state: generation 20428 (cycle)

This commit is contained in:
2026-10-04 12:55:01 +00:00
parent 4ed6179be7
commit 885aa13a53
8 changed files with 1428 additions and 1406 deletions

View File

@@ -3299,7 +3299,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-04T12:39:49.242111+00:00",
"generatedAt": "2026-10-04T12:52:46.984506+00:00",
"summary": {
"activeBlockCount": 166,
"byGpuFramework": {

View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-04T12:51:32.966353+00:00",
"generatedAt": "2026-10-04T12:54:43.351533+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-04T12:51:32.966353+00:00",
"catalogUpdatedAt": "2026-10-04T12:54:43.351533+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-04T12:51:32.966353+00:00",
"generatedAt": "2026-10-04T12:54:43.351533+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6557,6 +6557,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-04T12:51:32.966353+00:00",
"taskTreeUpdatedAt": "2026-10-04T12:54:43.351533+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-04T11:49:17.442446+00:00",
"lastSyncTime": "2026-10-04T11:49:17.148112+00:00",
"generatedAt": "2026-10-04T12:52:46.902801+00:00",
"lastSyncTime": "2026-10-04T12:52:46.641112+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2070,29 +2070,6 @@
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
},
"iluvatar_bi-150|vllm|text-generation|model_type:mellum": {
"architectureSignature": "model_type:mellum",
"architectures": [],
"evidenceCount": 3,
"expiresAt": "2026-10-04T12:07:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-04T12:07:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mellum",
"sourceModelIds": [
"JetBrains/Mellum2-12B-A2.5B-Thinking-SFT",
"JetBrains/Mellum2-12B-A2.5B-Instruct",
"JetBrains/Mellum2-12B-A2.5B-Thinking"
],
"sourceTaskIds": [
"4152671",
"4152323",
"4152351"
],
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
},
"iluvatar_bi-150|vllm|text-generation|model_type:nemotron_h": {
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
@@ -3327,7 +3304,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 167,
"activeBlockCount": 166,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -3340,7 +3317,7 @@
"Cambricon_mlu-370-x8|vllm-customized": 6,
"Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|transformers": 5,
"Iluvatar_bi-150|vllm": 7,
"Iluvatar_bi-150|vllm": 6,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
"Iluvatar_bi-150|vllm_tokenizer_patch": 2,
"Kunlunxin_p-800|vllm": 10,
@@ -3450,25 +3427,25 @@
"decisionSuccessRate": 0.0816,
"decisionTotal": 49,
"failureBreakdown": {
"ambiguous_runtime": 89,
"ambiguous_runtime": 90,
"context_length": 9,
"framework_architecture_unsupported": 35,
"memory_capacity": 1,
"platform_infrastructure": 1,
"参数/模板问题": 8
},
"failureCount": 143,
"failureRate": 0.9728,
"failureCount": 144,
"failureRate": 0.973,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0272,
"successRate": 0.027,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 147,
"unresolvedFailureCount": 97
"total": 148,
"unresolvedFailureCount": 98
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 71,
@@ -4915,27 +4892,27 @@
"unresolvedFailureCount": 57
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.6364,
"decisionSuccessRate": 0.3636,
"decisionTotal": 44,
"attributableFailureCount": 29,
"decisionFailureRate": 0.6444,
"decisionSuccessRate": 0.3556,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 24,
"framework_architecture_unsupported": 25,
"model_load": 3,
"tokenizer_compatibility": 1
},
"failureCount": 40,
"failureRate": 0.7143,
"failureCount": 41,
"failureRate": 0.7193,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 16,
"successRate": 0.2857,
"successRate": 0.2807,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 56,
"total": 57,
"unresolvedFailureCount": 12
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -6024,17 +6001,17 @@
"unresolvedFailureCount": 6476
},
"vllm": {
"attributableFailureCount": 3652,
"attributableFailureCount": 3653,
"decisionFailureRate": 0.9726,
"decisionSuccessRate": 0.0274,
"decisionTotal": 3755,
"decisionTotal": 3756,
"failureBreakdown": {
"ambiguous_runtime": 1597,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 93,
"context_length": 161,
"framework_architecture_unsupported": 1378,
"framework_architecture_unsupported": 1379,
"memory_capacity": 725,
"model_load": 224,
"platform_infrastructure": 876,
@@ -6043,14 +6020,14 @@
"tokenizer_compatibility": 420,
"参数/模板问题": 50
},
"failureCount": 6175,
"failureCount": 6176,
"failureRate": 0.9836,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 876,
"successCount": 103,
"successRate": 0.0164,
"total": 6278,
"total": 6279,
"unresolvedFailureCount": 1647
},
"vllm-customized": {
@@ -6178,7 +6155,7 @@
"decisionSuccessRate": 0.0637,
"decisionTotal": 157,
"failureBreakdown": {
"ambiguous_runtime": 203,
"ambiguous_runtime": 204,
"backend_operator": 15,
"context_length": 9,
"framework_architecture_unsupported": 90,
@@ -6190,18 +6167,18 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 29
},
"failureCount": 382,
"failureRate": 0.9745,
"failureCount": 383,
"failureRate": 0.9746,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 10,
"successRate": 0.0255,
"total": 392,
"unresolvedFailureCount": 232
"successRate": 0.0254,
"total": 393,
"unresolvedFailureCount": 233
}
},
"generatedAt": "2026-10-04T11:49:17.393864+00:00",
"generatedAt": "2026-10-04T12:52:46.890180+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 117,
@@ -6209,7 +6186,7 @@
"decisionSuccessRate": 0.1583,
"decisionTotal": 139,
"failureBreakdown": {
"ambiguous_runtime": 158,
"ambiguous_runtime": 159,
"context_length": 9,
"framework_architecture_unsupported": 102,
"memory_capacity": 2,
@@ -6220,15 +6197,15 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 346,
"failureRate": 0.9402,
"failureCount": 347,
"failureRate": 0.9404,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.0598,
"total": 368,
"unresolvedFailureCount": 228
"successRate": 0.0596,
"total": 369,
"unresolvedFailureCount": 229
},
"Ascend_910-b4": {
"attributableFailureCount": 329,
@@ -6397,16 +6374,16 @@
"unresolvedFailureCount": 1165
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 978,
"decisionFailureRate": 0.8468,
"decisionSuccessRate": 0.1532,
"decisionTotal": 1155,
"attributableFailureCount": 979,
"decisionFailureRate": 0.8469,
"decisionSuccessRate": 0.1531,
"decisionTotal": 1156,
"failureBreakdown": {
"ambiguous_runtime": 352,
"architecture_compatibility": 47,
"backend_operator": 1,
"context_length": 77,
"framework_architecture_unsupported": 296,
"framework_architecture_unsupported": 297,
"memory_capacity": 219,
"model_load": 87,
"platform_infrastructure": 7,
@@ -6417,14 +6394,14 @@
"日志缺失": 6,
"验证失败": 47
},
"failureCount": 1706,
"failureRate": 0.906,
"failureCount": 1707,
"failureRate": 0.9061,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 177,
"successRate": 0.094,
"total": 1883,
"successRate": 0.0939,
"total": 1884,
"unresolvedFailureCount": 721
},
"Kunlunxin_p-800": {
@@ -6871,6 +6848,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "k2_horizon",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -17738,14 +17738,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 4,
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"framework_architecture_unsupported": 4
"framework_architecture_unsupported": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5_moe",
@@ -17757,7 +17757,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|none": {
@@ -29191,6 +29191,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
"modelType": "k2_horizon",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -45698,14 +45722,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none|33": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
@@ -45718,7 +45742,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none|34": {
@@ -56549,20 +56573,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17287,
"totalRecords": 17511,
"terminalRecords": 17289,
"totalRecords": 17513,
"totals": {
"attributableFailureCount": 6204,
"attributableFailureCount": 6205,
"decisionFailureRate": 0.8641,
"decisionSuccessRate": 0.1359,
"decisionTotal": 7180,
"decisionTotal": 7181,
"failureBreakdown": {
"ambiguous_runtime": 4531,
"ambiguous_runtime": 4532,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 327,
"framework_architecture_unsupported": 2236,
"framework_architecture_unsupported": 2237,
"memory_capacity": 1206,
"model_load": 561,
"platform_infrastructure": 948,
@@ -56573,15 +56597,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16311,
"failureCount": 16313,
"failureRate": 0.9435,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 948,
"successCount": 976,
"successRate": 0.0565,
"total": 17287,
"unresolvedFailureCount": 9159
"total": 17289,
"unresolvedFailureCount": 9160
},
"warnings": [
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -56641,6 +56665,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17511,
"summarizedRecords": 17513,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "edecd2055648745a216fdd40bc25f3c2365f9d8cfa82f28cf35ef6213e3614af",
".modelhub_state/architecture_compatibility_blacklist.json": "d8082777ad2cabeedc5ddb481c2c9a3afef99ae9043f221343e03ed069f521e4",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "722f2cb1ed10d17172662fe7e45fc46d97817458689913ff3447f31ae7d27014",
".modelhub_state/official_capabilities.json": "7e118157493cf992ca90c9c558ed5b191d15e44dbe9c45e9f5f5444099c1679e",
".modelhub_state/outcome_checkpoint.json": "d3b1c94b09f1f25a88ec8109eff594e3cfa59e8b593a6dda958e9b63e12bfc4c",
".modelhub_state/market_intelligence.json": "7a15d3da2199d9f1f934e2b704cd15112024b5a32a29f8de19cfcc6d21fbafa6",
".modelhub_state/official_capabilities.json": "f470836ac28eea9dfa094d3791cc68d48412cfeb90e880942ab058cd4d3d5bd1",
".modelhub_state/outcome_checkpoint.json": "3919503c1300c650a10983fd8602c6a6f4ecd46e6994f4fbcf878b04ce703fed",
".modelhub_state/queue_cleanup_latest.json": "a7bce8642dd3f907a218a6359f2a867f82b8a265a7f1ea2c99631bdff194950f",
".modelhub_state/recent_outcomes.jsonl": "74684e0cb636f08121ef1ea1446e52ebb2f1891266683fdcded66873c8d76476",
".modelhub_state/recovery_active_tasks.jsonl": "2f4c4c30895f472406bcdd87e79cd289cef3eec68c5db29274d770fdd1c1613d",
".modelhub_state/recovery_intents.jsonl": "4c83a65be0f73be9be6f4442efe07876ca3922bcf485d77f3f664859bda2cb8c",
".modelhub_state/recovery_active_tasks.jsonl": "87822f17efb09b3ea79a8dde02a7ef1730644dfe76d1782d0b58f795f2e8728a",
".modelhub_state/recovery_intents.jsonl": "2d0222e6af53df57144efdc8f3471e621c85b282227ebaf5ef720908a6f93d04",
".modelhub_state/routing_intelligence.json": "46d123c1283f8ddc7b760ee11a007b1cb9cd850eec877013d71700b3f023d788",
".modelhub_state/submission_exclusions.jsonl": "8a533753b09639322718ffe59fad6a6f11e8cc3741d7be12085a149c97ca5507",
".modelhub_state/worker_crashes.jsonl": "50ffe2fb7a8d9d9967ff97b47af26f97753a0bbeae8a68113a221474751d9c2d",
"ledger/submissions.jsonl": "27f710b1752895d9dbf6e68f5c9d403b51fdb8ae8d69d3af4d966dbb3868ba4f",
"outcomes/submissions.jsonl": "1f18c34a16f65ebec84c2cc8c822ca9d13842ff185880c797a61d42cf5b37cb6"
"outcomes/submissions.jsonl": "c37c65b0454faf2e29179fc8967c0665dd6aa3bd657e99b2f88417f4ae68b06d"
},
"generation": 20427,
"generation": 20428,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-10-04T12:51:44.960968+00:00",
"updatedAt": "2026-10-04T12:55:01.420135+00:00",
"writerId": "2a476b5b64aa45219c00032efc0102bb"
}

View File

@@ -129,7 +129,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:21:25.658461+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-17T16:18:42.162554+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4918893", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:44:15.587030+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "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": "2026-09-17T16:34:57.137322+00:00", "targetGpu": "Vastai_va16", "taskId": "4919178", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T01:07:18.103258+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": 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": "2026-09-17T17:02:26.170226+00:00", "targetGpu": "Biren_166m", "taskId": "4919710", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-18T06:24:52.891825+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "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": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:21:10.450004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4923702", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-18T07:01:53.813894+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "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": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:55:35.549905+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4924043", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T10:35:01.790461+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "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": 13756989526, "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": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T02:29:42.495408+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4926623", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-18T16:22:07.716198+00:00", "modelId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8595477990, "estimatedRequiredGiB": 9.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "prism_hadamard_qwen35", "modelscopeFileSize": 8608734989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2589078768, "modelscopeTags": ["license:apache-2.0", "model_type:prism_hadamard_qwen35", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:mlx", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8608734989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T08:21:55.437762+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4931755", "taskType": "text-generation", "verifyResult": null}
@@ -142,7 +141,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T21:27:17.514867+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "d1bd75b85a2f7e3c48167c88ea99e7a0258a1c0018e9b3783b0dd8115ed250be", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T13:20:19.274818+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4935389", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T21:45:06.293065+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "20cb3c39f4c481f4f36a82f56d2790a08d35635571c54154d8414aa034539fdd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T13:40:31.530904+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4935565", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T22:02:17.790796+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "ec890c5fa72ce5b6a2dc821183a5c5a4672e35039ad1cfdbb4ec3edd6dfa8870", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T13:59:45.181269+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4935796", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-18T23:30:32.199117+00:00", "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T15:26:30.897319+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4936617", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-19T00:05:43.524382+00:00", "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T15:59:42.185316+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4936959", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:44:40.297028+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:41:55.617980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-19T03:01:51.490259+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:58:28.435554+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4938823", "taskType": "text-generation", "verifyResult": null}