state: generation 8469 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -1716,7 +1716,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-17T00:52:21.012122+00:00",
+  "generatedAt": "2026-09-17T00:55:02.300637+00:00",
   "summary": {
     "activeBlockCount": 83,
     "byGpuFramework": {

.modelhub_state/architecture_history_backfill.json

@@ -19,7 +19,7 @@
     "10": {
       "complete": false,
       "lastError": "ModelHubAPIError: 系统错误",
-      "listingErrors": 618,
+      "listingErrors": 619,
       "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": 10,
+  "nextAccountIndex": 11,
   "recordsScanned": 0,
   "seenTaskIds": [],
   "startedAt": "2026-09-04T03:55:51.365685+00:00",
   "terminalRecords": 0,
   "uniqueRecords": 0,
-  "updatedAt": "2026-09-17T00:52:20.987548+00:00",
+  "updatedAt": "2026-09-17T00:55:02.275271+00:00",
   "version": 1
 }

.modelhub_state/market_intelligence.json

@@ -416,7 +416,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-17T00:50:31.862897+00:00",
+  "generatedAt": "2026-09-17T00:53:30.747135+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-17T00:44:27.365235+00:00",
+  "generatedAt": "2026-09-17T00:53:22.021259+00:00",
-  "lastSyncTime": "2026-09-17T00:44:27.123621+00:00",
+  "lastSyncTime": "2026-09-17T00:53:21.758627+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -2609,11 +2609,11 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 3,
         "failureBreakdown": {
-          "ambiguous_runtime": 3,
+          "ambiguous_runtime": 5,
           "framework_architecture_unsupported": 2,
           "model_load": 1
         },
-        "failureCount": 6,
+        "failureCount": 8,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "pendingCount": 0,
@@ -2623,8 +2623,8 @@
         "successRate": 0.0,
         "targetGpu": "Vastai_va16",
         "taskType": "text-generation",
-        "total": 6,
+        "total": 8,
-        "unresolvedFailureCount": 3
+        "unresolvedFailureCount": 5
       },
       "Vastai_va16|vllm|text-generation": {
         "attributableFailureCount": 57,
@@ -2907,7 +2907,7 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 57,
         "failureBreakdown": {
-          "ambiguous_runtime": 58,
+          "ambiguous_runtime": 60,
           "backend_operator": 2,
           "framework_architecture_unsupported": 9,
           "model_load": 1,
@@ -2915,15 +2915,15 @@
           "tokenizer_compatibility": 45,
           "参数/模板问题": 8
         },
-        "failureCount": 130,
+        "failureCount": 132,
         "failureRate": 1.0,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 7,
         "successCount": 0,
         "successRate": 0.0,
-        "total": 130,
+        "total": 132,
-        "unresolvedFailureCount": 66
+        "unresolvedFailureCount": 68
       },
       "vllm_tokenizer_patch": {
         "attributableFailureCount": 6,
@@ -2945,7 +2945,7 @@
         "unresolvedFailureCount": 6
       }
     },
-    "generatedAt": "2026-09-17T00:44:27.359184+00:00",
+    "generatedAt": "2026-09-17T00:53:22.014439+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 51,
@@ -3240,22 +3240,22 @@
         "decisionSuccessRate": 0.2208,
         "decisionTotal": 77,
         "failureBreakdown": {
-          "ambiguous_runtime": 68,
+          "ambiguous_runtime": 70,
           "framework_architecture_unsupported": 53,
           "memory_capacity": 1,
           "model_load": 6,
           "参数/模板问题": 15,
           "验证失败": 130
         },
-        "failureCount": 273,
+        "failureCount": 275,
-        "failureRate": 0.9414,
+        "failureRate": 0.9418,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 17,
-        "successRate": 0.0586,
+        "successRate": 0.0582,
-        "total": 290,
+        "total": 292,
-        "unresolvedFailureCount": 213
+        "unresolvedFailureCount": 215
       },
       "hygon_k100-ai": {
         "attributableFailureCount": 62,
@@ -6058,9 +6058,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 2
+          "ambiguous_runtime": 4
         },
-        "failureCount": 2,
+        "failureCount": 4,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "modelType": "llama",
@@ -6072,8 +6072,8 @@
         "successRate": 0.0,
         "targetGpu": "Vastai_va16",
         "taskType": "text-generation",
-        "total": 2,
+        "total": 4,
-        "unresolvedFailureCount": 2
+        "unresolvedFailureCount": 4
       },
       "Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none": {
         "attributableFailureCount": 0,
@@ -11141,9 +11141,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 1
+          "ambiguous_runtime": 3
         },
-        "failureCount": 1,
+        "failureCount": 3,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "loadSizeLog2Bucket": 32,
@@ -11156,8 +11156,8 @@
         "successRate": 0.0,
         "targetGpu": "Vastai_va16",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 3,
-        "unresolvedFailureCount": 1
+        "unresolvedFailureCount": 3
       },
       "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|awq|33": {
         "attributableFailureCount": 0,
@@ -11425,15 +11425,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 2063,
+    "terminalRecords": 2065,
-    "totalRecords": 2166,
+    "totalRecords": 2168,
     "totals": {
       "attributableFailureCount": 670,
       "decisionFailureRate": 0.8874,
       "decisionSuccessRate": 0.1126,
       "decisionTotal": 755,
       "failureBreakdown": {
-        "ambiguous_runtime": 501,
+        "ambiguous_runtime": 503,
         "backend_operator": 45,
         "framework_architecture_unsupported": 442,
         "memory_capacity": 12,
@@ -11445,29 +11445,29 @@
         "参数/模板问题": 124,
         "验证失败": 673
       },
-      "failureCount": 1978,
+      "failureCount": 1980,
       "failureRate": 0.9588,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 10,
       "successCount": 85,
       "successRate": 0.0412,
-      "total": 2063,
+      "total": 2065,
-      "unresolvedFailureCount": 1298
+      "unresolvedFailureCount": 1300
     },
     "warnings": [
       "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_mrv-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-b4 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 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 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 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。",
       "组合 Vastai_va16|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。",
@@ -11492,6 +11492,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 2166,
+  "summarizedRecords": 2168,
   "version": 1
 }

manifest.json

@@ -1,24 +1,24 @@
 {
   "agentVersion": "2026.09.04.4",
   "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "2aaa44d3181690daa8368139ea852871199ac0a3337e01560ad07fad53f3d813",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "ebfb852fefeab190dc88a31db0db8c2aa8db807cef0f71339b6c88a67468151f",
-    ".modelhub_state/architecture_history_backfill.json": "17c57cf24de505dacedb74f6fc994b2b8baa27a466648825895e375f15932cb3",
+    ".modelhub_state/architecture_history_backfill.json": "c5c6c048c996d700719d15e889dd7b29065cdfa286d4ca5f446b641787a054e9",
-    ".modelhub_state/market_intelligence.json": "4391341dcb72416b413128a48a8338ac5a77524eb18d9a5c800afa046c72d5bf",
+    ".modelhub_state/market_intelligence.json": "9256ed280d510a6dd24ae8d6a6defbe7557d2f83a7c7c88df490e6734f88414f",
-    ".modelhub_state/official_capabilities.json": "4179953fd7b5b295db0e48cc10ae0e09f48836ced071f472c38689fccc8c6b63",
+    ".modelhub_state/official_capabilities.json": "a86b9de5a84af09127165b142dce977d468c758aefc4c9801286a412f0582090",
-    ".modelhub_state/outcome_checkpoint.json": "ab7c5e1f15db08a520544788c8ced395c329ce941bf21bd9b9f18b09c2d72860",
+    ".modelhub_state/outcome_checkpoint.json": "21a01d7c093d500315e7aae6bb73131a4c3204150bd930a5642384e2d713ebf3",
     ".modelhub_state/queue_cleanup_latest.json": "4b07ec677c9f7a1cef8978746f6e057a9979372430d32644646c3bd44e0a0546",
     ".modelhub_state/recent_outcomes.jsonl": "24b9cc5804e750ca3c47a527c7c17b3a82143b2d275022aca63433ce23ec86c3",
-    ".modelhub_state/recovery_active_tasks.jsonl": "cceeaec85610f3db636df231cc2b9b1366dceade0a7c024ced385051d77d2eeb",
+    ".modelhub_state/recovery_active_tasks.jsonl": "e40cefc423720588a24165d0edf17a9b8bd957fbda8a0cd205dbe2d688aa048c",
-    ".modelhub_state/recovery_intents.jsonl": "5ede2018f132437795bc4600582a44bc717702d4e403779827b923c483161d55",
+    ".modelhub_state/recovery_intents.jsonl": "baa17bc383c9c50d00028c3cdd344cf04ecba32d0d49631c73569633b00c8ded",
     ".modelhub_state/routing_intelligence.json": "008e6b54a9b7e1bc15577d1efc269953cea31d9de94d820a59dc3a61a5e8019c",
     ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
     ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
     "ledger/submissions.jsonl": "fc80b10bacf20e41381d1a59657f0b98108bc98d0c1ac8638ad1c6202d10ce94",
-    "outcomes/submissions.jsonl": "e9c412f7ec4e3130abda1bc4b115e989ac41b68d32e6160b0581ec1320ee8df9"
+    "outcomes/submissions.jsonl": "806c9875cfb2c17d0376a59f05130cbd149294d97ac48376af4dded1cfd730ed"
   },
-  "generation": 8468,
+  "generation": 8469,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-17T00:52:21.095834+00:00",
+  "updatedAt": "2026-09-17T00:55:03.081334+00:00",
   "writerId": "eccb3e0018f640d19e578c271a207b5c"
 }

outcomes/submissions.jsonl

@@ -44,9 +44,7 @@
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:42:08.215400+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "49c09622b187326c7d52c77c501ea1ed17ae85611b418c974c6d1dd95d2ec84c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:40:05.806797+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4649761", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:35:47.104165+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "99fcfb5673a881c74d82451063f2e7a90a328c33bce1e63a9d0bf3ccffd99170", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:30:50.543106+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650543", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:44:15.950234+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "05c5a771e8ede0f61c61c1696314e8cb295d87d07704eedc68e43f7483931e45", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:39:36.525018+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4650654", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113639+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:38.385517+00:00", "targetGpu": "Vastai_va16", "taskId": "4651796", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113688+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:38.391817+00:00", "targetGpu": "Vastai_va16", "taskId": "4651794", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113630+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "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": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:38.389388+00:00", "targetGpu": "Vastai_va16", "taskId": "4651792", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113645+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-05T16:20:43.655577+00:00", "targetGpu": "Vastai_va16", "taskId": "4651783", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:33:16.913577+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:30:08.472711+00:00", "targetGpu": "Vastai_va16", "taskId": "4651931", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503426+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093198689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.389266+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657903", "taskType": "text-generation", "verifyResult": null}
@@ -612,7 +610,7 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T00:01:16.498610+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T15:56:24.313012+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4897428", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-17T00:18:36.611812+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545917879, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T16:13:31.480300+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4897844", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T00:35:45.048451+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545917879, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T16:30:54.957126+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4898429", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545917879, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T16:47:53.958874+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4898802", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-17T00:53:21.758585+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545917879, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T16:47:53.958874+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4898802", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T17:17:09.491174+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4899358", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T17:33:45.172944+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4899710", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T17:39:01.692039+00:00", "targetGpu": "MetaX_c-500", "taskId": "4899818", "taskType": "text-generation", "verifyResult": null}