diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 0831b554f0..6b74e46fc2 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -2850,7 +2850,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-21T20:29:48.864519+00:00", + "generatedAt": "2026-09-21T20:32:52.348993+00:00", "summary": { "activeBlockCount": 143, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 266b32dbd9..667d564104 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -434,7 +434,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-21T20:31:50.591990+00:00", + "generatedAt": "2026-09-21T20:33:06.808859+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 76f256c0c2..09bcb9d01c 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-21T20:31:50.591990+00:00", + "catalogUpdatedAt": "2026-09-21T20:33:06.808859+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-21T20:31:50.591990+00:00", + "generatedAt": "2026-09-21T20:33:06.808859+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6890,6 +6890,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-21T20:31:50.591990+00:00", + "taskTreeUpdatedAt": "2026-09-21T20:33:06.808859+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index cac905ea9b..47227c1b12 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-21T20:29:48.794296+00:00", - "lastSyncTime": "2026-09-21T20:29:48.458102+00:00", + "generatedAt": "2026-09-21T20:32:52.267273+00:00", + "lastSyncTime": "2026-09-21T20:32:51.958999+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2977,24 +2977,24 @@ "decisionSuccessRate": 0.0625, "decisionTotal": 32, "failureBreakdown": { - "ambiguous_runtime": 35, + "ambiguous_runtime": 36, "context_length": 3, "framework_architecture_unsupported": 26, "memory_capacity": 1, "参数/模板问题": 8 }, - "failureCount": 73, - "failureRate": 0.9733, + "failureCount": 74, + "failureRate": 0.9737, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 2, - "successRate": 0.0267, + "successRate": 0.0263, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 75, - "unresolvedFailureCount": 43 + "total": 76, + "unresolvedFailureCount": 44 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 68, @@ -5657,7 +5657,7 @@ "decisionSuccessRate": 0.0253, "decisionTotal": 79, "failureBreakdown": { - "ambiguous_runtime": 84, + "ambiguous_runtime": 85, "backend_operator": 1, "context_length": 3, "framework_architecture_unsupported": 66, @@ -5668,18 +5668,18 @@ "tokenizer_compatibility": 1, "参数/模板问题": 27 }, - "failureCount": 189, - "failureRate": 0.9895, + "failureCount": 190, + "failureRate": 0.9896, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 2, - "successRate": 0.0105, - "total": 191, - "unresolvedFailureCount": 111 + "successRate": 0.0104, + "total": 192, + "unresolvedFailureCount": 112 } }, - "generatedAt": "2026-09-21T20:29:48.783719+00:00", + "generatedAt": "2026-09-21T20:32:52.255753+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 99, @@ -5687,7 +5687,7 @@ "decisionSuccessRate": 0.161, "decisionTotal": 118, "failureBreakdown": { - "ambiguous_runtime": 96, + "ambiguous_runtime": 97, "context_length": 3, "framework_architecture_unsupported": 91, "memory_capacity": 2, @@ -5697,15 +5697,15 @@ "日志缺失": 3, "验证失败": 27 }, - "failureCount": 264, - "failureRate": 0.9329, + "failureCount": 265, + "failureRate": 0.9331, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.0671, - "total": 283, - "unresolvedFailureCount": 165 + "successRate": 0.0669, + "total": 284, + "unresolvedFailureCount": 166 }, "Ascend_910-b4": { "attributableFailureCount": 322, @@ -6325,10 +6325,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "ambiguous_runtime": 3, + "ambiguous_runtime": 4, "context_length": 1 }, - "failureCount": 4, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", @@ -6340,8 +6340,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 3 + "total": 5, + "unresolvedFailureCount": 4 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": { "attributableFailureCount": 0, @@ -21757,9 +21757,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 2 + "ambiguous_runtime": 3 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, @@ -21772,8 +21772,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": { "attributableFailureCount": 0, @@ -37980,15 +37980,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 16404, - "totalRecords": 16598, + "terminalRecords": 16405, + "totalRecords": 16599, "totals": { "attributableFailureCount": 5918, "decisionFailureRate": 0.8622, "decisionSuccessRate": 0.1378, "decisionTotal": 6864, "failureBreakdown": { - "ambiguous_runtime": 4031, + "ambiguous_runtime": 4032, "architecture_compatibility": 212, "attention_backend": 1, "backend_operator": 104, @@ -38004,31 +38004,31 @@ "日志缺失": 719, "验证失败": 674 }, - "failureCount": 15458, + "failureCount": 15459, "failureRate": 0.9423, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 925, "successCount": 946, "successRate": 0.0577, - "total": 16404, - "unresolvedFailureCount": 8615 + "total": 16405, + "unresolvedFailureCount": 8616 }, "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 Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "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。", @@ -38068,6 +38068,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 16598, + "summarizedRecords": 16599, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 535ae4c80d..1e75f2b1e5 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2295,6 +2295,9 @@ {"batchId": "de7be1887fb943db80077113aab19f7d", "completedAt": "2026-09-21T20:24:44.320851+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:24:42.392100+00:00", "framework": "vllm", "intentId": "deca3187fb0f43a19fb934467119fe0d", "lastModified": "2026-09-21T18:44:33+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "reason": null, "reconciledAt": "2026-09-21T20:30:04.074742+00:00", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5006850", "taskType": "text-generation"} {"batchId": "6e1c6ac73c394636a6a10fe3663125fa", "completedAt": "2026-09-21T20:26:44.867873+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:26:43.709790+00:00", "framework": "vllm", "intentId": "d3d3f1c1b5d34ddfbed9398607656dbe", "lastModified": "2026-09-21T18:45:44+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "reason": null, "reconciledAt": "2026-09-21T20:30:04.072528+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5006868", "taskType": "text-generation"} {"batchId": "1545959f472c4f22ac67465bf16884e9", "completedAt": "2026-09-21T20:29:00.532469+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:28:42.976465+00:00", "framework": "vllm", "intentId": "d9cb8728afe0483b86df5000c4fafb57", "lastModified": "2026-09-21T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "reason": null, "reconciledAt": "2026-09-21T20:30:04.073114+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5006904", "taskType": "text-generation"} +{"batchId": "cce5e92d1c4245ccaa9b0f47123ca463", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:33:07.585254+00:00", "framework": "vllm", "intentId": "58af8c4dd5cb48ff8c5c9e1e76692bc3", "lastModified": "2026-09-21T18:38:06+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "repoId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} +{"batchId": "cce5e92d1c4245ccaa9b0f47123ca463", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:33:07.585378+00:00", "framework": "vllm", "intentId": "7cbe83ffaa49416c88c2b422ffa1d101", "lastModified": "2026-09-21T18:27:55+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g32-v2_C", "repoId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} +{"batchId": "cce5e92d1c4245ccaa9b0f47123ca463", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:33:07.585441+00:00", "framework": "vllm", "intentId": "da0b0b58b85849e280a9e40b5e2cf571", "lastModified": "2026-09-21T18:32:18+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g64-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g64-v2_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691776+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.136949+00:00", "framework": "vllm", "intentId": "cff6b666a842431faf928f94c2086fdf", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 0d79ced0a3..b5148525e4 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.20.2", "checksums": { ".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f", - ".modelhub_state/architecture_compatibility_blacklist.json": "c95d68825ceb1b7ea42f076f269a263c541dbe1efbd30a11dbfce0cb62158082", + ".modelhub_state/architecture_compatibility_blacklist.json": "7e0073b1cb07a8f8690342919988d03b5c50afcca2af33781afd7ccbca6d0856", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "7df0b9d9aa7dd1226fbdefb03bd45e530bed083690db1fbd405c93de8365c502", - ".modelhub_state/official_capabilities.json": "bf49ae7ede86966c28da81d629e5b2576b627c99cc9413e888b668103d7aebd5", - ".modelhub_state/outcome_checkpoint.json": "44bc8c9ee35363d0ad41d5733758d0fc0d4188075deedc067970ef2257ab505e", + ".modelhub_state/market_intelligence.json": "e6a40c7bde9972caeec6e100ad4355fac7dd3885859674e3ac42b371ceb5506c", + ".modelhub_state/official_capabilities.json": "eb3e26a1b123b747e4c120b4adac3487021ba8ac1f87b26d4a2971734892b7c1", + ".modelhub_state/outcome_checkpoint.json": "592a31c0d08d7f22088ec613b44aa85bae7418141b936b7fde8d333e581e38ae", ".modelhub_state/queue_cleanup_latest.json": "f93bde2de8f7cc7073f34b5456a3df43c8f54023eacfce210dc11e227efd469c", ".modelhub_state/recent_outcomes.jsonl": "9e2a4dc46246785df8dffcbd4b6aea5cc0b32794af784e60d3a212af041c91c6", ".modelhub_state/recovery_active_tasks.jsonl": "edd0e779b6734e05bbb8b2c9c7a57e05b8913584b263248467ce2133c3f821c0", - ".modelhub_state/recovery_intents.jsonl": "d236f73446599d5b69f8a517dd97be16ffb3ccf8baba830b19257f1b54ce832d", + ".modelhub_state/recovery_intents.jsonl": "3fd15f0793fe896714f575de48521f33cfb864ecf0fdbdd638ac40335a1c3027", ".modelhub_state/routing_intelligence.json": "2cd79876e6a12531ba2735385756a6e9500176eb79d0a50ff9084bde74a581f2", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", "ledger/submissions.jsonl": "c3f26b5e027107d42662509dd24d6b293b5ce9acd38a0a9e3c525b7bf7bf354d", - "outcomes/submissions.jsonl": "a44b1d20f0dbfd2788ef03d385da58b8f27d5d471e33fdfa3f1905afd2fe1ee2" + "outcomes/submissions.jsonl": "65990c387eca2260373afe5b3b11e24b1790e5627a321a76820c360de9ec4f62" }, - "generation": 11716, - "phase": "cycle", + "generation": 11717, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-09-21T20:31:51.040823+00:00", + "updatedAt": "2026-09-21T20:33:07.756544+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index e97ece37e9..672fb94298 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -419,7 +419,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600240+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T03:24:23.730955+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969577", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600422+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:31.903313+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969626", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599992+00:00", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "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": 9093325064, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325064}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.042085+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969633", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600416+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.045316+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969632", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599928+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T03:25:32.137439+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969642", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600220+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.146902+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969640", "taskType": "text-generation", "verifyResult": null}