state: generation 8728 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -1741,7 +1741,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-17T12:17:56.938618+00:00",
+  "generatedAt": "2026-09-17T12:20:40.230305+00:00",
   "summary": {
     "activeBlockCount": 84,
     "byGpuFramework": {

.modelhub_state/architecture_history_backfill.json

@@ -11,7 +11,7 @@
     "1": {
       "complete": false,
       "lastError": "ModelHubAPIError: 系统错误",
-      "listingErrors": 638,
+      "listingErrors": 639,
       "nextPage": 1,
       "recordsScanned": 0,
       "uniqueRecords": 0
@@ -102,12 +102,12 @@
   "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
   "failureLogsInspected": 0,
   "mode": "incremental_decision_only",
-  "nextAccountIndex": 1,
+  "nextAccountIndex": 2,
   "recordsScanned": 0,
   "seenTaskIds": [],
   "startedAt": "2026-09-04T03:55:51.365685+00:00",
   "terminalRecords": 0,
   "uniqueRecords": 0,
-  "updatedAt": "2026-09-17T12:17:56.914702+00:00",
+  "updatedAt": "2026-09-17T12:20:40.205359+00:00",
   "version": 1
 }

.modelhub_state/market_intelligence.json

@@ -416,7 +416,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-17T12:16:00.922637+00:00",
+  "generatedAt": "2026-09-17T12:19:07.874503+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-17T12:01:22.158675+00:00",
+  "generatedAt": "2026-09-17T12:18:58.101013+00:00",
-  "lastSyncTime": "2026-09-17T12:01:19.615770+00:00",
+  "lastSyncTime": "2026-09-17T12:18:57.810959+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -2224,29 +2224,29 @@
         "unresolvedFailureCount": 32
       },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
-        "attributableFailureCount": 24,
+        "attributableFailureCount": 25,
-        "decisionFailureRate": 0.8571,
+        "decisionFailureRate": 0.8621,
-        "decisionSuccessRate": 0.1429,
+        "decisionSuccessRate": 0.1379,
-        "decisionTotal": 28,
+        "decisionTotal": 29,
         "failureBreakdown": {
           "ambiguous_runtime": 12,
           "backend_operator": 4,
           "framework_architecture_unsupported": 7,
-          "model_load": 4,
+          "model_load": 5,
           "runtime_memory": 9,
           "参数/模板问题": 1
         },
-        "failureCount": 37,
+        "failureCount": 38,
-        "failureRate": 0.9024,
+        "failureRate": 0.9048,
         "framework": "vllm_0_17_0_corex_4_4_0",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 4,
-        "successRate": 0.0976,
+        "successRate": 0.0952,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 41,
+        "total": 42,
         "unresolvedFailureCount": 13
       },
       "Iluvatar_bi-150|vllm|text-generation": {
@@ -2906,26 +2906,26 @@
         "unresolvedFailureCount": 11
       },
       "vllm_0_17_0_corex_4_4_0": {
-        "attributableFailureCount": 24,
+        "attributableFailureCount": 25,
-        "decisionFailureRate": 0.8571,
+        "decisionFailureRate": 0.8621,
-        "decisionSuccessRate": 0.1429,
+        "decisionSuccessRate": 0.1379,
-        "decisionTotal": 28,
+        "decisionTotal": 29,
         "failureBreakdown": {
           "ambiguous_runtime": 12,
           "backend_operator": 4,
           "framework_architecture_unsupported": 7,
-          "model_load": 4,
+          "model_load": 5,
           "runtime_memory": 9,
           "参数/模板问题": 1
         },
-        "failureCount": 37,
+        "failureCount": 38,
-        "failureRate": 0.9024,
+        "failureRate": 0.9048,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 4,
-        "successRate": 0.0976,
+        "successRate": 0.0952,
-        "total": 41,
+        "total": 42,
         "unresolvedFailureCount": 13
       },
       "vllm_fix_tokenizer": {
@@ -2972,7 +2972,7 @@
         "unresolvedFailureCount": 8
       }
     },
-    "generatedAt": "2026-09-17T12:01:22.151198+00:00",
+    "generatedAt": "2026-09-17T12:18:58.095636+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 56,
@@ -3114,28 +3114,28 @@
         "unresolvedFailureCount": 29
       },
       "Iluvatar_bi-150": {
-        "attributableFailureCount": 51,
+        "attributableFailureCount": 52,
-        "decisionFailureRate": 0.8361,
+        "decisionFailureRate": 0.8387,
-        "decisionSuccessRate": 0.1639,
+        "decisionSuccessRate": 0.1613,
-        "decisionTotal": 61,
+        "decisionTotal": 62,
         "failureBreakdown": {
           "ambiguous_runtime": 20,
           "backend_operator": 7,
           "framework_architecture_unsupported": 21,
-          "model_load": 11,
+          "model_load": 12,
           "repository_structure": 1,
           "runtime_memory": 11,
           "参数/模板问题": 3,
           "验证失败": 30
         },
-        "failureCount": 104,
+        "failureCount": 105,
-        "failureRate": 0.9123,
+        "failureRate": 0.913,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 10,
-        "successRate": 0.0877,
+        "successRate": 0.087,
-        "total": 114,
+        "total": 115,
         "unresolvedFailureCount": 53
       },
       "Iluvatar_mrv-100": {
@@ -4723,13 +4723,15 @@
         "unresolvedFailureCount": 0
       },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none": {
-        "attributableFailureCount": 0,
+        "attributableFailureCount": 1,
-        "decisionFailureRate": 0.0,
+        "decisionFailureRate": 0.5,
-        "decisionSuccessRate": 1.0,
+        "decisionSuccessRate": 0.5,
-        "decisionTotal": 1,
+        "decisionTotal": 2,
-        "failureBreakdown": {},
+        "failureBreakdown": {
-        "failureCount": 0,
+          "model_load": 1
-        "failureRate": 0.0,
+        },
+        "failureCount": 1,
+        "failureRate": 0.5,
         "framework": "vllm_0_17_0_corex_4_4_0",
         "modelType": "llama",
         "pendingCount": 0,
@@ -4737,10 +4739,10 @@
         "platformFailureCount": 0,
         "quantizationMethod": "none",
         "successCount": 1,
-        "successRate": 1.0,
+        "successRate": 0.5,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
         "unresolvedFailureCount": 0
       },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nanbeige|compressed-tensors": {
@@ -9596,6 +9598,30 @@
         "total": 2,
         "unresolvedFailureCount": 0
       },
+      "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none|30": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "model_load": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_0_17_0_corex_4_4_0",
+        "loadSizeLog2Bucket": 30,
+        "modelType": "llama",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Iluvatar_bi-150",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none|32": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -12968,19 +12994,19 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 2131,
+    "terminalRecords": 2132,
-    "totalRecords": 2234,
+    "totalRecords": 2235,
     "totals": {
-      "attributableFailureCount": 701,
+      "attributableFailureCount": 702,
-      "decisionFailureRate": 0.884,
+      "decisionFailureRate": 0.8841,
-      "decisionSuccessRate": 0.116,
+      "decisionSuccessRate": 0.1159,
-      "decisionTotal": 793,
+      "decisionTotal": 794,
       "failureBreakdown": {
         "ambiguous_runtime": 522,
         "backend_operator": 50,
         "framework_architecture_unsupported": 467,
         "memory_capacity": 12,
-        "model_load": 85,
+        "model_load": 86,
         "platform_infrastructure": 10,
         "repository_structure": 8,
         "runtime_memory": 18,
@@ -12988,14 +13014,14 @@
         "参数/模板问题": 133,
         "验证失败": 673
       },
-      "failureCount": 2039,
+      "failureCount": 2040,
       "failureRate": 0.9568,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 10,
       "successCount": 92,
       "successRate": 0.0432,
-      "total": 2131,
+      "total": 2132,
       "unresolvedFailureCount": 1328
     },
     "warnings": [
@@ -13006,11 +13032,11 @@
       "GPU Biren_166m 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 hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -13036,6 +13062,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 2234,
+  "summarizedRecords": 2235,
   "version": 1
 }

manifest.json

@@ -1,24 +1,24 @@
 {
   "agentVersion": "2026.09.04.4",
   "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "45583583ee4ae88d015dbd2a32594b8ecaf49898a6ea4e4490a03a90357b8c1c",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "46ebf24657b2019e8b1a0b44c3727c81f555ee9ec8c83fb5fecd7bc4f1a8048c",
-    ".modelhub_state/architecture_history_backfill.json": "81d4df0ef7cd72cf8cd31bd3131e12175716f124fc9a4b473be27a491ffcfdbe",
+    ".modelhub_state/architecture_history_backfill.json": "91520af8d43fe5c0bd3bc3026666ba0f8c7e4a71753bae34153e5c7f5cc8d382",
-    ".modelhub_state/market_intelligence.json": "d719b1e5d837247317d6069cb5be2f8cd6072bdd6ec354da0a38232a902de6a5",
+    ".modelhub_state/market_intelligence.json": "75ad0616b356c426f58f1447c60ca97b96cddf98cb120cfdac58f623f853ddec",
-    ".modelhub_state/official_capabilities.json": "646ea59c472cdafd659fb7cfafbf916fac28ea6b67eeac07f046a1c08c5fe04a",
+    ".modelhub_state/official_capabilities.json": "3fe93df0459e6d8dbe887db67f737ce63581d8361686feb36c56619ecedeacbd",
-    ".modelhub_state/outcome_checkpoint.json": "234b947c1113da20705f50c9e694e856cce6644a9c77c4d7a64879ae692033d2",
+    ".modelhub_state/outcome_checkpoint.json": "73f4c6ad81448736c940f6ecc059d060041569bfd2195de4558b3f5bbee6a0e9",
     ".modelhub_state/queue_cleanup_latest.json": "4be02869ade05ead6def3f33db6297b95930841c24c0c7cab3372f7790acadd8",
     ".modelhub_state/recent_outcomes.jsonl": "a391daf68a87578021331c170ae71dca18bd55fe9c4e61e89058aa2daac29778",
-    ".modelhub_state/recovery_active_tasks.jsonl": "3778ab14cdd1ca6e272cc80dc15a8980711dcc061119cede38dc70a84e99c863",
+    ".modelhub_state/recovery_active_tasks.jsonl": "8882a3b94b0f1b8d169fb9cf5bf6b76d700a294960a0b55fb73119ca53f4c479",
-    ".modelhub_state/recovery_intents.jsonl": "020c1e2c4e3aae9ddaed69c1046bc2033cdab7b1fe1c86e93a8b480ee1d187bb",
+    ".modelhub_state/recovery_intents.jsonl": "e831c049ccdfc6abcb603581219187af80a8a0998a1340fef37905cc687f4503",
     ".modelhub_state/routing_intelligence.json": "163cc1fb627c53bcf510bb545c5a55d87fb0b35f354a5157a2aabb5023a8bce5",
     ".modelhub_state/submission_exclusions.jsonl": "a0cb4e822e4b6d26c26c3bf22698cacbab31f2df5f3402ecf04fdfb3a3577ef7",
     ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
     "ledger/submissions.jsonl": "347d43a4f0d694460855911b0dfe9cc0c56a9162d549067d09aeaf76b23b92a4",
-    "outcomes/submissions.jsonl": "b3dfa0777548ed124ce9c0d044fd59ca4f4679bf6a5561e5a3a428ab52c3983b"
+    "outcomes/submissions.jsonl": "e8485ae4d80ace3151704d82f7e0861900d92493e10040b538ac31bb7fa5dcb0"
   },
-  "generation": 8727,
+  "generation": 8728,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-17T12:17:57.039049+00:00",
+  "updatedAt": "2026-09-17T12:20:41.271252+00:00",
   "writerId": "eccb3e0018f640d19e578c271a207b5c"
 }

outcomes/submissions.jsonl

@@ -112,7 +112,6 @@
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T20:25:19.301793+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "cfe08978e062dae728d260488110f70f7f12953c8f377a0f9c0a93bc3f6b0862", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:23:10.091322+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4718772", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T20:58:55.412646+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0f182c60e08246cffa89958d8d6a49257753ec0079779607a24d3f4762f95536", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619452, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:52:27.905778+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4719218", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T20:58:55.412627+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "78f026e44886f960cbcecb5cfbfc4b0b2239d86ba4b225a73df72965f73e0ed2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:52:27.907475+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4719219", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T21:08:14.021122+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:04:27.346213+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4719399", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:18:07.599908+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9294c48825334146131a77fed6083f3e1a641f9feb25fb7c3cab049e21d5f81e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619452, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:16:04.810496+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4719506", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:18:07.599874+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c03adae4b35c577b219efa214a72e6ba0eee2287660172b6efc70ec1f7b26139", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:16:04.812757+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4719505", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:51:48.716975+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "781818a9e50a17094d0f92de6e822f23f13d475b94f3e496485b51719b9fea9c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619452, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:51:12.910659+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4720103", "taskType": "text-generation", "verifyResult": null}