state: generation 19400 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3341,7 +3341,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-10-01T21:56:07.948433+00:00",
+  "generatedAt": "2026-10-01T22:04:49.197255+00:00",
   "summary": {
     "activeBlockCount": 168,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -434,7 +434,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-10-01T22:03:43.054869+00:00",
+  "generatedAt": "2026-10-01T22:06:46.367346+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-10-01T22:03:43.054869+00:00",
+  "catalogUpdatedAt": "2026-10-01T22:06:46.367346+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-10-01T22:03:43.054869+00:00",
+  "generatedAt": "2026-10-01T22:06:46.367346+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6630,6 +6630,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-10-01T22:03:43.054869+00:00",
+  "taskTreeUpdatedAt": "2026-10-01T22:06:46.367346+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-10-01T20:57:12.703376+00:00",
+  "generatedAt": "2026-10-01T22:04:49.108094+00:00",
-  "lastSyncTime": "2026-10-01T20:57:12.462569+00:00",
+  "lastSyncTime": "2026-10-01T22:04:48.852822+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3922,29 +3922,29 @@
         "unresolvedFailureCount": 4
       },
       "Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
-        "attributableFailureCount": 20,
+        "attributableFailureCount": 21,
-        "decisionFailureRate": 0.6897,
+        "decisionFailureRate": 0.7,
-        "decisionSuccessRate": 0.3103,
+        "decisionSuccessRate": 0.3,
-        "decisionTotal": 29,
+        "decisionTotal": 30,
         "failureBreakdown": {
           "ambiguous_runtime": 45,
-          "framework_architecture_unsupported": 17,
+          "framework_architecture_unsupported": 18,
           "model_load": 3,
           "platform_infrastructure": 1,
           "参数/模板问题": 1,
           "验证失败": 3
         },
-        "failureCount": 70,
+        "failureCount": 71,
-        "failureRate": 0.8861,
+        "failureRate": 0.8875,
         "framework": "vllm-mlu",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 9,
-        "successRate": 0.1139,
+        "successRate": 0.1125,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 79,
+        "total": 80,
         "unresolvedFailureCount": 49
       },
       "Cambricon_mlu-370-x4|vllm|text-generation": {
@@ -6093,27 +6093,27 @@
         "unresolvedFailureCount": 51
       },
       "vllm-mlu": {
-        "attributableFailureCount": 35,
+        "attributableFailureCount": 36,
-        "decisionFailureRate": 0.614,
+        "decisionFailureRate": 0.6207,
-        "decisionSuccessRate": 0.386,
+        "decisionSuccessRate": 0.3793,
-        "decisionTotal": 57,
+        "decisionTotal": 58,
         "failureBreakdown": {
           "ambiguous_runtime": 95,
-          "framework_architecture_unsupported": 29,
+          "framework_architecture_unsupported": 30,
           "model_load": 5,
           "platform_infrastructure": 1,
           "tokenizer_compatibility": 1,
           "参数/模板问题": 4,
           "验证失败": 3
         },
-        "failureCount": 138,
+        "failureCount": 139,
-        "failureRate": 0.8625,
+        "failureRate": 0.8634,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 22,
-        "successRate": 0.1375,
+        "successRate": 0.1366,
-        "total": 160,
+        "total": 161,
         "unresolvedFailureCount": 102
       },
       "vllm-patch-tokenizer": {
@@ -6217,7 +6217,7 @@
         "unresolvedFailureCount": 225
       }
     },
-    "generatedAt": "2026-10-01T20:57:12.690281+00:00",
+    "generatedAt": "2026-10-01T22:04:49.095265+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 113,
@@ -6305,15 +6305,15 @@
         "unresolvedFailureCount": 564
       },
       "Cambricon_mlu-370-x4": {
-        "attributableFailureCount": 753,
+        "attributableFailureCount": 754,
-        "decisionFailureRate": 0.9105,
+        "decisionFailureRate": 0.9106,
-        "decisionSuccessRate": 0.0895,
+        "decisionSuccessRate": 0.0894,
-        "decisionTotal": 827,
+        "decisionTotal": 828,
         "failureBreakdown": {
           "ambiguous_runtime": 510,
           "architecture_compatibility": 53,
           "context_length": 48,
-          "framework_architecture_unsupported": 306,
+          "framework_architecture_unsupported": 307,
           "memory_capacity": 219,
           "model_load": 7,
           "platform_infrastructure": 16,
@@ -6323,14 +6323,14 @@
           "日志缺失": 13,
           "验证失败": 42
         },
-        "failureCount": 1621,
+        "failureCount": 1622,
-        "failureRate": 0.9563,
+        "failureRate": 0.9564,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 16,
         "successCount": 74,
-        "successRate": 0.0437,
+        "successRate": 0.0436,
-        "total": 1695,
+        "total": 1696,
         "unresolvedFailureCount": 852
       },
       "Cambricon_mlu-370-x8": {
@@ -11511,15 +11511,15 @@
         "unresolvedFailureCount": 0
       },
       "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none": {
-        "attributableFailureCount": 4,
+        "attributableFailureCount": 5,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 4,
+        "decisionTotal": 5,
         "failureBreakdown": {
-          "framework_architecture_unsupported": 4,
+          "framework_architecture_unsupported": 5,
           "验证失败": 1
         },
-        "failureCount": 5,
+        "failureCount": 6,
         "failureRate": 1.0,
         "framework": "vllm-mlu",
         "modelType": "qwen3_5",
@@ -11531,7 +11531,7 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 5,
+        "total": 6,
         "unresolvedFailureCount": 1
       },
       "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors": {
@@ -35772,6 +35772,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|32": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm-mlu",
+        "loadSizeLog2Bucket": 32,
+        "modelType": "qwen3_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Cambricon_mlu-370-x4",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|33": {
         "attributableFailureCount": 3,
         "decisionFailureRate": 1.0,
@@ -54498,20 +54522,20 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17209,
+    "terminalRecords": 17210,
-    "totalRecords": 17430,
+    "totalRecords": 17431,
     "totals": {
-      "attributableFailureCount": 6170,
+      "attributableFailureCount": 6171,
-      "decisionFailureRate": 0.8635,
+      "decisionFailureRate": 0.8636,
-      "decisionSuccessRate": 0.1365,
+      "decisionSuccessRate": 0.1364,
-      "decisionTotal": 7145,
+      "decisionTotal": 7146,
       "failureBreakdown": {
         "ambiguous_runtime": 4497,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 128,
         "context_length": 326,
-        "framework_architecture_unsupported": 2213,
+        "framework_architecture_unsupported": 2214,
         "memory_capacity": 1206,
         "model_load": 553,
         "platform_infrastructure": 944,
@@ -54522,30 +54546,30 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16234,
+      "failureCount": 16235,
       "failureRate": 0.9433,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 944,
       "successCount": 975,
       "successRate": 0.0567,
-      "total": 17209,
+      "total": 17210,
       "unresolvedFailureCount": 9120
     },
     "warnings": [
       "GPU Iluvatar_mrv-100 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 Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_bi-100 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 Cambricon_mlu-370-x8 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 Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU 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 Vastai_va16 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。",
       "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 Kunlunxin_p-800|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。",
@@ -54590,6 +54614,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 17430,
+  "summarizedRecords": 17431,
   "version": 1
 }

ledger/submissions.jsonl

@@ -223,7 +223,6 @@
 {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "submitTime": "2026-09-20T03:09:17.666037+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969308", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
 {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "submitTime": "2026-09-20T03:09:17.694934+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969317", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
 {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "modelId": "inceptionai/Jais-2-8B-Chat", "submitTime": "2026-09-20T03:09:17.840209+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
-{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "modelId": "BAAI/RoboBrain2.5-8B-NV", "submitTime": "2026-09-20T03:09:17.837872+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969323", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
 {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "submitTime": "2026-09-20T03:25:32.045316+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969632", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.22.1",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "46b5f60bde18df956b341300a7b934a86c4d1bfa71e58145ee4135888a0f8e5b",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "359082324f6380e5ee4fb5815c8d0b01cb2014b5fa189c741d28d566e5f97569",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "81a64429b35a65a4bd5c09e6dc6c017d1f6f556877ccce7587a6a4625e4e4e79",
+    ".modelhub_state/market_intelligence.json": "2a1b489b0251941d5fbec09bb48ff42998516be27a82a258ca3e4bc579653f21",
-    ".modelhub_state/official_capabilities.json": "f834cb19bc1a5e5ff6af8b589411e02be2fdb02b290b548e66bc7da3d2d0ffc8",
+    ".modelhub_state/official_capabilities.json": "0e6736ae7e4426c6e3632edc734830f5066518b1e8e634e459926e149a34b036",
-    ".modelhub_state/outcome_checkpoint.json": "b4925e7d15edb9f9643db3d56034088228fd52d802ac58d4dda62ca96593ee94",
+    ".modelhub_state/outcome_checkpoint.json": "de64e7616b80a77063eb842dc1a40c420c137516b51cae6880ed0893dcf08c99",
     ".modelhub_state/queue_cleanup_latest.json": "ec9c714dde635223eb7f5550481af3a4ff97e6326f9bfe9026419293fd2022b3",
     ".modelhub_state/recent_outcomes.jsonl": "2523ec2f7019354108df01107e7f0a74a17201a51201d3993b38b265a6fafd64",
-    ".modelhub_state/recovery_active_tasks.jsonl": "83f8b9181a5a32720be75076ac6617a400d8e135ea7637bbc258b587b2e415ae",
+    ".modelhub_state/recovery_active_tasks.jsonl": "9c522d5317ddfd3ab1d2d3a3912a6612646b30d76c57f75cb327c6e0f17e1faf",
-    ".modelhub_state/recovery_intents.jsonl": "b734e43cdf19b31398569d2610586ef9847c30605ae2a850dc18d78a31eb881b",
+    ".modelhub_state/recovery_intents.jsonl": "f93122d08709735a699e432f274a16c580ee334177fd004118fe860791ed293f",
     ".modelhub_state/routing_intelligence.json": "4cab060aa87c62b99c0f5f10e414a79361ce90d66fd3ab7f01b38511e88cd04c",
     ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
     ".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
-    "ledger/submissions.jsonl": "31a8d160c632fcd39f691b07117cc090017735b2bae96e54b6940e730210d1ef",
+    "ledger/submissions.jsonl": "f2008ae8f605aa37f6fddf514b2290acc5c3be90214b18647cd64aae1a594e3a",
-    "outcomes/submissions.jsonl": "64d7823699947045b91ee22f0d61e1d56561c655354bd31f9979d8492cf91559"
+    "outcomes/submissions.jsonl": "1095b0de6439a8e8117a6d6fbbd5e5257a7e817502d923fba3ab90d38b6c3eeb"
   },
-  "generation": 19399,
+  "generation": 19400,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-01T22:03:46.102628+00:00",
+  "updatedAt": "2026-10-01T22:07:12.877091+00:00",
   "writerId": "a812d0e025c3474eb16b828a4d987334"
 }

outcomes/submissions.jsonl

@@ -140,7 +140,6 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T01:54:16.705192+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T17:52:33.017540+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4900094", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T02:10:59.211438+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T18:09:58.859804+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4900532", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-17T10:10:02.608080+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T02:02:00.958898+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4906949", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-17T10:10:02.608073+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T02:02:00.946894+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4906950", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:21:23.552173+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb269a9a8b4c1eeb18e3ef78bedcf638c3d1821a581b2f17113cde2fcd8be6c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:19:02.317218+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4912678", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:42:14.260331+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7df61fc66119e362f4b324c308b44e18bd70c6e8415d3cf79ad822bc9e6377c3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:36:01.072109+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4912861", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T18:05:14.493617+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cde1dd013433575dd6e624ec4e742d4992d0b53d429ab95bc4dbe8884fc49e49", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:57:55.404929+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4913157", "taskType": "text-generation", "verifyResult": null}