9",
".modelhub_state/recovery_intents.jsonl": "c6e027a9254441d06380300c8ae0b6392452a16a4332671ca89e491f96749cdc",
".modelhub_state/recovery_active_tasks.jsonl": "ac3731511436d5f430369af8ed00e95eee8ee18789b4c8694b2565722183cb2c",
".modelhub_state/recovery_intents.jsonl": "e8d63888bd85ab305ea79e0d6ff3667ea1bf066a5fcb1a9517bc313089f3df9c",
".modelhub_state/routing_intelligence.json": "5d6f745d56b69f23b3cfad9a5bd343a36b4b56bb8553dea7bb11d7a023d2b106",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "a114c86de719ef4f35af3b38699e542753aee282ea563e9b4b5a5edead3f00fa",
"outcomes/submissions.jsonl": "c1cee63001661cbc379d2496fc578e14d35bca918b8ddd8e05593281c69f1652"
"ledger/submissions.jsonl": "58bf6d711e7a9c6f8e32e7c0843583ffc5e1e3f4eaf13714b730af7e926823c0",
"outcomes/submissions.jsonl": "0c53e66ec3b34c32bae79f736ffe2ee1c1a4b88e2e95757f18f5fd18b1c4caea"
},
"generation": 5204,
"generation": 5205,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T14:28:50.969214+00:00",
"updatedAt": "2026-09-10T14:31:42.354896+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}

5
outcomes/submissions.jsonl
View File

@@ -175,7 +175,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:39:38.309054+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:38:16.005175+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4661079", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:08:06.614699+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"backend_operator": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T10:14:38.509276+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:06:36.456528+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661426", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:08:06.614723+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:06:36.493823+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661437", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:36:29.362958+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367933, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367933}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:34:20.120418+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661809", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T14:42:01.034713+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T06:30:19.979390+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4662535", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-06T15:03:37.399221+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:02:35.712857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4662918", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-06T15:18:32.207677+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:17:44.185498+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4663094", "taskType": "text-generation", "verifyResult": null}
@@ -560,8 +559,8 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:13:15.207804+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:12:56.897964+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754370", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:13:15.207812+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:12:56.900331+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754369", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:13:15.207818+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:12:56.905628+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754371", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9ee85a9702ae695242c8b5436b1b856292d4a16c2f839d36bf93fbe98fb66d4e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:28:56.145522+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:28:56.134725+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754659", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T14:29:51.626225+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9ee85a9702ae695242c8b5436b1b856292d4a16c2f839d36bf93fbe98fb66d4e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:28:56.145522+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:29:51.626244+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:28:56.134725+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754659", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:30:53.020882+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754721", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:30:53.025848+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754722", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T06:38:16.883366+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754820", "taskType": "text-generation", "verifyResult": null}