state: generation 7548 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -322,18 +322,20 @@
     "ascend_910-b4|vllm|text-generation|model_type:qwen3_5": {
       "architectureSignature": "model_type:qwen3_5",
       "architectures": [],
-      "evidenceCount": 2,
+      "evidenceCount": 3,
-      "expiresAt": "2026-10-14T12:41:21+00:00",
+      "expiresAt": "2026-10-15T05:29:21+00:00",
       "framework": "vllm",
-      "latestFailureAt": "2026-09-14T12:41:21+00:00",
+      "latestFailureAt": "2026-09-15T05:29:21+00:00",
       "latestSuccessfulAt": null,
       "matchType": "model_type",
       "modelType": "qwen3_5",
       "sourceModelIds": [
+        "EschaLabs/Qwen3.8-27B-Escha-W2",
         "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128",
         "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8"
       ],
       "sourceTaskIds": [
+        "4610338",
         "4610343",
         "4610337"
       ],
@@ -1564,7 +1566,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-15T05:33:43.091541+00:00",
+  "generatedAt": "2026-09-15T05:37:15.349362+00:00",
   "summary": {
     "activeBlockCount": 77,
     "byGpuFramework": {

.modelhub_state/architecture_history_backfill.json

@@ -35,7 +35,7 @@
     "2": {
       "complete": false,
       "lastError": "ModelHubAPIError: 系统错误",
-      "listingErrors": 548,
+      "listingErrors": 549,
       "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": 2,
+  "nextAccountIndex": 3,
   "recordsScanned": 0,
   "seenTaskIds": [],
   "startedAt": "2026-09-04T03:55:51.365685+00:00",
   "terminalRecords": 0,
   "uniqueRecords": 0,
-  "updatedAt": "2026-09-15T05:33:43.065557+00:00",
+  "updatedAt": "2026-09-15T05:37:15.325302+00:00",
   "version": 1
 }

.modelhub_state/market_intelligence.json

@@ -416,7 +416,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-15T05:31:54.494026+00:00",
+  "generatedAt": "2026-09-15T05:34:50.478493+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-15T05:15:31.935581+00:00",
+  "generatedAt": "2026-09-15T05:34:44.035061+00:00",
-  "lastSyncTime": "2026-09-15T05:15:31.609450+00:00",
+  "lastSyncTime": "2026-09-15T05:34:43.803064+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -326,18 +326,20 @@
       "ascend_910-b4|vllm|text-generation|model_type:qwen3_5": {
         "architectureSignature": "model_type:qwen3_5",
         "architectures": [],
-        "evidenceCount": 2,
+        "evidenceCount": 3,
-        "expiresAt": "2026-10-14T12:41:21+00:00",
+        "expiresAt": "2026-10-15T05:29:21+00:00",
         "framework": "vllm",
-        "latestFailureAt": "2026-09-14T12:41:21+00:00",
+        "latestFailureAt": "2026-09-15T05:29:21+00:00",
         "latestSuccessfulAt": null,
         "matchType": "model_type",
         "modelType": "qwen3_5",
         "sourceModelIds": [
+          "EschaLabs/Qwen3.8-27B-Escha-W2",
           "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128",
           "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8"
         ],
         "sourceTaskIds": [
+          "4610338",
           "4610343",
           "4610337"
         ],
@@ -1720,18 +1722,18 @@
         "unresolvedFailureCount": 1
       },
       "Ascend_910-b4|vllm|text-generation": {
-        "attributableFailureCount": 50,
+        "attributableFailureCount": 51,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 50,
+        "decisionTotal": 51,
         "failureBreakdown": {
           "ambiguous_runtime": 38,
-          "framework_architecture_unsupported": 46,
+          "framework_architecture_unsupported": 47,
           "memory_capacity": 1,
           "repository_structure": 1,
           "tokenizer_compatibility": 2
         },
-        "failureCount": 88,
+        "failureCount": 89,
         "failureRate": 1.0,
         "framework": "vllm",
         "pendingCount": 0,
@@ -1741,7 +1743,7 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b4",
         "taskType": "text-generation",
-        "total": 88,
+        "total": 89,
         "unresolvedFailureCount": 38
       },
       "Biren_166m|unknown|text-generation": {
@@ -2607,14 +2609,14 @@
         "unresolvedFailureCount": 893
       },
       "vllm": {
-        "attributableFailureCount": 333,
+        "attributableFailureCount": 334,
-        "decisionFailureRate": 0.9823,
+        "decisionFailureRate": 0.9824,
-        "decisionSuccessRate": 0.0177,
+        "decisionSuccessRate": 0.0176,
-        "decisionTotal": 339,
+        "decisionTotal": 340,
         "failureBreakdown": {
           "ambiguous_runtime": 217,
           "backend_operator": 34,
-          "framework_architecture_unsupported": 244,
+          "framework_architecture_unsupported": 245,
           "memory_capacity": 7,
           "model_load": 27,
           "platform_infrastructure": 1,
@@ -2623,14 +2625,14 @@
           "tokenizer_compatibility": 7,
           "参数/模板问题": 30
         },
-        "failureCount": 581,
+        "failureCount": 582,
         "failureRate": 0.9898,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 6,
         "successRate": 0.0102,
-        "total": 587,
+        "total": 588,
         "unresolvedFailureCount": 247
       },
       "vllm-mlu": {
@@ -2739,7 +2741,7 @@
         "unresolvedFailureCount": 1
       }
     },
-    "generatedAt": "2026-09-15T05:15:31.928794+00:00",
+    "generatedAt": "2026-09-15T05:34:44.030489+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 40,
@@ -2765,13 +2767,13 @@
         "unresolvedFailureCount": 67
       },
       "Ascend_910-b4": {
-        "attributableFailureCount": 51,
+        "attributableFailureCount": 52,
-        "decisionFailureRate": 0.9623,
+        "decisionFailureRate": 0.963,
-        "decisionSuccessRate": 0.0377,
+        "decisionSuccessRate": 0.037,
-        "decisionTotal": 53,
+        "decisionTotal": 54,
         "failureBreakdown": {
           "ambiguous_runtime": 39,
-          "framework_architecture_unsupported": 46,
+          "framework_architecture_unsupported": 47,
           "memory_capacity": 1,
           "model_load": 1,
           "repository_structure": 1,
@@ -2779,14 +2781,14 @@
           "参数/模板问题": 12,
           "验证失败": 175
         },
-        "failureCount": 277,
+        "failureCount": 278,
-        "failureRate": 0.9928,
+        "failureRate": 0.9929,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 2,
-        "successRate": 0.0072,
+        "successRate": 0.0071,
-        "total": 279,
+        "total": 280,
         "unresolvedFailureCount": 226
       },
       "Biren_166m": {
@@ -5464,21 +5466,21 @@
         "unresolvedFailureCount": 1
       },
       "Ascend_910-b4|vllm|text-generation": {
-        "attributableFailureCount": 13,
+        "attributableFailureCount": 14,
-        "consecutiveFailures": 13,
+        "consecutiveFailures": 14,
         "consecutivePlatformFailures": 0,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 13,
+        "decisionTotal": 14,
         "failureBreakdown": {
-          "ambiguous_runtime": 7,
+          "ambiguous_runtime": 6,
-          "framework_architecture_unsupported": 13
+          "framework_architecture_unsupported": 14
         },
         "failureCount": 20,
         "failureRate": 1.0,
         "framework": "vllm",
         "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-14T23:27:02.946784+00:00",
+        "lastTerminalAt": "2026-09-15T05:34:43.803047+00:00",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
@@ -5487,7 +5489,7 @@
         "targetGpu": "Ascend_910-b4",
         "taskType": "text-generation",
         "total": 20,
-        "unresolvedFailureCount": 7
+        "unresolvedFailureCount": 6
       },
       "Biren_166m|unknown|text-generation": {
         "attributableFailureCount": 8,
@@ -9296,17 +9298,17 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 1900,
+    "terminalRecords": 1901,
-    "totalRecords": 1993,
+    "totalRecords": 1994,
     "totals": {
-      "attributableFailureCount": 582,
+      "attributableFailureCount": 583,
-      "decisionFailureRate": 0.8981,
+      "decisionFailureRate": 0.8983,
-      "decisionSuccessRate": 0.1019,
+      "decisionSuccessRate": 0.1017,
-      "decisionTotal": 648,
+      "decisionTotal": 649,
       "failureBreakdown": {
         "ambiguous_runtime": 457,
         "backend_operator": 44,
-        "framework_architecture_unsupported": 376,
+        "framework_architecture_unsupported": 377,
         "memory_capacity": 12,
         "model_load": 78,
         "platform_infrastructure": 6,
@@ -9316,14 +9318,14 @@
         "参数/模板问题": 116,
         "验证失败": 673
       },
-      "failureCount": 1834,
+      "failureCount": 1835,
       "failureRate": 0.9653,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 6,
       "successCount": 66,
       "successRate": 0.0347,
-      "total": 1900,
+      "total": 1901,
       "unresolvedFailureCount": 1246
     },
     "warnings": [
@@ -9362,6 +9364,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 1993,
+  "summarizedRecords": 1994,
   "version": 1
 }

.modelhub_state/recent_outcomes.jsonl

@@ -1,3 +1,4 @@
+{"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"], "framework": "vllm", "lastSyncTime": "2026-09-15T05:34:43.803047+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T05:29:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4610338", "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": "2026-09-15T05:15:31.609401+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T05:09:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4594447", "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"], "framework": "vllm", "lastSyncTime": "2026-09-15T05:15:31.609450+00:00", "modelId": "douyamv/Qwen3.8-27B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T05:07:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4583327", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-15T03:19:58.951190+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T03:17:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4531335", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"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": "", "lastSyncTime": "2026-09-10T05:27:18.447582+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:19:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481721", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-10T05:18:58.697108+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:13:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4609099", "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": "", "lastSyncTime": "2026-09-10T05:18:58.697138+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:13:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610360", "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": "2026-09-10T04:54:16.213427+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493600", "taskType": "text-generation", "verifyResult": -1}

manifest.json

@@ -1,24 +1,24 @@
 {
   "agentVersion": "2026.09.04.4",
   "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "2cdc80302e6eff8124f069142bc57174f6fe65414bb9ac4e181ccf212f3f05a3",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "201f3ff3e973cd3af7c307e6f54ef88ce56647b4e253fd3cadc1a5d949340667",
-    ".modelhub_state/architecture_history_backfill.json": "6593fa88df0904e3e115906d4a8c13fb263f723ffa40f1b5cc2c4c83688b761f",
+    ".modelhub_state/architecture_history_backfill.json": "43eec9424dcd50b10fa1be8f4aa4158fbba3378c54c154afb52b21c473b5de56",
-    ".modelhub_state/market_intelligence.json": "a1b087aa92ae2c595f75985db9a4f6835632cc00caaab4675196b9bcf8b1525e",
+    ".modelhub_state/market_intelligence.json": "38f980f10cf4a16e1fc86bbaf5996cf5b3a5fe1d9b325dc176449751dfcf4750",
-    ".modelhub_state/official_capabilities.json": "09107b2ac8110fb49171c355c2935d005412634428bdf6d20c903ed63e6fe8da",
+    ".modelhub_state/official_capabilities.json": "55f90b1fbbb8c569cbea87cb70028d482735ecf5050bc2daaf1d838e89ae0bf1",
-    ".modelhub_state/outcome_checkpoint.json": "e976621f8ad61c19037df80a22ff5783d82c71533bb6d2f415779e165fa307c5",
+    ".modelhub_state/outcome_checkpoint.json": "b5df8edd48af39b93786ef09ee7acb82bf041ce498ff73c46210e4f3b3739c71",
     ".modelhub_state/queue_cleanup_latest.json": "01e08fd4618eb925c85708b1e84308d8914f762fc7ce784e5b71b8af21bef866",
-    ".modelhub_state/recent_outcomes.jsonl": "ec5c0b96de5f5d3e1fcb2bd5ae2cb45732fffbfd474915f331ff519b33512a30",
+    ".modelhub_state/recent_outcomes.jsonl": "f6e3e90af51c49e76039bdd3accf7fc6b9b5b5a702f8e699fbf5badd1db3c44f",
-    ".modelhub_state/recovery_active_tasks.jsonl": "cfe902e406d9325d3e1358a5721d85133e5a2bcfe8fed4acd24962ff11be6516",
+    ".modelhub_state/recovery_active_tasks.jsonl": "e57e9751a3126cdd228b9f7a908b72ec243a123e519d29f7b513eb90f24c15f3",
-    ".modelhub_state/recovery_intents.jsonl": "5dea98a50c2c7fc28fa8b17929166bd61ed20e9e2134e8480d6d688d12c126af",
+    ".modelhub_state/recovery_intents.jsonl": "cbfce3a20f349b1f59c2a23864d4359937c818eb80abf80d563b50fd9f2e4c3b",
     ".modelhub_state/routing_intelligence.json": "3d8a13cda7ef7e2d279be17fe53b44b30fbfcc75b45cb282a1252198990c4e47",
     ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
     ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
     "ledger/submissions.jsonl": "55dc43661afa1a3153dc3909cfcf407bc301bb1a44f76606af697979642f3d9c",
-    "outcomes/submissions.jsonl": "6dbb22c451a26bbdc8d0ce6b84f81cfe2a4f294c94e05c014a7505339a220b12"
+    "outcomes/submissions.jsonl": "1c8d1748305b46c12a4967336c2931a7966551e0e703cab0e56354cbcc3a23e5"
   },
-  "generation": 7547,
+  "generation": 7548,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-15T05:33:43.183227+00:00",
+  "updatedAt": "2026-09-15T05:37:16.016890+00:00",
   "writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
 }

outcomes/submissions.jsonl

@@ -635,8 +635,8 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:15:31.609429+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:09:06.637418+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4857320", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:15:31.609440+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:09:06.635873+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4857321", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T05:25:28.408813+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:17:59.038422+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4857428", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T21:27:24.586588+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857632", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T05:34:43.803008+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:27:24.586588+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857632", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T21:27:24.589018+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857633", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T05:34:43.803064+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:27:24.589018+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857633", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T21:47:17.029854+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857814", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T21:47:17.027666+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857813", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T22:08:21.049320+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4858026", "taskType": "text-generation", "verifyResult": null}