state: generation 10279 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -1762,7 +1762,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-20T05:35:11.648884+00:00",
+  "generatedAt": "2026-09-20T05:38:37.122922+00:00",
   "summary": {
     "activeBlockCount": 85,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -416,7 +416,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-20T05:37:35.816738+00:00",
+  "generatedAt": "2026-09-20T05:38:44.159213+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-20T05:37:35.816738+00:00",
+  "catalogUpdatedAt": "2026-09-20T05:38:44.159213+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-20T05:37:35.816738+00:00",
+  "generatedAt": "2026-09-20T05:38:44.159213+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6553,6 +6553,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-20T05:37:35.816738+00:00",
+  "taskTreeUpdatedAt": "2026-09-20T05:38:44.159213+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-20T05:31:47.498700+00:00",
+  "generatedAt": "2026-09-20T05:38:37.068183+00:00",
-  "lastSyncTime": "2026-09-20T05:31:47.157545+00:00",
+  "lastSyncTime": "2026-09-20T05:38:36.779422+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -2054,15 +2054,15 @@
         "unresolvedFailureCount": 17
       },
       "Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
-        "attributableFailureCount": 9,
+        "attributableFailureCount": 10,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 9,
+        "decisionTotal": 10,
         "failureBreakdown": {
           "ambiguous_runtime": 16,
-          "framework_architecture_unsupported": 9
+          "framework_architecture_unsupported": 10
         },
-        "failureCount": 25,
+        "failureCount": 26,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "pendingCount": 0,
@@ -2072,7 +2072,7 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b4",
         "taskType": "text-generation",
-        "total": 25,
+        "total": 26,
         "unresolvedFailureCount": 16
       },
       "Ascend_910-b4|vllm|text-generation": {
@@ -4322,26 +4322,26 @@
         "unresolvedFailureCount": 96
       },
       "vllm_tokenizer_patch": {
-        "attributableFailureCount": 21,
+        "attributableFailureCount": 22,
-        "decisionFailureRate": 0.9545,
+        "decisionFailureRate": 0.9565,
-        "decisionSuccessRate": 0.0455,
+        "decisionSuccessRate": 0.0435,
-        "decisionTotal": 22,
+        "decisionTotal": 23,
         "failureBreakdown": {
           "ambiguous_runtime": 23,
-          "framework_architecture_unsupported": 21
+          "framework_architecture_unsupported": 22
         },
-        "failureCount": 44,
+        "failureCount": 45,
-        "failureRate": 0.9778,
+        "failureRate": 0.9783,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 1,
-        "successRate": 0.0222,
+        "successRate": 0.0217,
-        "total": 45,
+        "total": 46,
         "unresolvedFailureCount": 23
       }
     },
-    "generatedAt": "2026-09-20T05:31:47.492438+00:00",
+    "generatedAt": "2026-09-20T05:38:37.060555+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 72,
@@ -4369,14 +4369,14 @@
         "unresolvedFailureCount": 108
       },
       "Ascend_910-b4": {
-        "attributableFailureCount": 302,
+        "attributableFailureCount": 303,
-        "decisionFailureRate": 0.8297,
+        "decisionFailureRate": 0.8301,
-        "decisionSuccessRate": 0.1703,
+        "decisionSuccessRate": 0.1699,
-        "decisionTotal": 364,
+        "decisionTotal": 365,
         "failureBreakdown": {
           "ambiguous_runtime": 144,
           "context_length": 1,
-          "framework_architecture_unsupported": 162,
+          "framework_architecture_unsupported": 163,
           "memory_capacity": 18,
           "model_load": 85,
           "platform_infrastructure": 1,
@@ -4386,14 +4386,14 @@
           "日志缺失": 14,
           "验证失败": 175
         },
-        "failureCount": 890,
+        "failureCount": 891,
         "failureRate": 0.9349,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 62,
         "successRate": 0.0651,
-        "total": 952,
+        "total": 953,
         "unresolvedFailureCount": 587
       },
       "Biren_166m": {
@@ -5206,14 +5206,14 @@
         "unresolvedFailureCount": 0
       },
       "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": {
-        "attributableFailureCount": 1,
+        "attributableFailureCount": 2,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 1,
+        "decisionTotal": 2,
         "failureBreakdown": {
-          "framework_architecture_unsupported": 1
+          "framework_architecture_unsupported": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "modelType": "qwen3_5_moe",
@@ -5225,7 +5225,7 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b4",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
         "unresolvedFailureCount": 0
       },
       "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": {
@@ -11076,14 +11076,14 @@
         "unresolvedFailureCount": 0
       },
       "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors|34": {
-        "attributableFailureCount": 1,
+        "attributableFailureCount": 2,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 1,
+        "decisionTotal": 2,
         "failureBreakdown": {
-          "framework_architecture_unsupported": 1
+          "framework_architecture_unsupported": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "loadSizeLog2Bucket": 34,
@@ -11096,7 +11096,7 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b4",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
         "unresolvedFailureCount": 0
       },
       "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": {
@@ -17945,20 +17945,20 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 15756,
+    "terminalRecords": 15757,
-    "totalRecords": 15859,
+    "totalRecords": 15860,
     "totals": {
-      "attributableFailureCount": 5700,
+      "attributableFailureCount": 5701,
       "decisionFailureRate": 0.8618,
       "decisionSuccessRate": 0.1382,
-      "decisionTotal": 6614,
+      "decisionTotal": 6615,
       "failureBreakdown": {
         "ambiguous_runtime": 3718,
         "architecture_compatibility": 212,
         "attention_backend": 1,
         "backend_operator": 101,
         "context_length": 318,
-        "framework_architecture_unsupported": 1956,
+        "framework_architecture_unsupported": 1957,
         "memory_capacity": 1181,
         "model_load": 474,
         "platform_infrastructure": 922,
@@ -17969,14 +17969,14 @@
         "日志缺失": 719,
         "验证失败": 673
       },
-      "failureCount": 14842,
+      "failureCount": 14843,
       "failureRate": 0.942,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 922,
       "successCount": 914,
       "successRate": 0.058,
-      "total": 15756,
+      "total": 15757,
       "unresolvedFailureCount": 8220
     },
     "warnings": [
@@ -18020,13 +18020,13 @@
       "组合 Ascend_910-b3|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 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 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": 15859,
+  "summarizedRecords": 15860,
   "version": 1
 }

ledger/submissions.jsonl

@@ -105,7 +105,6 @@
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-08T18:47:44.093470+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725852", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
 {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/prithivMLmods/MiniCPM5-2B-GGUF", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T19:24:44.852247+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4726325", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
 {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/prithivMLmods/MiniCPM5-2B-GGUF", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T19:44:39.694828+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4726617", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
-{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T21:29:34.930719+00:00", "targetGpu": "Vastai_va16", "taskId": "4727973", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T22:42:29.518873+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4729173", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "submitTime": "2026-09-08T23:02:51.785155+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729509", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "submitTime": "2026-09-08T23:02:51.924564+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}

manifest.json

@@ -1,24 +1,24 @@
 {
   "agentVersion": "2026.09.20.2",
   "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "4bd0d3e8f3bf9cd755200570d146e7f8b05e76db27e88afe59f1703be2a9127e",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "0c39d90e880b1a026ad69fad03d0ea02c513b78a9b31ecc2f2582f62d7286b0f",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "96a82d44fd6d3ddea15b7214066bb9df0f86385fe3ae99071d0e88e1654531ee",
+    ".modelhub_state/market_intelligence.json": "31a411f5de5e0bb462dc9fd07588fe4d77e8f6857a70a55c3ed1c6c99c4b03dd",
-    ".modelhub_state/official_capabilities.json": "f9d4bd087a368d6ecd06372637e3cfb63ff36cd11e11f8964f9f7ddc42174273",
+    ".modelhub_state/official_capabilities.json": "2a3a4b37b75b9ac8bfea0d1d65c7fbb05982bb592645f4facecf422e7efc3dfd",
-    ".modelhub_state/outcome_checkpoint.json": "8f23d333da995879d3556f009be09635d21ac97dc886345157e0a3f543233e4d",
+    ".modelhub_state/outcome_checkpoint.json": "7978a6d4c4393600c4ad9ebabb89d834c304de4848ac4670aef26b9964153815",
     ".modelhub_state/queue_cleanup_latest.json": "25b335b72d13b2b3ece533c0d2becb501b6af2b8e22541f81dbe2557eefe8d4f",
     ".modelhub_state/recent_outcomes.jsonl": "a6922b033a6620de4c1eebf27e571bc594980df5d0b7d7d7ae8eb909b24661eb",
-    ".modelhub_state/recovery_active_tasks.jsonl": "79d7fcc2d8b2aa6ceefa46e730c890bbb562570dca4ff8c3da98f67a8fc5fc15",
+    ".modelhub_state/recovery_active_tasks.jsonl": "5eec5683ad89f19e68046582d7af2fec9274b4bbd48191bc75f4999a45c21e22",
-    ".modelhub_state/recovery_intents.jsonl": "1f3a0024eb931915129bb340f93a915bfb5751cbe004593a59d9d64873999470",
+    ".modelhub_state/recovery_intents.jsonl": "1fc37629797c4f8115ea7c08e68799020edc5b75027e75afdb529b7c61b063fb",
     ".modelhub_state/routing_intelligence.json": "883bf953aeb66decf6d3562b5f6db7e61496d89258dbd29ffbedda006925e315",
     ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
     ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
-    "ledger/submissions.jsonl": "c5e33fac37c42ed4f7e180d1ee68db63cff2ac76b7bd1b02fdde7ef023d2af25",
+    "ledger/submissions.jsonl": "8a913bf41bd9934dc107b6b226e2ba777a2c2a379bb225cb0077e37c2c18f65b",
-    "outcomes/submissions.jsonl": "0ebb041b75fdf7d2ca66b60303f295594f7392c84354bb26302e36331a0e621d"
+    "outcomes/submissions.jsonl": "82b169076ee6683311d72a05da2becf4c32f9bac6494022b377e5dc35746407f"
   },
-  "generation": 10278,
+  "generation": 10279,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-20T05:37:36.153095+00:00",
+  "updatedAt": "2026-09-20T05:38:45.049490+00:00",
   "writerId": "fc715c06e24c4db2ae3e425e435db996"
 }

outcomes/submissions.jsonl

@@ -171,7 +171,6 @@
 {"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": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:13:15.207795+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-10T06:11:11.799771+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754343", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:13:15.207804+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "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:nvfp4", "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": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:12:56.897964+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754370", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:13:15.207812+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "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:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:12:56.900331+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754369", "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-patch-tokenizer", "lastSyncTime": "2026-09-10T14:38:26.994325+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "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:nvfp4", "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": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:30:53.020882+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754721", "taskType": "text-generation", "verifyResult": null}