state: generation 17948 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3280,7 +3280,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-28T16:09:58.861821+00:00",
+  "generatedAt": "2026-09-28T16:18:42.205285+00:00",
   "summary": {
     "activeBlockCount": 165,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -396,7 +396,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-28T16:17:27.673626+00:00",
+  "generatedAt": "2026-09-28T16:20:11.644618+00:00",
   "gpuStats": {
     "Ascend_910-b4": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-28T16:17:27.673626+00:00",
+  "catalogUpdatedAt": "2026-09-28T16:20:11.644618+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-28T16:17:27.673626+00:00",
+  "generatedAt": "2026-09-28T16:20:11.644618+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6570,6 +6570,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-28T16:17:27.673626+00:00",
+  "taskTreeUpdatedAt": "2026-09-28T16:20:11.644618+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-28T12:16:36.344733+00:00",
+  "generatedAt": "2026-09-28T16:18:42.123597+00:00",
-  "lastSyncTime": "2026-09-28T12:16:36.062761+00:00",
+  "lastSyncTime": "2026-09-28T16:18:41.860656+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3890,12 +3890,12 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 25,
         "failureBreakdown": {
-          "ambiguous_runtime": 45,
+          "ambiguous_runtime": 46,
           "framework_architecture_unsupported": 24,
           "memory_capacity": 1,
           "参数/模板问题": 1
         },
-        "failureCount": 71,
+        "failureCount": 72,
         "failureRate": 1.0,
         "framework": "vllm",
         "pendingCount": 0,
@@ -3905,8 +3905,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 71,
+        "total": 72,
-        "unresolvedFailureCount": 46
+        "unresolvedFailureCount": 47
       },
       "Cambricon_mlu-370-x8|unknown|feature_emb": {
         "attributableFailureCount": 0,
@@ -5981,7 +5981,7 @@
         "decisionSuccessRate": 0.0261,
         "decisionTotal": 3723,
         "failureBreakdown": {
-          "ambiguous_runtime": 1585,
+          "ambiguous_runtime": 1586,
           "architecture_compatibility": 112,
           "attention_backend": 3,
           "backend_operator": 93,
@@ -5995,15 +5995,15 @@
           "tokenizer_compatibility": 416,
           "参数/模板问题": 50
         },
-        "failureCount": 6132,
+        "failureCount": 6133,
         "failureRate": 0.9844,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 871,
         "successCount": 97,
         "successRate": 0.0156,
-        "total": 6229,
+        "total": 6230,
-        "unresolvedFailureCount": 1635
+        "unresolvedFailureCount": 1636
       },
       "vllm-customized": {
         "attributableFailureCount": 14,
@@ -6153,7 +6153,7 @@
         "unresolvedFailureCount": 197
       }
     },
-    "generatedAt": "2026-09-28T12:16:36.331263+00:00",
+    "generatedAt": "2026-09-28T16:18:42.111883+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 102,
@@ -6245,7 +6245,7 @@
         "decisionSuccessRate": 0.0891,
         "decisionTotal": 819,
         "failureBreakdown": {
-          "ambiguous_runtime": 505,
+          "ambiguous_runtime": 506,
           "architecture_compatibility": 53,
           "context_length": 48,
           "framework_architecture_unsupported": 299,
@@ -6258,15 +6258,15 @@
           "日志缺失": 13,
           "验证失败": 42
         },
-        "failureCount": 1609,
+        "failureCount": 1610,
         "failureRate": 0.9566,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 16,
         "successCount": 73,
         "successRate": 0.0434,
-        "total": 1682,
+        "total": 1683,
-        "unresolvedFailureCount": 847
+        "unresolvedFailureCount": 848
       },
       "Cambricon_mlu-370-x8": {
         "attributableFailureCount": 60,
@@ -11500,9 +11500,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 9
+          "ambiguous_runtime": 10
         },
-        "failureCount": 9,
+        "failureCount": 10,
         "failureRate": 1.0,
         "framework": "vllm",
         "modelType": "llama",
@@ -11514,8 +11514,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 9,
+        "total": 10,
-        "unresolvedFailureCount": 9
+        "unresolvedFailureCount": 10
       },
       "Cambricon_mlu-370-x4|vllm|text-generation|llama|none": {
         "attributableFailureCount": 0,
@@ -34666,9 +34666,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 5
+          "ambiguous_runtime": 6
         },
-        "failureCount": 5,
+        "failureCount": 6,
         "failureRate": 1.0,
         "framework": "vllm",
         "loadSizeLog2Bucket": 33,
@@ -34681,8 +34681,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 5,
+        "total": 6,
-        "unresolvedFailureCount": 5
+        "unresolvedFailureCount": 6
       },
       "Cambricon_mlu-370-x4|vllm|text-generation|llama|none|30": {
         "attributableFailureCount": 0,
@@ -51854,15 +51854,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17078,
+    "terminalRecords": 17079,
-    "totalRecords": 17299,
+    "totalRecords": 17300,
     "totals": {
       "attributableFailureCount": 6123,
       "decisionFailureRate": 0.8637,
       "decisionSuccessRate": 0.1363,
       "decisionTotal": 7089,
       "failureBreakdown": {
-        "ambiguous_runtime": 4428,
+        "ambiguous_runtime": 4429,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 128,
@@ -51878,15 +51878,15 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16112,
+      "failureCount": 16113,
       "failureRate": 0.9434,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 938,
       "successCount": 966,
       "successRate": 0.0566,
-      "total": 17078,
+      "total": 17079,
-      "unresolvedFailureCount": 9051
+      "unresolvedFailureCount": 9052
     },
     "warnings": [
       "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -51915,7 +51915,6 @@
       "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。",
       "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 Iluvatar_mrv-100|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 Kunlunxin_p-800|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 MetaX_c-500|vllm|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|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51940,10 +51939,11 @@
       "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 Cambricon_mlu-370-x4|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 Ascend_910-b3|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 Vastai_va16|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 Vastai_va16|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 Kunlunxin_p-800|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": 17299,
+  "summarizedRecords": 17300,
   "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": "42efdee251faddeff48d58b4cf17f0f8876a088e7fe0eed4ca85a17ee318f8ea",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "755524c6f521e648050ec5373e777260da10e1011b0ddae59d1930e4651eaeb0",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "81e54d0f5aa76d7399c90e25dcb5c695e32a33a1035190b1332656a9291ed52b",
+    ".modelhub_state/market_intelligence.json": "f91c496ceae533535f623b1abad552c2118c7ea95032e9ec124a8827c6fe63ad",
-    ".modelhub_state/official_capabilities.json": "f874f5f51b47f6fc2d42b4064397fbf3cce62e70e83748deb6274973a89799af",
+    ".modelhub_state/official_capabilities.json": "2f1fc2aef7b7b53780d251d03aeeca026ef6d6eaca92f5e6663d769203496b3d",
-    ".modelhub_state/outcome_checkpoint.json": "0f22f43784b8d18b08a402e392195c06011531fb13d770b7cde513ab8bcbb283",
+    ".modelhub_state/outcome_checkpoint.json": "717ace965eb0652049a44a3229ed395b420e6b8b0307b6a97b7c4a38ba6c0f27",
     ".modelhub_state/queue_cleanup_latest.json": "d09d9940cc3b3be17208fe9c9249cf654886f748a0e8ae3d2c99fbf473612f1f",
     ".modelhub_state/recent_outcomes.jsonl": "1dbde9c4996b0dbc395b2b06ede89ee01d228323012054151eb598a3995b826e",
-    ".modelhub_state/recovery_active_tasks.jsonl": "e2d514a7820bc1ad21ab3574653fb2337a7d11741b4b10b0e31cac20bd8fe970",
+    ".modelhub_state/recovery_active_tasks.jsonl": "6aa89739b0e4af57a23d08bb22f95f7486c5d1cff0a9b30438ca7ed1e7fa2656",
-    ".modelhub_state/recovery_intents.jsonl": "0f2936b5bf4777b917c294887073885f1517a1f92649ab94583a45e94d3c5d01",
+    ".modelhub_state/recovery_intents.jsonl": "2477edc353816609a4e538ce8ac9a177bc43371c1558df3c12c84939f9a51ee8",
     ".modelhub_state/routing_intelligence.json": "4864d455a863d4f5712f620109cc96b5b2ab91f24bce5ef4e7a9f6191c4ecead",
     ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
     ".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06",
     "ledger/submissions.jsonl": "0dbee188d0ab75761812ce60b96822b84ffe04d8cd6a76f10bf382713b92cdfd",
-    "outcomes/submissions.jsonl": "70528236b1980741ffdba69f0790f3d266981b6dae9799eb305f583c421789de"
+    "outcomes/submissions.jsonl": "60910058f7691ece03051aa2f1e8e869722b508e52b27123bd4135f3fcd5719c"
   },
-  "generation": 17947,
+  "generation": 17948,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-28T16:17:39.967019+00:00",
+  "updatedAt": "2026-09-28T16:20:28.078364+00:00",
   "writerId": "9d958b95ce4146c9939da0f14b9201ff"
 }

outcomes/submissions.jsonl

@@ -426,7 +426,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998391+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:04:12.536952+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998195+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.509125+00:00", "targetGpu": "Biren_166m", "taskId": "4991811", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:33:30.477748+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:08.713395+00:00", "targetGpu": "Biren_166m", "taskId": "4991852", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477642+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261938, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261938}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.284265+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991861", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T12:58:50.741624+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T04:44:11.759434+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4994057", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759836+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T15:02:24.876266+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449487, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449487}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:49:13.744923+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4995536", "taskType": "text-generation", "verifyResult": null}