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

state: generation 11388 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 10:09:20 +00:00
parent 0d4a0e18b2
commit 94deb27af1
8 changed files with 1819 additions and 1794 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2652,7 +2652,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T10:05:14.085772+00:00",
"generatedAt": "2026-09-21T10:09:10.871832+00:00",
"summary": {
"activeBlockCount": 133,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T10:08:07.874184+00:00",
"generatedAt": "2026-09-21T10:09:19.688955+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T10:08:07.874184+00:00",
"catalogUpdatedAt": "2026-09-21T10:09:19.688955+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T10:08:07.874184+00:00",
"generatedAt": "2026-09-21T10:09:19.688955+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6520,6 +6520,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T10:08:07.874184+00:00",
"taskTreeUpdatedAt": "2026-09-21T10:09:19.688955+00:00",
"version": 1
}

143
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T10:05:14.010504+00:00",
"lastSyncTime": "2026-09-21T10:05:11.455599+00:00",
"generatedAt": "2026-09-21T10:09:10.804379+00:00",
"lastSyncTime": "2026-09-21T10:09:08.998398+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2956,16 +2956,17 @@
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 21,
"attributableFailureCount": 22,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 21,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 31,
"ambiguous_runtime": 32,
"framework_architecture_unsupported": 21,
"platform_infrastructure": 1
"platform_infrastructure": 1,
"repository_structure": 1
},
"failureCount": 53,
"failureCount": 55,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -2975,8 +2976,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 53,
"unresolvedFailureCount": 31
"total": 55,
"unresolvedFailureCount": 32
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 201,
@@ -5441,32 +5442,33 @@
"unresolvedFailureCount": 158
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 61,
"decisionFailureRate": 0.9683,
"decisionSuccessRate": 0.0317,
"decisionTotal": 63,
"attributableFailureCount": 62,
"decisionFailureRate": 0.9688,
"decisionSuccessRate": 0.0312,
"decisionTotal": 64,
"failureBreakdown": {
"ambiguous_runtime": 53,
"ambiguous_runtime": 54,
"context_length": 1,
"framework_architecture_unsupported": 56,
"memory_capacity": 1,
"model_load": 2,
"platform_infrastructure": 1,
"repository_structure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 19
},
"failureCount": 134,
"failureRate": 0.9853,
"failureCount": 136,
"failureRate": 0.9855,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0147,
"total": 136,
"unresolvedFailureCount": 72
"successRate": 0.0145,
"total": 138,
"unresolvedFailureCount": 73
}
},
"generatedAt": "2026-09-21T10:05:13.998246+00:00",
"generatedAt": "2026-09-21T10:09:10.794071+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5495,32 +5497,32 @@
"unresolvedFailureCount": 149
},
"Ascend_910-b4": {
"attributableFailureCount": 316,
"decisionFailureRate": 0.836,
"decisionSuccessRate": 0.164,
"decisionTotal": 378,
"attributableFailureCount": 317,
"decisionFailureRate": 0.8364,
"decisionSuccessRate": 0.1636,
"decisionTotal": 379,
"failureBreakdown": {
"ambiguous_runtime": 163,
"ambiguous_runtime": 164,
"context_length": 1,
"framework_architecture_unsupported": 175,
"memory_capacity": 18,
"model_load": 85,
"platform_infrastructure": 2,
"repository_structure": 27,
"repository_structure": 28,
"tokenizer_compatibility": 10,
"参数/模板问题": 262,
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 932,
"failureRate": 0.9376,
"failureCount": 934,
"failureRate": 0.9378,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 62,
"successRate": 0.0624,
"total": 994,
"unresolvedFailureCount": 614
"successRate": 0.0622,
"total": 996,
"unresolvedFailureCount": 615
},
"Biren_166m": {
"attributableFailureCount": 182,
@@ -6824,9 +6826,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "lfm2",
@@ -6838,8 +6840,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq": {
"attributableFailureCount": 0,
@@ -6934,14 +6936,15 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|mpt|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 1,
"repository_structure": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "mpt",
@@ -6953,7 +6956,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|muse_glimmer|none": {
@@ -21060,9 +21063,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 29,
@@ -21075,8 +21078,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|30": {
"attributableFailureCount": 0,
@@ -21318,6 +21321,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|mpt|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -33495,15 +33522,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16209,
"totalRecords": 16392,
"terminalRecords": 16211,
"totalRecords": 16394,
"totals": {
"attributableFailureCount": 5864,
"attributableFailureCount": 5865,
"decisionFailureRate": 0.8615,
"decisionSuccessRate": 0.1385,
"decisionTotal": 6807,
"decisionTotal": 6808,
"failureBreakdown": {
"ambiguous_runtime": 3911,
"ambiguous_runtime": 3912,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -33512,38 +33539,38 @@
"memory_capacity": 1197,
"model_load": 495,
"platform_infrastructure": 924,
"repository_structure": 735,
"repository_structure": 736,
"runtime_memory": 84,
"tokenizer_compatibility": 660,
"参数/模板问题": 3174,
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15266,
"failureCount": 15268,
"failureRate": 0.9418,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 924,
"successCount": 943,
"successRate": 0.0582,
"total": 16209,
"unresolvedFailureCount": 8478
"total": 16211,
"unresolvedFailureCount": 8479
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-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 Ascend_910-b3 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|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|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -33583,6 +33610,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16392,
"summarizedRecords": 16394,
"version": 1
}

1334
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2032
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.20.2",
"checksums": {
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
".modelhub_state/architecture_compatibility_blacklist.json": "1a8931a0c81a60e06cb37207e46b8c859917ed6ecc689b457d3734dd877e7484",
".modelhub_state/architecture_compatibility_blacklist.json": "c68eedaa954b73d16734f98c2dbf63f73490805f498c2d941b65c0bd2ebb5e61",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "43d9486e6847dbab90175a46197d0f1e3d733f68ae3b07a57216c6e16a86b7bb",
".modelhub_state/official_capabilities.json": "b9168154495cde8cbb1b85d8d15ad11418fc11cbdaa51dd07f8d9dbb8b4a377c",
".modelhub_state/outcome_checkpoint.json": "6a85314b855a7379636957e38c2a203dcfaa1fd7b651132d52f51e972add48f2",
".modelhub_state/market_intelligence.json": "385a043de2624de011e9317b27ed3fb61675a46ba26ad8473245270cd1635a8c",
".modelhub_state/official_capabilities.json": "109d1fb54c5d1db4c8fc4d56dfe33db1cad160029f4dd0d25635296b3e2df8d7",
".modelhub_state/outcome_checkpoint.json": "5bd412a03af1724f4dbed0cb64f76c6b95dc5693a1c157bef9a76b3412e726d1",
".modelhub_state/queue_cleanup_latest.json": "f4afc5dbbf57b883780778e798518d72ad1770b7d52c2f9efa7ac7bca07813f7",
".modelhub_state/recent_outcomes.jsonl": "4048d7521696df671c525091f8381c845004f134c14b71c03c52b03a037590ac",
".modelhub_state/recovery_active_tasks.jsonl": "2a8614934866717c284167d475c31036aacb7143c15ff60fb65793ad8b97159b",
".modelhub_state/recovery_intents.jsonl": "7578ac402259ba273df2c6c37f7a7e02fc9b1fcb290de72bdc1b3999820ffbc0",
".modelhub_state/recovery_active_tasks.jsonl": "5dc0eddaa7e406049d8d3fbd1851557b549e68dc15948ddf6b589f2c52a9700d",
".modelhub_state/recovery_intents.jsonl": "929e688316743124ec44d065e1f2f2447d211c315cc4e25e63d03f9f27dc4233",
".modelhub_state/routing_intelligence.json": "b74967b2f36e5e3e4ccf187ed4919ab22f86e688d61337513590a4e2d68e45cb",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "12e5a0e74212526ca79a9b5eddf218e65037c277fe261ab92e906ba00cf292bf",
"outcomes/submissions.jsonl": "020ed5cf53e2d8cf979d3f03b423204594635b24d296a03721e57c11189e7c76"
"outcomes/submissions.jsonl": "65504d42ffa3eb7befbd82a751c9b4f036388e9d2f25b7a36517a6c4837fd9c1"
},
"generation": 11387,
"generation": 11388,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-21T10:08:08.322746+00:00",
"updatedAt": "2026-09-21T10:09:20.736936+00:00",
"writerId": "8b35139af6674067a339a670222d4b67"
}

76
outcomes/submissions.jsonl
View File

@@ -391,7 +391,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-20T11:00:25.647717+00:00", "modelId": "chenqi2026/7a-8elite", "modelProfile": {"architectures": [], "configFingerprint": "48d3a9b2a54c7767b8326d72b3ed023e1469b86b36badd5ea46d40b3b79e65cd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 89208224, "estimatedRequiredGiB": 3.907, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3496327232, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 79009792, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3496327232}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:43.741402+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4968996", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647473+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:43.835992+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969002", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647845+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.837922+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969007", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647697+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.036416+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969019", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647426+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.038289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969018", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647557+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.040710+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969021", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647466+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.140009+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969028", "taskType": "text-generation", "verifyResult": null}
@@ -411,7 +410,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647652+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-8B-R", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556344, "estimatedRequiredGiB": 17.97, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16079585018, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16079585018}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.306108+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969091", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766271+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.490200+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969296", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766176+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "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": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.550122+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969304", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766067+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.548946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969298", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766490+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.553586+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969305", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766011+00:00", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.536035+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969297", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766123+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.551543+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969307", "taskType": "text-generation", "verifyResult": null}
@@ -993,43 +991,43 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:58:02.958201+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:54:23.235347+00:00", "targetGpu": "Biren_166m", "taskId": "4991515", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:01:37.498148+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:57:56.851808+00:00", "targetGpu": "Biren_166m", "taskId": "4991645", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T10:05:11.455577+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:02:02.598580+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991686", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:04:12.536952+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221450, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221450}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:32.701292+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991785", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 2018195467}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:32.882713+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991786", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-09-20T20:49:19.683371+00:00", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:33.047437+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991787", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:33.273419+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4991788", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457676, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457676}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:33.446694+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4991789", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093204103, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093204103}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:33.575630+00:00", "targetGpu": "Biren_166m", "taskId": "4991794", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626643, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626643}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:46.596390+00:00", "targetGpu": "Biren_166m", "taskId": "4991795", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786187, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786187}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:46.713745+00:00", "targetGpu": "Biren_166m", "taskId": "4991796", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:46.809974+00:00", "targetGpu": "Biren_166m", "taskId": "4991797", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:46.910778+00:00", "targetGpu": "Biren_166m", "taskId": "4991798", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24651300904, "estimatedRequiredGiB": 27.587, "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": 24684544516, "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": "gptq", "repositoryOnDiskBytes": 24684544516}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:47.007073+00:00", "targetGpu": "Biren_166m", "taskId": "4991801", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:00.640183+00:00", "targetGpu": "Biren_166m", "taskId": "4991802", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:00.755826+00:00", "targetGpu": "Biren_166m", "taskId": "4991803", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:00.861090+00:00", "targetGpu": "Biren_166m", "taskId": "4991804", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:00.958470+00:00", "targetGpu": "Biren_166m", "taskId": "4991805", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:01.066580+00:00", "targetGpu": "Biren_166m", "taskId": "4991806", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:13.065520+00:00", "targetGpu": "Biren_166m", "taskId": "4991807", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261800, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261800}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:13.182758+00:00", "targetGpu": "Biren_166m", "taskId": "4991808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858540940}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:13.292272+00:00", "targetGpu": "Biren_166m", "taskId": "4991809", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:13.409394+00:00", "targetGpu": "Biren_166m", "taskId": "4991810", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:13.509125+00:00", "targetGpu": "Biren_166m", "taskId": "4991811", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "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": 6768615358}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:13.631792+00:00", "targetGpu": "Biren_166m", "taskId": "4991818", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "pending", "submitTime": "2026-09-21T02:08:28.213255+00:00", "targetGpu": "Biren_166m", "taskId": "4991819", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:28.316169+00:00", "targetGpu": "Biren_166m", "taskId": "4991820", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:28.408499+00:00", "targetGpu": "Biren_166m", "taskId": "4991821", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:28.519960+00:00", "targetGpu": "Biren_166m", "taskId": "4991822", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:28.643120+00:00", "targetGpu": "Biren_166m", "taskId": "4991827", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:43.018017+00:00", "targetGpu": "Biren_166m", "taskId": "4991828", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "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": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:43.110856+00:00", "targetGpu": "Biren_166m", "taskId": "4991829", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29274355224, "estimatedRequiredGiB": 32.761, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 29314389092, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 29314389092}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:43.206324+00:00", "targetGpu": "Biren_166m", "taskId": "4991830", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:43.311478+00:00", "targetGpu": "Biren_166m", "taskId": "4991831", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:43.406886+00:00", "targetGpu": "Biren_166m", "taskId": "4991841", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:56.660493+00:00", "targetGpu": "Biren_166m", "taskId": "4991842", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:56.744772+00:00", "targetGpu": "Biren_166m", "taskId": "4991843", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:56.833801+00:00", "targetGpu": "Biren_166m", "taskId": "4991844", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:56.940233+00:00", "targetGpu": "Biren_166m", "taskId": "4991845", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998391+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:04:12.536952+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T10:09:08.998272+00:00", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221450, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221450}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:32.701292+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991785", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T10:09:08.998266+00:00", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 2018195467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:32.882713+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991786", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T10:09:08.998259+00:00", "modelId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-09-20T20:49:19.683371+00:00", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:33.047437+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991787", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:09:08.998253+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:33.273419+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4991788", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:09:08.998247+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457676, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457676}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:33.446694+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4991789", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998331+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093204103, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093204103}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:33.575630+00:00", "targetGpu": "Biren_166m", "taskId": "4991794", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998325+00:00", "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626643, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626643}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:46.596390+00:00", "targetGpu": "Biren_166m", "taskId": "4991795", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998319+00:00", "modelId": "neuralmagic/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786187, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786187}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:46.713745+00:00", "targetGpu": "Biren_166m", "taskId": "4991796", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998312+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:46.809974+00:00", "targetGpu": "Biren_166m", "taskId": "4991797", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998306+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:46.910778+00:00", "targetGpu": "Biren_166m", "taskId": "4991798", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998300+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24651300904, "estimatedRequiredGiB": 27.587, "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": 24684544516, "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": "gptq", "repositoryOnDiskBytes": 24684544516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:07:47.007073+00:00", "targetGpu": "Biren_166m", "taskId": "4991801", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998295+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:00.640183+00:00", "targetGpu": "Biren_166m", "taskId": "4991802", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998289+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:00.755826+00:00", "targetGpu": "Biren_166m", "taskId": "4991803", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998284+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:00.861090+00:00", "targetGpu": "Biren_166m", "taskId": "4991804", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998278+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:00.958470+00:00", "targetGpu": "Biren_166m", "taskId": "4991805", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998226+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:01.066580+00:00", "targetGpu": "Biren_166m", "taskId": "4991806", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998220+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.065520+00:00", "targetGpu": "Biren_166m", "taskId": "4991807", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998213+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261800, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261800}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.182758+00:00", "targetGpu": "Biren_166m", "taskId": "4991808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998207+00:00", "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858540940}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.292272+00:00", "targetGpu": "Biren_166m", "taskId": "4991809", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998201+00:00", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.409394+00:00", "targetGpu": "Biren_166m", "taskId": "4991810", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998195+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.509125+00:00", "targetGpu": "Biren_166m", "taskId": "4991811", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998386+00:00", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "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": 6768615358}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.631792+00:00", "targetGpu": "Biren_166m", "taskId": "4991818", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998381+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-09-21T02:08:28.213255+00:00", "targetGpu": "Biren_166m", "taskId": "4991819", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998375+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:28.316169+00:00", "targetGpu": "Biren_166m", "taskId": "4991820", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998369+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:28.408499+00:00", "targetGpu": "Biren_166m", "taskId": "4991821", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998364+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:28.519960+00:00", "targetGpu": "Biren_166m", "taskId": "4991822", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998359+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:28.643120+00:00", "targetGpu": "Biren_166m", "taskId": "4991827", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998354+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:43.018017+00:00", "targetGpu": "Biren_166m", "taskId": "4991828", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998348+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "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": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:43.110856+00:00", "targetGpu": "Biren_166m", "taskId": "4991829", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998343+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29274355224, "estimatedRequiredGiB": 32.761, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 29314389092, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 29314389092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:43.206324+00:00", "targetGpu": "Biren_166m", "taskId": "4991830", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998337+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:43.311478+00:00", "targetGpu": "Biren_166m", "taskId": "4991831", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998187+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:43.406886+00:00", "targetGpu": "Biren_166m", "taskId": "4991841", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998179+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:56.660493+00:00", "targetGpu": "Biren_166m", "taskId": "4991842", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998172+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:56.744772+00:00", "targetGpu": "Biren_166m", "taskId": "4991843", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998162+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:56.833801+00:00", "targetGpu": "Biren_166m", "taskId": "4991844", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998136+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:56.940233+00:00", "targetGpu": "Biren_166m", "taskId": "4991845", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:08:57.053681+00:00", "targetGpu": "Biren_166m", "taskId": "4991846", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 968080210, "estimatedRequiredGiB": 1.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 979581804, "modelscopeLicense": "apache-2.0", "modelscopeParams": 268944384, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:coder", "custom_tag:lora", "custom_tag:code", "custom_tag:lychee", "custom_tag:finetune", "custom_tag:multilingual"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 979581804}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:09:08.424925+00:00", "targetGpu": "Biren_166m", "taskId": "4991847", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "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": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:09:08.530131+00:00", "targetGpu": "Biren_166m", "taskId": "4991848", "taskType": "text-generation", "verifyResult": null}