state: generation 10603 (cycle)
This commit is contained in:
@@ -1941,7 +1941,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T13:52:36.178562+00:00",
|
||||
"generatedAt": "2026-09-20T13:56:00.762635+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 94,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -425,7 +425,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T13:54:58.599106+00:00",
|
||||
"generatedAt": "2026-09-20T13:56:08.713912+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-20T13:54:58.599106+00:00",
|
||||
"catalogUpdatedAt": "2026-09-20T13:56:08.713912+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-20T13:54:58.599106+00:00",
|
||||
"generatedAt": "2026-09-20T13:56:08.713912+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6350,6 +6350,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-20T13:54:58.599106+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-20T13:56:08.713912+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T13:52:36.126026+00:00",
|
||||
"lastSyncTime": "2026-09-20T13:52:36.058476+00:00",
|
||||
"generatedAt": "2026-09-20T13:56:00.704058+00:00",
|
||||
"lastSyncTime": "2026-09-20T13:56:00.086520+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2241,10 +2241,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 11,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 16,
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 11
|
||||
},
|
||||
"failureCount": 27,
|
||||
"failureCount": 28,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -2254,8 +2254,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 27,
|
||||
"unresolvedFailureCount": 16
|
||||
"total": 28,
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 199,
|
||||
@@ -2360,27 +2360,27 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 33,
|
||||
"decisionFailureRate": 0.7021,
|
||||
"decisionSuccessRate": 0.2979,
|
||||
"decisionTotal": 47,
|
||||
"attributableFailureCount": 34,
|
||||
"decisionFailureRate": 0.7083,
|
||||
"decisionSuccessRate": 0.2917,
|
||||
"decisionTotal": 48,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 26,
|
||||
"model_load": 6,
|
||||
"model_load": 7,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 34,
|
||||
"failureRate": 0.7083,
|
||||
"failureCount": 35,
|
||||
"failureRate": 0.7143,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 14,
|
||||
"successRate": 0.2917,
|
||||
"successRate": 0.2857,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 48,
|
||||
"total": 49,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -4458,10 +4458,10 @@
|
||||
"unresolvedFailureCount": 6405
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3473,
|
||||
"attributableFailureCount": 3474,
|
||||
"decisionFailureRate": 0.9789,
|
||||
"decisionSuccessRate": 0.0211,
|
||||
"decisionTotal": 3548,
|
||||
"decisionTotal": 3549,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1429,
|
||||
"architecture_compatibility": 112,
|
||||
@@ -4470,21 +4470,21 @@
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1260,
|
||||
"memory_capacity": 720,
|
||||
"model_load": 197,
|
||||
"model_load": 198,
|
||||
"platform_infrastructure": 864,
|
||||
"repository_structure": 470,
|
||||
"runtime_memory": 60,
|
||||
"tokenizer_compatibility": 408,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5806,
|
||||
"failureCount": 5807,
|
||||
"failureRate": 0.9872,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 75,
|
||||
"successRate": 0.0128,
|
||||
"total": 5881,
|
||||
"total": 5882,
|
||||
"unresolvedFailureCount": 1469
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -4604,21 +4604,21 @@
|
||||
"decisionSuccessRate": 0.0741,
|
||||
"decisionTotal": 27,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 23,
|
||||
"ambiguous_runtime": 24,
|
||||
"framework_architecture_unsupported": 25
|
||||
},
|
||||
"failureCount": 48,
|
||||
"failureRate": 0.96,
|
||||
"failureCount": 49,
|
||||
"failureRate": 0.9608,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.04,
|
||||
"total": 50,
|
||||
"unresolvedFailureCount": 23
|
||||
"successRate": 0.0392,
|
||||
"total": 51,
|
||||
"unresolvedFailureCount": 24
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T13:52:36.117916+00:00",
|
||||
"generatedAt": "2026-09-20T13:56:00.696428+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 75,
|
||||
@@ -4651,7 +4651,7 @@
|
||||
"decisionSuccessRate": 0.1694,
|
||||
"decisionTotal": 366,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 144,
|
||||
"ambiguous_runtime": 145,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 164,
|
||||
"memory_capacity": 18,
|
||||
@@ -4663,28 +4663,28 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 892,
|
||||
"failureRate": 0.935,
|
||||
"failureCount": 893,
|
||||
"failureRate": 0.9351,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 62,
|
||||
"successRate": 0.065,
|
||||
"total": 954,
|
||||
"unresolvedFailureCount": 587
|
||||
"successRate": 0.0649,
|
||||
"total": 955,
|
||||
"unresolvedFailureCount": 588
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 171,
|
||||
"decisionFailureRate": 0.8769,
|
||||
"decisionSuccessRate": 0.1231,
|
||||
"decisionTotal": 195,
|
||||
"attributableFailureCount": 172,
|
||||
"decisionFailureRate": 0.8776,
|
||||
"decisionSuccessRate": 0.1224,
|
||||
"decisionTotal": 196,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 131,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 113,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 17,
|
||||
"model_load": 18,
|
||||
"platform_infrastructure": 2,
|
||||
"repository_structure": 18,
|
||||
"runtime_memory": 2,
|
||||
@@ -4693,14 +4693,14 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 607,
|
||||
"failureCount": 608,
|
||||
"failureRate": 0.962,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 24,
|
||||
"successRate": 0.038,
|
||||
"total": 631,
|
||||
"total": 632,
|
||||
"unresolvedFailureCount": 434
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -5412,6 +5412,29 @@
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|cohere2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "cohere2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -5688,6 +5711,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|gpt_oss|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -13464,6 +13510,30 @@
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|cohere2|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "cohere2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -13848,6 +13918,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|gpt_oss|compressed-tensors|35": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 35,
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -21845,22 +21939,22 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15857,
|
||||
"totalRecords": 15961,
|
||||
"terminalRecords": 15859,
|
||||
"totalRecords": 15963,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5753,
|
||||
"attributableFailureCount": 5754,
|
||||
"decisionFailureRate": 0.8619,
|
||||
"decisionSuccessRate": 0.1381,
|
||||
"decisionTotal": 6675,
|
||||
"decisionTotal": 6676,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3758,
|
||||
"ambiguous_runtime": 3759,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
"context_length": 318,
|
||||
"framework_architecture_unsupported": 1984,
|
||||
"memory_capacity": 1195,
|
||||
"model_load": 477,
|
||||
"model_load": 478,
|
||||
"platform_infrastructure": 922,
|
||||
"repository_structure": 734,
|
||||
"runtime_memory": 78,
|
||||
@@ -21869,15 +21963,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14935,
|
||||
"failureCount": 14937,
|
||||
"failureRate": 0.9419,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 922,
|
||||
"successRate": 0.0581,
|
||||
"total": 15857,
|
||||
"unresolvedFailureCount": 8260
|
||||
"total": 15859,
|
||||
"unresolvedFailureCount": 8261
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -21922,13 +22016,13 @@
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 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。",
|
||||
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 15961,
|
||||
"summarizedRecords": 15963,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "96f98c2368f03820cd232af40f676f968f8653bbb3fcd8e9ad98552db2c8fc99",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "0a21b57603ac1ef46c44153a8eede6e4dc7a45c8cc208509471b7a168f5e24bd",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "c81f12b28338b051f2da2817445bced87e390b26b7523437b2f69f63b642907b",
|
||||
".modelhub_state/official_capabilities.json": "3b8eb202d8a25886b8487bc000245ad9c1f1279fcc4fa67a04285aeb18b5bdec",
|
||||
".modelhub_state/outcome_checkpoint.json": "bc82ba9f9ef65953578b10d47c1a561845a36a2ea2348c428e3dba0c661589d6",
|
||||
".modelhub_state/market_intelligence.json": "803e7e616bb6ae09f3b5925455019a4fef09b0455397a8aabb9e3277607dd2b4",
|
||||
".modelhub_state/official_capabilities.json": "3902d6bb36a032c0a159e025ce551a102fd67fbf0fee44a83c6940f415e84cee",
|
||||
".modelhub_state/outcome_checkpoint.json": "4feb4ace3d90e4e92b4aaea832a3d87069aac1d949c85e824c8afe8708d3a32f",
|
||||
".modelhub_state/queue_cleanup_latest.json": "e2e00c2ff21d5b9199394746162ac123ed97a333c607f0af6c750af0b96ebf52",
|
||||
".modelhub_state/recent_outcomes.jsonl": "6973f12c807aad13e9919d00690216cc961734b6c02c5cb777c2686bd7109d80",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "13640bd8f187c83fe93fbf430dd95448303908d09aae5e2c9f80c913ee508a6e",
|
||||
".modelhub_state/recovery_intents.jsonl": "f53d22fe9e592f65670657dad5f4f1330dbca986e31affb563990a1f5aa2f150",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "9b75eb0119235a1233a8c30ee1c1682bd8249c17150f2bdf9ddb8dc46546b97e",
|
||||
".modelhub_state/recovery_intents.jsonl": "0704255cb4c7a29476af98e1b4c89ca9c91e57b0e8c6fce500888c4b5fc737f5",
|
||||
".modelhub_state/routing_intelligence.json": "ef7888b3a5c6f906d0062f4c5a1352705c0c3f30d32746f3048068cd9d20fa6b",
|
||||
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
|
||||
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
||||
"ledger/submissions.jsonl": "1f9d4360d881f61266ea982fc4e6f27a5b8132bd105bff1a3cdfbef3cd6f6890",
|
||||
"outcomes/submissions.jsonl": "0d5ee4f750333b3ea93eb51dd757e6f86eb897b07b90fac02abf2491f022edce"
|
||||
"outcomes/submissions.jsonl": "935978028e5b97665a7a29e72c8e55fd1072e9e46870e015e2a66e4bcfb39f58"
|
||||
},
|
||||
"generation": 10602,
|
||||
"generation": 10603,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-20T13:54:59.013891+00:00",
|
||||
"updatedAt": "2026-09-20T13:56:09.756887+00:00",
|
||||
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
||||
}
|
||||
|
||||
@@ -4,7 +4,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:14:29.722109+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:53:17.234593+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:04:36.601749+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:01:53.788146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4628814", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T23:24:55.604425+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:17:04.566515+00:00", "targetGpu": "Biren_166m", "taskId": "4629091", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-04T23:34:40.935439+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:32:11.649244+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4629295", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T00:55:08.690909+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:50:16.092995+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630839", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692571+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:16.665549+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632117", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -162,7 +161,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T14:13:15.207776+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "37bac6ce21d60134ebaca4c6569bab1151fd62af1ad962effbf472bc8bdbafbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:11:11.806743+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754342", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T14:29:51.626225+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9ee85a9702ae695242c8b5436b1b856292d4a16c2f839d36bf93fbe98fb66d4e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:28:56.145522+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:29:51.626244+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:28:56.134725+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754659", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:38:26.994284+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:38:16.883366+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754820", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:03:19.195695+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:56:12.042564+00:00", "targetGpu": "Vastai_va16", "taskId": "4755190", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009053+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.204766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755596", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009045+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.209710+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755597", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user