state: generation 16700 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3261,7 +3261,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-26T17:14:27.691343+00:00",
+  "generatedAt": "2026-09-26T17:19:54.499080+00:00",
   "summary": {
     "activeBlockCount": 164,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -396,7 +396,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-26T17:18:51.853456+00:00",
+  "generatedAt": "2026-09-26T17:20:50.548064+00:00",
   "gpuStats": {
     "Ascend_910-b4": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-26T17:18:51.853456+00:00",
+  "catalogUpdatedAt": "2026-09-26T17:20:50.548064+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-26T17:18:51.853456+00:00",
+  "generatedAt": "2026-09-26T17:20:50.548064+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6265,6 +6265,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-26T17:18:51.853456+00:00",
+  "taskTreeUpdatedAt": "2026-09-26T17:20:50.548064+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-26T17:14:27.607568+00:00",
+  "generatedAt": "2026-09-26T17:19:54.419455+00:00",
-  "lastSyncTime": "2026-09-26T17:14:27.552028+00:00",
+  "lastSyncTime": "2026-09-26T17:19:54.158491+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -5409,34 +5409,34 @@
         "failureBreakdown": {
           "backend_operator": 9,
           "framework_architecture_unsupported": 14,
-          "platform_infrastructure": 19,
+          "platform_infrastructure": 20,
           "tokenizer_compatibility": 88,
           "参数/模板问题": 6
         },
-        "failureCount": 136,
+        "failureCount": 137,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "pendingCount": 0,
         "pendingRate": 0.0,
-        "platformFailureCount": 19,
+        "platformFailureCount": 20,
         "successCount": 0,
         "successRate": 0.0,
         "targetGpu": "Sunrise_pt-200-x1",
         "taskType": "text-generation",
-        "total": 136,
+        "total": 137,
         "unresolvedFailureCount": 6
       },
       "Sunrise_pt-200-x1|vllm|text-generation": {
-        "attributableFailureCount": 613,
+        "attributableFailureCount": 614,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 613,
+        "decisionTotal": 614,
         "failureBreakdown": {
           "ambiguous_runtime": 109,
           "architecture_compatibility": 43,
           "backend_operator": 27,
           "context_length": 34,
-          "framework_architecture_unsupported": 141,
+          "framework_architecture_unsupported": 142,
           "memory_capacity": 113,
           "platform_infrastructure": 205,
           "repository_structure": 75,
@@ -5444,7 +5444,7 @@
           "tokenizer_compatibility": 179,
           "参数/模板问题": 9
         },
-        "failureCount": 936,
+        "failureCount": 937,
         "failureRate": 1.0,
         "framework": "vllm",
         "pendingCount": 0,
@@ -5454,7 +5454,7 @@
         "successRate": 0.0,
         "targetGpu": "Sunrise_pt-200-x1",
         "taskType": "text-generation",
-        "total": 936,
+        "total": 937,
         "unresolvedFailureCount": 118
       },
       "Sunrise_pt-200-x1|vllm|unknown": {
@@ -5956,17 +5956,17 @@
         "unresolvedFailureCount": 6473
       },
       "vllm": {
-        "attributableFailureCount": 3621,
+        "attributableFailureCount": 3622,
         "decisionFailureRate": 0.9739,
         "decisionSuccessRate": 0.0261,
-        "decisionTotal": 3718,
+        "decisionTotal": 3719,
         "failureBreakdown": {
           "ambiguous_runtime": 1574,
           "architecture_compatibility": 112,
           "attention_backend": 3,
           "backend_operator": 92,
           "context_length": 161,
-          "framework_architecture_unsupported": 1356,
+          "framework_architecture_unsupported": 1357,
           "memory_capacity": 725,
           "model_load": 220,
           "platform_infrastructure": 869,
@@ -5975,14 +5975,14 @@
           "tokenizer_compatibility": 416,
           "参数/模板问题": 50
         },
-        "failureCount": 6114,
+        "failureCount": 6115,
         "failureRate": 0.9844,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 869,
         "successCount": 97,
         "successRate": 0.0156,
-        "total": 6211,
+        "total": 6212,
         "unresolvedFailureCount": 1624
       },
       "vllm-customized": {
@@ -6090,18 +6090,18 @@
           "framework_architecture_unsupported": 32,
           "memory_capacity": 10,
           "model_load": 9,
-          "platform_infrastructure": 19,
+          "platform_infrastructure": 20,
           "tokenizer_compatibility": 88,
           "参数/模板问题": 13
         },
-        "failureCount": 499,
+        "failureCount": 500,
         "failureRate": 0.9901,
         "pendingCount": 0,
         "pendingRate": 0.0,
-        "platformFailureCount": 19,
+        "platformFailureCount": 20,
         "successCount": 5,
         "successRate": 0.0099,
-        "total": 504,
+        "total": 505,
         "unresolvedFailureCount": 332
       },
       "vllm_tokenizer_patch": {
@@ -6133,7 +6133,7 @@
         "unresolvedFailureCount": 196
       }
     },
-    "generatedAt": "2026-09-26T17:14:27.595531+00:00",
+    "generatedAt": "2026-09-26T17:19:54.406878+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 102,
@@ -6468,32 +6468,32 @@
         "unresolvedFailureCount": 299
       },
       "Sunrise_pt-200-x1": {
-        "attributableFailureCount": 743,
+        "attributableFailureCount": 744,
-        "decisionFailureRate": 0.8888,
+        "decisionFailureRate": 0.8889,
-        "decisionSuccessRate": 0.1112,
+        "decisionSuccessRate": 0.1111,
-        "decisionTotal": 836,
+        "decisionTotal": 837,
         "failureBreakdown": {
           "ambiguous_runtime": 162,
           "architecture_compatibility": 44,
           "backend_operator": 36,
           "context_length": 39,
-          "framework_architecture_unsupported": 157,
+          "framework_architecture_unsupported": 158,
           "memory_capacity": 113,
-          "platform_infrastructure": 224,
+          "platform_infrastructure": 225,
           "repository_structure": 83,
           "runtime_memory": 1,
           "tokenizer_compatibility": 270,
           "参数/模板问题": 228,
           "验证失败": 32
         },
-        "failureCount": 1389,
+        "failureCount": 1391,
-        "failureRate": 0.9372,
+        "failureRate": 0.9373,
         "pendingCount": 0,
         "pendingRate": 0.0,
-        "platformFailureCount": 224,
+        "platformFailureCount": 225,
         "successCount": 93,
-        "successRate": 0.0628,
+        "successRate": 0.0627,
-        "total": 1482,
+        "total": 1484,
         "unresolvedFailureCount": 422
       },
       "Vastai_va16": {
@@ -20613,6 +20613,29 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3|none": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "platform_infrastructure": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "modelType": "qwen3",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 1,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Sunrise_pt-200-x1",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
         "attributableFailureCount": 3,
         "decisionFailureRate": 1.0,
@@ -20705,6 +20728,29 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "modelType": "qwen3_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "modelopt",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Sunrise_pt-200-x1",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": {
         "attributableFailureCount": 2,
         "decisionFailureRate": 1.0,
@@ -47903,6 +47949,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3|none|24": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "platform_infrastructure": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "loadSizeLog2Bucket": 24,
+        "modelType": "qwen3",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 1,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Sunrise_pt-200-x1",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -48071,6 +48141,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt|34": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "loadSizeLog2Bucket": 34,
+        "modelType": "qwen3_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "modelopt",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Sunrise_pt-200-x1",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|33": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -50813,23 +50907,23 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17040,
+    "terminalRecords": 17042,
-    "totalRecords": 17261,
+    "totalRecords": 17263,
     "totals": {
-      "attributableFailureCount": 6110,
+      "attributableFailureCount": 6111,
       "decisionFailureRate": 0.8635,
       "decisionSuccessRate": 0.1365,
-      "decisionTotal": 7076,
+      "decisionTotal": 7077,
       "failureBreakdown": {
         "ambiguous_runtime": 4407,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 127,
         "context_length": 322,
-        "framework_architecture_unsupported": 2170,
+        "framework_architecture_unsupported": 2171,
         "memory_capacity": 1206,
         "model_load": 550,
-        "platform_infrastructure": 935,
+        "platform_infrastructure": 936,
         "repository_structure": 742,
         "runtime_memory": 100,
         "tokenizer_compatibility": 678,
@@ -50837,30 +50931,30 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16074,
+      "failureCount": 16076,
       "failureRate": 0.9433,
       "pendingCount": 0,
       "pendingRate": 0.0,
-      "platformFailureCount": 935,
+      "platformFailureCount": 936,
       "successCount": 966,
       "successRate": 0.0567,
-      "total": 17040,
+      "total": 17042,
       "unresolvedFailureCount": 9029
     },
     "warnings": [
       "GPU Biren_166m 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 Iluvatar_bi-100 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 Iluvatar_bi-150 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Kunlunxin_p-800 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 Ascend_910-b3 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 Vastai_va16 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 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 Iluvatar_bi-150 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 Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
       "组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -50873,6 +50967,7 @@
       "组合 Iluvatar_bi-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-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-x4|vllm-mlu|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 hygon_k100-ai|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-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -50898,11 +50993,10 @@
       "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|llamacpp|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 MetaX_c-500|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": 17261,
+  "summarizedRecords": 17263,
   "version": 1
 }

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.22.1",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "274ffc4bf5a44fa0e4f01bda1ef59c9dbb538c48c2baccc0785f8e8f4576bb2b",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "4011932ee6dcc31d7acce4819c8be219cce3f8d58cb0393c20cf25cd4b74c522",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "c5f05f9a249034146a0a0cbee759f9a149310eb97b4f91ef5a0d130821095d1b",
+    ".modelhub_state/market_intelligence.json": "0c8cca253732462f872885fa5c33e0cd96477be3389a6705ccf16f898911819a",
-    ".modelhub_state/official_capabilities.json": "83d3e46084cc315e3bef3090b512d18b8bb2a84bda33ab460a3711e969dd4a28",
+    ".modelhub_state/official_capabilities.json": "94f712b74cd92b6d74838940e7255aa5599831af858ed074fedfee1dd56d0ac3",
-    ".modelhub_state/outcome_checkpoint.json": "2724105c224bddee80416a2124557af2cb39d170a3e68767cee65a44db6fd8b5",
+    ".modelhub_state/outcome_checkpoint.json": "87bc6b0ae19930fb62c6cb744e4bdcd55bf55e096e3ac77a4835757d2c96d4dd",
     ".modelhub_state/queue_cleanup_latest.json": "dec10eb574f7da548f3ba2d81064346ebac4cd728c834ece356077b765895663",
     ".modelhub_state/recent_outcomes.jsonl": "5bb3cb27e3f3907a8c702285032b948854e2231cc687129c54c45d75115b3d47",
-    ".modelhub_state/recovery_active_tasks.jsonl": "b46af010e92902915fe7672b16664bb429f78adbeaafa2999bd0289852d7c2db",
+    ".modelhub_state/recovery_active_tasks.jsonl": "7ff073fe1fdd2f942c0162688408874d0bea6b35cf0964983ae752090c4d018e",
-    ".modelhub_state/recovery_intents.jsonl": "5df2e08a8843622d2f941b0e83af768424eea321a10c2f5fb3dee5c8774166e3",
+    ".modelhub_state/recovery_intents.jsonl": "668b7413c1842806f8fa1058e93e1025c072ab0c37bb3966a4ba5332c2dbe762",
     ".modelhub_state/routing_intelligence.json": "519577e231ce3934d8378cbf1f13f1356f0576991f528675ded72ec2b8b3c804",
     ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
     ".modelhub_state/worker_crashes.jsonl": "ccd40ad86ab5068ea1c3520a48fa733cf2e4b357ae5abb95ff00728d5d1b5487",
     "ledger/submissions.jsonl": "6071510b13d7fa1186e155941f35e6810e50a687772bd3064a7286c5ba918d9c",
-    "outcomes/submissions.jsonl": "be9146006f31e79fda9a5ed4954eb6dae37a5ba39fbdb42d1b31d73098b22c15"
+    "outcomes/submissions.jsonl": "66ae7581811fcad3bc8f774f7b2268b56b4c41fa9933aa42807a381da20b20be"
   },
-  "generation": 16699,
+  "generation": 16700,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-26T17:18:52.578014+00:00",
+  "updatedAt": "2026-09-26T17:20:54.620926+00:00",
   "writerId": "08206cb1993a433e83f1d3e297db2d2e"
 }

outcomes/submissions.jsonl

@@ -14,7 +14,6 @@
 {"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": "2026-09-06T08:35:17.503426+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}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503433+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39365175520, "estimatedRequiredGiB": 44.029, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 39396646235, "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": 39396646235}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.385964+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657900", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503369+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.392602+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657901", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503472+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19509024201, "estimatedRequiredGiB": 21.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19530936726, "modelscopeLicense": null, "modelscopeParams": 5419330688, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19530936726}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.419799+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657897", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503479+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 451270785, "estimatedRequiredGiB": 0.534, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 478002291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 119465472, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 478002291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.487200+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657899", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503418+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.393987+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657908", "taskType": "text-generation", "verifyResult": null}
@@ -23,7 +22,6 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T08:54:40.814445+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-09-06T00:51:47.515580+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4658219", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601493+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-06T02:23:39.684428+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659269", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601408+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703969742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "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:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703969742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:23:39.690219+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659268", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601473+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:24:31.818066+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659299", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T11:46:43.318197+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26540803088, "estimatedRequiredGiB": 29.664, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 26542898184, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13270298624, "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": 26542898184}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T03:45:55.331628+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660328", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:21:22.998937+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-06T04:17:45.285806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660827", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:39:38.309054+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:38:16.005175+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4661079", "taskType": "text-generation", "verifyResult": null}