state: generation 16730 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3261,7 +3261,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-26T18:16:20.058342+00:00",
+  "generatedAt": "2026-09-26T18:22:15.193152+00:00",
   "summary": {
     "activeBlockCount": 164,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -396,7 +396,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-26T18:21:11.778814+00:00",
+  "generatedAt": "2026-09-26T18:23:02.175139+00:00",
   "gpuStats": {
     "Ascend_910-b4": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-26T18:21:11.778814+00:00",
+  "catalogUpdatedAt": "2026-09-26T18:23:02.175139+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-26T18:21:11.778814+00:00",
+  "generatedAt": "2026-09-26T18:23:02.175139+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6265,6 +6265,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-26T18:21:11.778814+00:00",
+  "taskTreeUpdatedAt": "2026-09-26T18:23:02.175139+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-26T17:57:36.464760+00:00",
+  "generatedAt": "2026-09-26T18:22:15.111319+00:00",
-  "lastSyncTime": "2026-09-26T17:57:36.159288+00:00",
+  "lastSyncTime": "2026-09-26T18:22:14.859595+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -5438,23 +5438,23 @@
           "context_length": 34,
           "framework_architecture_unsupported": 142,
           "memory_capacity": 113,
-          "platform_infrastructure": 205,
+          "platform_infrastructure": 206,
           "repository_structure": 75,
           "runtime_memory": 1,
           "tokenizer_compatibility": 179,
           "参数/模板问题": 9
         },
-        "failureCount": 937,
+        "failureCount": 938,
         "failureRate": 1.0,
         "framework": "vllm",
         "pendingCount": 0,
         "pendingRate": 0.0,
-        "platformFailureCount": 205,
+        "platformFailureCount": 206,
         "successCount": 0,
         "successRate": 0.0,
         "targetGpu": "Sunrise_pt-200-x1",
         "taskType": "text-generation",
-        "total": 937,
+        "total": 938,
         "unresolvedFailureCount": 118
       },
       "Sunrise_pt-200-x1|vllm|unknown": {
@@ -5969,20 +5969,20 @@
           "framework_architecture_unsupported": 1357,
           "memory_capacity": 725,
           "model_load": 220,
-          "platform_infrastructure": 869,
+          "platform_infrastructure": 870,
           "repository_structure": 470,
           "runtime_memory": 66,
           "tokenizer_compatibility": 416,
           "参数/模板问题": 50
         },
-        "failureCount": 6115,
+        "failureCount": 6116,
         "failureRate": 0.9844,
         "pendingCount": 0,
         "pendingRate": 0.0,
-        "platformFailureCount": 869,
+        "platformFailureCount": 870,
         "successCount": 97,
         "successRate": 0.0156,
-        "total": 6212,
+        "total": 6213,
         "unresolvedFailureCount": 1624
       },
       "vllm-customized": {
@@ -6133,7 +6133,7 @@
         "unresolvedFailureCount": 196
       }
     },
-    "generatedAt": "2026-09-26T17:57:36.450612+00:00",
+    "generatedAt": "2026-09-26T18:22:15.098384+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 102,
@@ -6479,21 +6479,21 @@
           "context_length": 39,
           "framework_architecture_unsupported": 158,
           "memory_capacity": 113,
-          "platform_infrastructure": 225,
+          "platform_infrastructure": 226,
           "repository_structure": 83,
           "runtime_memory": 1,
           "tokenizer_compatibility": 271,
           "参数/模板问题": 228,
           "验证失败": 32
         },
-        "failureCount": 1392,
+        "failureCount": 1393,
         "failureRate": 0.9374,
         "pendingCount": 0,
         "pendingRate": 0.0,
-        "platformFailureCount": 225,
+        "platformFailureCount": 226,
         "successCount": 93,
         "successRate": 0.0626,
-        "total": 1485,
+        "total": 1486,
         "unresolvedFailureCount": 422
       },
       "Vastai_va16": {
@@ -20758,21 +20758,21 @@
         "decisionTotal": 2,
         "failureBreakdown": {
           "framework_architecture_unsupported": 2,
-          "platform_infrastructure": 1
+          "platform_infrastructure": 2
         },
-        "failureCount": 3,
+        "failureCount": 4,
         "failureRate": 1.0,
         "framework": "vllm",
         "modelType": "qwen3_5",
         "pendingCount": 0,
         "pendingRate": 0.0,
-        "platformFailureCount": 1,
+        "platformFailureCount": 2,
         "quantizationMethod": "none",
         "successCount": 0,
         "successRate": 0.0,
         "targetGpu": "Sunrise_pt-200-x1",
         "taskType": "text-generation",
-        "total": 3,
+        "total": 4,
         "unresolvedFailureCount": 0
       },
       "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none": {
@@ -48196,22 +48196,23 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 1,
         "failureBreakdown": {
-          "framework_architecture_unsupported": 1
+          "framework_architecture_unsupported": 1,
+          "platform_infrastructure": 1
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm",
         "loadSizeLog2Bucket": 34,
         "modelType": "qwen3_5",
         "pendingCount": 0,
         "pendingRate": 0.0,
-        "platformFailureCount": 0,
+        "platformFailureCount": 1,
         "quantizationMethod": "none",
         "successCount": 0,
         "successRate": 0.0,
         "targetGpu": "Sunrise_pt-200-x1",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
         "unresolvedFailureCount": 0
       },
       "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|33": {
@@ -50907,8 +50908,8 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17043,
+    "terminalRecords": 17044,
-    "totalRecords": 17264,
+    "totalRecords": 17265,
     "totals": {
       "attributableFailureCount": 6112,
       "decisionFailureRate": 0.8635,
@@ -50923,7 +50924,7 @@
         "framework_architecture_unsupported": 2171,
         "memory_capacity": 1206,
         "model_load": 550,
-        "platform_infrastructure": 936,
+        "platform_infrastructure": 937,
         "repository_structure": 742,
         "runtime_memory": 100,
         "tokenizer_compatibility": 679,
@@ -50931,30 +50932,30 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16077,
+      "failureCount": 16078,
       "failureRate": 0.9433,
       "pendingCount": 0,
       "pendingRate": 0.0,
-      "platformFailureCount": 936,
+      "platformFailureCount": 937,
       "successCount": 966,
       "successRate": 0.0567,
-      "total": 17043,
+      "total": 17044,
       "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。",
@@ -50967,6 +50968,7 @@
       "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。",
@@ -50992,11 +50994,10 @@
       "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": 17264,
+  "summarizedRecords": 17265,
   "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": "1693f3b1bc0cb2d1a08a8da8be64ce5b50c9ce9c50b5c9d0bbff21e2a1925edb",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "371eb5dea2d75f856a56e2646d32ea1892d264cac9a7bc4aba84718aa291df82",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "eabb69471d2d3045579339437de11d7439898132e1c12280a6e25a8c6d2e6052",
+    ".modelhub_state/market_intelligence.json": "dc89874815692106fa131d9bd0d3eb4339b7125a16b6d5db54aa0166c8beb1e2",
-    ".modelhub_state/official_capabilities.json": "eca2da4fee361768361e10e14d3c351ba0416427d1a9fb3096a4dc0413b9c3b9",
+    ".modelhub_state/official_capabilities.json": "ae052897e38e75234c709248d54735374d667ace17d07144d89a038d9a632149",
-    ".modelhub_state/outcome_checkpoint.json": "5e8dd0e0381938adad29ee475a89387a6fbde5e1fb7e3042aef7d371284ac12f",
+    ".modelhub_state/outcome_checkpoint.json": "eb6acad1d0a916824c09f61ef7e725857a9878eaa34aaaf1ba429ccf4cf5167b",
     ".modelhub_state/queue_cleanup_latest.json": "69b07b4c7f0e1a61310077a9b0cf5b45c959484d402ad60f0304381993afe5e7",
     ".modelhub_state/recent_outcomes.jsonl": "94cee511bdff3336099866fb3c6afdd345089bb56c8aa0e85ff9041c08254a57",
-    ".modelhub_state/recovery_active_tasks.jsonl": "d10a57d906a03086e8e25b9e613d4234bc29699b3c3f7e5fa88e697cb6504b8b",
+    ".modelhub_state/recovery_active_tasks.jsonl": "70e5c0b9a011beb81cb63d9745d53c827a998ab37192943794b5d4454a2e2627",
-    ".modelhub_state/recovery_intents.jsonl": "35fa3a5bea120cc0d501b8670155a9f2b7be482a8825ba228547d5579a1e5383",
+    ".modelhub_state/recovery_intents.jsonl": "a85fd076184a7e754331424ee55779241fb60a267d955c83e891d3ca1d00fc59",
     ".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": "66ae7581811fcad3bc8f774f7b2268b56b4c41fa9933aa42807a381da20b20be"
+    "outcomes/submissions.jsonl": "2805905ddbacf503a2b99beb34b6d9f08a789895840d024a14e7c32ab12900c8"
   },
-  "generation": 16729,
+  "generation": 16730,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-26T18:21:12.425704+00:00",
+  "updatedAt": "2026-09-26T18:23:05.880064+00:00",
   "writerId": "08206cb1993a433e83f1d3e297db2d2e"
 }

outcomes/submissions.jsonl

@@ -31,7 +31,6 @@
 {"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", "lastSyncTime": "2026-09-07T02:37:59.437424+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "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": 3057371034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T03:57:59.407871+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "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": 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": "2026-09-06T19:48:32.773868+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676609", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T04:34:12.697055+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "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": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "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": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T20:23:42.610808+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677309", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:05:30.903841+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959216, "estimatedRequiredGiB": 18.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 8389956608, "modelscopeTags": ["model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:recommendation", "custom_tag:generative-recommendation", "custom_tag:reasoning", "custom_tag:itemic-token", "custom_tag:qwen3", "custom_tag:pretraining", "custom_tag:competition"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16806898419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T20:54:07.883252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677960", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228856+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:08:47.388697+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678359", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228798+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:08:47.402496+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678379", "taskType": "text-generation", "verifyResult": null}