state: generation 7164 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -1498,7 +1498,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-14T11:58:31.624132+00:00",
+  "generatedAt": "2026-09-14T12:01:42.736630+00:00",
   "summary": {
     "activeBlockCount": 75,
     "byGpuFramework": {

.modelhub_state/architecture_history_backfill.json

@@ -75,7 +75,7 @@
     "7": {
       "complete": false,
       "lastError": "ModelHubAPIError: 系统错误",
-      "listingErrors": 520,
+      "listingErrors": 521,
       "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": 7,
+  "nextAccountIndex": 8,
   "recordsScanned": 0,
   "seenTaskIds": [],
   "startedAt": "2026-09-04T03:55:51.365685+00:00",
   "terminalRecords": 0,
   "uniqueRecords": 0,
-  "updatedAt": "2026-09-14T11:58:31.600023+00:00",
+  "updatedAt": "2026-09-14T12:01:42.711668+00:00",
   "version": 1
 }

.modelhub_state/market_intelligence.json

@@ -416,7 +416,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-14T11:56:32.082872+00:00",
+  "generatedAt": "2026-09-14T11:59:42.256660+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-14T11:50:08.250891+00:00",
+  "generatedAt": "2026-09-14T11:59:32.848814+00:00",
-  "lastSyncTime": "2026-09-14T11:50:08.015544+00:00",
+  "lastSyncTime": "2026-09-14T11:59:32.597739+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -1571,12 +1571,12 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 33,
         "failureBreakdown": {
-          "ambiguous_runtime": 29,
+          "ambiguous_runtime": 30,
           "framework_architecture_unsupported": 31,
           "memory_capacity": 1,
           "tokenizer_compatibility": 1
         },
-        "failureCount": 62,
+        "failureCount": 63,
         "failureRate": 1.0,
         "framework": "vllm",
         "pendingCount": 0,
@@ -1586,8 +1586,8 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 62,
+        "total": 63,
-        "unresolvedFailureCount": 29
+        "unresolvedFailureCount": 30
       },
       "Ascend_910-b4|llamacpp|text-generation": {
         "attributableFailureCount": 1,
@@ -2081,10 +2081,10 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 36,
+          "ambiguous_runtime": 38,
           "参数/模板问题": 1
         },
-        "failureCount": 37,
+        "failureCount": 39,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "pendingCount": 0,
@@ -2094,8 +2094,8 @@
         "successRate": 0.0,
         "targetGpu": "Kunlunxin_p-800",
         "taskType": "text-generation",
-        "total": 37,
+        "total": 39,
-        "unresolvedFailureCount": 37
+        "unresolvedFailureCount": 39
       },
       "MetaX_c-500|unknown|text-generation": {
         "attributableFailureCount": 0,
@@ -2542,7 +2542,7 @@
         "decisionSuccessRate": 0.0096,
         "decisionTotal": 314,
         "failureBreakdown": {
-          "ambiguous_runtime": 207,
+          "ambiguous_runtime": 208,
           "backend_operator": 34,
           "framework_architecture_unsupported": 223,
           "memory_capacity": 7,
@@ -2553,15 +2553,15 @@
           "tokenizer_compatibility": 7,
           "参数/模板问题": 30
         },
-        "failureCount": 549,
+        "failureCount": 550,
         "failureRate": 0.9946,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 3,
         "successRate": 0.0054,
-        "total": 552,
+        "total": 553,
-        "unresolvedFailureCount": 237
+        "unresolvedFailureCount": 238
       },
       "vllm-mlu": {
         "attributableFailureCount": 8,
@@ -2631,7 +2631,7 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 53,
         "failureBreakdown": {
-          "ambiguous_runtime": 38,
+          "ambiguous_runtime": 40,
           "backend_operator": 2,
           "framework_architecture_unsupported": 8,
           "model_load": 1,
@@ -2639,15 +2639,15 @@
           "tokenizer_compatibility": 42,
           "参数/模板问题": 7
         },
-        "failureCount": 102,
+        "failureCount": 104,
         "failureRate": 1.0,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 4,
         "successCount": 0,
         "successRate": 0.0,
-        "total": 102,
+        "total": 104,
-        "unresolvedFailureCount": 45
+        "unresolvedFailureCount": 47
       },
       "vllm_tokenizer_patch": {
         "attributableFailureCount": 0,
@@ -2668,7 +2668,7 @@
         "unresolvedFailureCount": 1
       }
     },
-    "generatedAt": "2026-09-14T11:50:08.246900+00:00",
+    "generatedAt": "2026-09-14T11:59:32.843492+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 33,
@@ -2676,22 +2676,22 @@
         "decisionSuccessRate": 0.0294,
         "decisionTotal": 34,
         "failureBreakdown": {
-          "ambiguous_runtime": 29,
+          "ambiguous_runtime": 30,
           "framework_architecture_unsupported": 31,
           "memory_capacity": 1,
           "tokenizer_compatibility": 1,
           "参数/模板问题": 8,
           "验证失败": 27
         },
-        "failureCount": 97,
+        "failureCount": 98,
-        "failureRate": 0.9898,
+        "failureRate": 0.9899,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 1,
-        "successRate": 0.0102,
+        "successRate": 0.0101,
-        "total": 98,
+        "total": 99,
-        "unresolvedFailureCount": 64
+        "unresolvedFailureCount": 65
       },
       "Ascend_910-b4": {
         "attributableFailureCount": 48,
@@ -2861,20 +2861,20 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 1,
         "failureBreakdown": {
-          "ambiguous_runtime": 75,
+          "ambiguous_runtime": 77,
           "memory_capacity": 1,
           "参数/模板问题": 1,
           "验证失败": 23
         },
-        "failureCount": 100,
+        "failureCount": 102,
         "failureRate": 1.0,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 0,
         "successRate": 0.0,
-        "total": 100,
+        "total": 102,
-        "unresolvedFailureCount": 99
+        "unresolvedFailureCount": 101
       },
       "MetaX_c-500": {
         "attributableFailureCount": 55,
@@ -3844,6 +3844,29 @@
         "total": 3,
         "unresolvedFailureCount": 3
       },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|mxfp4": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "modelType": "gpt_oss",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "mxfp4",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -3913,6 +3936,29 @@
         "total": 3,
         "unresolvedFailureCount": 3
       },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "modelType": "qwen3_5_moe",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "compressed-tensors",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -4896,7 +4942,7 @@
         "failureRate": 1.0,
         "framework": "vllm",
         "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-14T07:52:30.913030+00:00",
+        "lastTerminalAt": "2026-09-14T11:59:32.597701+00:00",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
@@ -5175,9 +5221,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 2
+          "ambiguous_runtime": 1
         },
-        "failureCount": 2,
+        "failureCount": 1,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "lastPlatformFailureAt": null,
@@ -5189,8 +5235,8 @@
         "successRate": 0.0,
         "targetGpu": "Kunlunxin_p-800",
         "taskType": "text-generation",
-        "total": 2,
+        "total": 1,
-        "unresolvedFailureCount": 2
+        "unresolvedFailureCount": 1
       },
       "MetaX_c-500|unknown|text-generation": {
         "attributableFailureCount": 0,
@@ -5459,31 +5505,6 @@
         "taskType": "text-generation",
         "total": 1,
         "unresolvedFailureCount": 1
-      },
-      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none": {
-        "attributableFailureCount": 0,
-        "consecutiveFailures": 0,
-        "decisionFailureRate": 0.0,
-        "decisionSuccessRate": 0.0,
-        "decisionTotal": 0,
-        "failureBreakdown": {
-          "ambiguous_runtime": 1
-        },
-        "failureCount": 1,
-        "failureRate": 1.0,
-        "framework": "vllm_fix_tokenizer",
-        "lastTerminalAt": "2026-09-12T23:53:22.743813+00:00",
-        "modelType": "rwkv7",
-        "pendingCount": 0,
-        "pendingRate": 0.0,
-        "platformFailureCount": 0,
-        "quantizationMethod": "none",
-        "successCount": 0,
-        "successRate": 0.0,
-        "targetGpu": "Kunlunxin_p-800",
-        "taskType": "text-generation",
-        "total": 1,
-        "unresolvedFailureCount": 1
       }
     },
     "sizedProfileCombinationStats": {
@@ -6659,6 +6680,30 @@
         "total": 2,
         "unresolvedFailureCount": 2
       },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|mxfp4|34": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "loadSizeLog2Bucket": 34,
+        "modelType": "gpt_oss",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "mxfp4",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|28": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -6827,6 +6872,30 @@
         "total": 2,
         "unresolvedFailureCount": 2
       },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "loadSizeLog2Bucket": 34,
+        "modelType": "qwen3_5_moe",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "compressed-tensors",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|36": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -8242,15 +8311,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 1829,
+    "terminalRecords": 1832,
-    "totalRecords": 1922,
+    "totalRecords": 1925,
     "totals": {
       "attributableFailureCount": 549,
       "decisionFailureRate": 0.9015,
       "decisionSuccessRate": 0.0985,
       "decisionTotal": 609,
       "failureBreakdown": {
-        "ambiguous_runtime": 432,
+        "ambiguous_runtime": 435,
         "backend_operator": 43,
         "framework_architecture_unsupported": 349,
         "memory_capacity": 12,
@@ -8262,15 +8331,15 @@
         "参数/模板问题": 109,
         "验证失败": 673
       },
-      "failureCount": 1769,
+      "failureCount": 1772,
       "failureRate": 0.9672,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 6,
       "successCount": 60,
       "successRate": 0.0328,
-      "total": 1829,
+      "total": 1832,
-      "unresolvedFailureCount": 1214
+      "unresolvedFailureCount": 1217
     },
     "warnings": [
       "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -8308,6 +8377,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 1922,
+  "summarizedRecords": 1925,
   "version": 1
 }

.modelhub_state/recent_outcomes.jsonl

@@ -1,3 +1,4 @@
+{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-14T11:59:32.597701+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T11:57:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4575880", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-14T11:40:43.317618+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T11:39:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471935", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-14T11:40:43.317642+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T11:39:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471914", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-14T10:28:20.247729+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T10:27:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477784", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T21:47:28.214740+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:41:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610342", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T21:37:50.501060+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505065", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T18:58:50.012615+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16314183099, "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:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 16314183099}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:08:22.097030+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746441", "taskType": "text-generation", "verifyResult": -1}
-{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T23:53:22.743813+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898265436, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2948065280, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898265436}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:08:22.094532+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746447", "taskType": "text-generation", "verifyResult": -1}

manifest.json

@@ -1,24 +1,24 @@
 {
   "agentVersion": "2026.09.04.4",
   "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "91c2f4aaaf2d45311c809a4fbbee47846c36dead1cfc1178309b0458dc915506",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "96d2ffc738ab27a7eafddada5821a06381c7cd1288b84d8287e011cb3cbc6dde",
-    ".modelhub_state/architecture_history_backfill.json": "8715b27d5b292aabb33f84ac8f32a352a5e3328ce5e8e85a15a4aff085fd5f6c",
+    ".modelhub_state/architecture_history_backfill.json": "8619b9c98771ffea982e339e08fee617a630c2dad46cf779bd74d9249db945a2",
-    ".modelhub_state/market_intelligence.json": "90a2e48dfe9c59a37d9fc1844f4eeb7901f38a108271701c2a7b0ebef00e185d",
+    ".modelhub_state/market_intelligence.json": "094a4e223e928ee1b0feae5c042fd8ce9e2b4f6113a0cfffd98e7de2cf654e26",
-    ".modelhub_state/official_capabilities.json": "7f5ce3a3ca7aef683079921cbb08ebb64b14207cb869d80d9018edd0fea24f85",
+    ".modelhub_state/official_capabilities.json": "d8ee72cc6982d2e0ee677854a78f1912e5120dd1d31a8ca665c314430c73e29f",
-    ".modelhub_state/outcome_checkpoint.json": "2e82844a2a2bd49b6d0a116552cc8a127cb1c4874c5a69630c083650f6974d40",
+    ".modelhub_state/outcome_checkpoint.json": "e30c2d3678976289aa676cdeeabe15d60473d53d5cd32f0be59056eef00394f0",
     ".modelhub_state/queue_cleanup_latest.json": "e5d9b334b2784235be02767778d1d31aa5d889dbe0cdb9bf65bb77a097c78531",
-    ".modelhub_state/recent_outcomes.jsonl": "fec83e03ae4b3a0c872fb87d8c96b9dfa135fd131a6af08858404e71a6b4c4c9",
+    ".modelhub_state/recent_outcomes.jsonl": "72c25a0d6d28cf0ebadc6b2d988c92a81963033875dd7742edf8d8daec715e5f",
-    ".modelhub_state/recovery_active_tasks.jsonl": "4a8e55f87c626a46336fdeace0d069d3e9703dc9aab06d55c2fd8374003f7f37",
+    ".modelhub_state/recovery_active_tasks.jsonl": "8f83875916d06d410616ee1563051b0cc16daf45e24857ef0a35bf4ce7302f63",
-    ".modelhub_state/recovery_intents.jsonl": "10c05804bad9fb6751ae3c3d3568e959bfb73ca96803e30c45111771f8160a03",
+    ".modelhub_state/recovery_intents.jsonl": "779682afd078563d7b1231f358abcf01f8a11cecc6d6592722bcf67918ac09e0",
     ".modelhub_state/routing_intelligence.json": "350794262038f5417f2c2055e35c53a6da870601a90b6c6b470484a8808e8764",
     ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
     ".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
     "ledger/submissions.jsonl": "534da75337c614c3a3b5ecc6a07cf615533851ea1ac60f312bfbcce339099da3",
-    "outcomes/submissions.jsonl": "f870c1f40446ecdb1dc7ada1d9077e285b37ce74b903a7b46bd8e5d51e75cef4"
+    "outcomes/submissions.jsonl": "8a7f9b04e31b5c1244b75947509fbdf1e989f044d33aaacb9f35ef1eb6a740a7"
   },
-  "generation": 7163,
+  "generation": 7164,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-14T11:58:31.726187+00:00",
+  "updatedAt": "2026-09-14T12:01:43.320467+00:00",
   "writerId": "69701e73196b4ac2b3fad0f412335168"
 }

outcomes/submissions.jsonl

@@ -163,7 +163,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613082+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679222028, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679222028}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.194804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667926", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613054+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72656575880, "estimatedRequiredGiB": 81.21, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72665883326, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72665883326}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.550329+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667927", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613090+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:01:57.388649+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668028", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:33:26.815214+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22109595640, "estimatedRequiredGiB": 24.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22137550529, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 20921584848, "modelscopeTags": ["license:Apache License 2.0", "model_type:gpt_oss", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "mxfp4", "repositoryOnDiskBytes": 22137550529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:32:32.785339+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668538", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806846+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679220993, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679220993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399880+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:07:54.384483+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669411", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T00:59:44.608188+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "verifyResult": null}
@@ -346,7 +345,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504652+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.785155+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729509", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504496+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-08T23:02:51.831733+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729515", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504528+00:00", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelProfile": {"architectures": ["HunYuanMoEV1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1700, "estimatedRequiredGiB": 90.469, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hunyuan", "modelscopeFileSize": 80949912827, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 80393195968, "modelscopeTags": ["license:Apache License 2.0", "model_type:hunyuan", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 80949912827}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.924564+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504434+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119861184, "estimatedRequiredGiB": 29.243, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26165778261, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26165778261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.933574+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729525", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504558+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306305296, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19329225494, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329225494}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.939534+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729523", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504596+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426230291, "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": 1426230291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.094406+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729529", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504631+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.086476+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729527", "taskType": "text-generation", "verifyResult": null}