state: generation 10606 (intent)

.modelhub_state/queue_cleanup_latest.json

@@ -37,6 +37,16 @@
       "vllm_fix_tokenizer",
       "vllm_tokenizer_patch"
     ],
+    "cambricon_mlu-370-x4|text-generation": [
+      "vllm",
+      "vllm-customized",
+      "vllm-mlu"
+    ],
+    "cambricon_mlu-370-x8|text-generation": [
+      "vllm",
+      "vllm-customized",
+      "vllm-mlu"
+    ],
     "hygon_k100-ai|text-generation": [
       "llamacpp",
       "vllm",
@@ -50,6 +60,15 @@
       "vllm_fix_tokenizer",
       "vllm_tokenizer_patch"
     ],
+    "iluvatar_mrv-100|text-generation": [
+      "transformers",
+      "vllm"
+    ],
+    "kunlunxin_p-800|text-generation": [
+      "vllm",
+      "vllm_fix_tokenizer",
+      "vllm_tokenizer_patch"
+    ],
     "metax_c-500|text-generation": [
       "vllm",
       "vllm_tokenizer_patch"
@@ -63,6 +82,10 @@
       "sglang",
       "vllm",
       "vllm_fix_tokenizer"
+    ],
+    "vastai_va16|text-generation": [
+      "vllm",
+      "vllm_fix_tokenizer"
     ]
   },
   "architectureFrameworkCatalogErrors": {},
@@ -91,22 +114,49 @@
     "z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
   },
   "architectureModelConfigsComplete": 46,
-  "architectureOnly": true,
+  "architectureOnly": false,
   "architecturePolicySkipped": {
-    "frameworkCatalogUnknown": 3,
+    "frameworkCatalogUnknown": 0,
     "frameworkContextUnknown": 65,
     "modelArchitectureUnknown": 161,
-    "noMatchingBlock": 955,
+    "noMatchingBlock": 958,
     "partiallyBlockedFrameworkSet": 22,
     "runningMatchedProtected": 0,
     "submissionContextMismatch": 0,
     "submissionContextUnknown": 0
   },
-  "cancelledCount": 0,
-  "cancelledTasks": [],
-  "certainOomCount": 0,
-  "certainOomTasks": [],
-  "cleanupCandidateCount": 0,
+  "cancelledCount": 1,
+  "cancelledTasks": [
+    {
+      "accountIndex": 4,
+      "cleanupReasons": [
+        "certain_oom_repository_size_exceeds_gpu_capacity"
+      ],
+      "gpuCapacityGiB": 100.0,
+      "gpuType": "Kunlunxin_p-800",
+      "modelId": "logic65/Whittle-Qwen-3.8-35B-A3B",
+      "reason": "certain_oom_repository_size_exceeds_gpu_capacity",
+      "repositorySizeGiB": 132.503,
+      "requiredGiB": 159.003,
+      "status": "waiting",
+      "taskId": 4960317
+    }
+  ],
+  "certainOomCount": 1,
+  "certainOomTasks": [
+    {
+      "accountIndex": 4,
+      "gpuCapacityGiB": 100.0,
+      "gpuType": "Kunlunxin_p-800",
+      "modelId": "logic65/Whittle-Qwen-3.8-35B-A3B",
+      "reason": "certain_oom_repository_size_exceeds_gpu_capacity",
+      "repositorySizeGiB": 132.503,
+      "requiredGiB": 159.003,
+      "status": "waiting",
+      "taskId": 4960317
+    }
+  ],
+  "cleanupCandidateCount": 1,
   "dryRun": false,
   "listingErrors": {},
   "modelAgeErrors": {},
@@ -131,18 +181,20 @@
   ],
   "oldOverflowCount": 0,
   "oldOverflowTasks": [],
-  "policyCancelledRecorded": 0,
+  "policyCancelledRecorded": 1,
   "policyNoLongerAppliesCount": 0,
   "policyNoLongerAppliesTasks": [],
   "recentModelDays": 7,
   "recentModelReserveSlots": 5,
-  "repositorySizeErrors": {},
-  "repositorySizesComplete": 0,
+  "repositorySizeErrors": {
+    "empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
+  },
+  "repositorySizesComplete": 339,
   "skipped": {
-    "fitsKnownCapacity": 0,
+    "fitsKnownCapacity": 1138,
     "gpuCapacityUnknown": 0,
-    "repositorySizeUnknown": 0
+    "repositorySizeUnknown": 2
   },
   "stopErrors": [],
-  "uniqueModels": 339
+  "uniqueModels": 340
 }