state: generation 7333 (cycle)

2026-09-14 19:43:48 +00:00
parent 5f8610e34e
commit aaf3f57db4
9 changed files with 2012 additions and 1966 deletions
--- a/.modelhub_state/architecture_compatibility_blacklist.json
+++ b/.modelhub_state/architecture_compatibility_blacklist.json
@@ -1548,7 +1548,7 @@
      "taskType": "text-generation"
    }
  },
-  "generatedAt": "2026-09-14T19:40:17.845600+00:00",
+  "generatedAt": "2026-09-14T19:43:48.301553+00:00",
  "summary": {
    "activeBlockCount": 77,
    "byGpuFramework": {
--- a/.modelhub_state/architecture_history_backfill.json
+++ b/.modelhub_state/architecture_history_backfill.json
@@ -19,7 +19,7 @@
    "10": {
      "complete": false,
      "lastError": "ModelHubAPIError: 系统错误",
-      "listingErrors": 532,
+      "listingErrors": 533,
      "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": 10,
+  "nextAccountIndex": 11,
  "recordsScanned": 0,
  "seenTaskIds": [],
  "startedAt": "2026-09-04T03:55:51.365685+00:00",
  "terminalRecords": 0,
  "uniqueRecords": 0,
-  "updatedAt": "2026-09-14T19:40:17.818965+00:00",
+  "updatedAt": "2026-09-14T19:43:48.275269+00:00",
  "version": 1
 }
--- a/.modelhub_state/market_intelligence.json
+++ b/.modelhub_state/market_intelligence.json
@@ -416,7 +416,7 @@
    }
  },
  "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-14T19:38:26.771346+00:00",
+  "generatedAt": "2026-09-14T19:41:29.657780+00:00",
  "gpuStats": {
    "Ascend_910-b3": {
      "available": true,
--- a/.modelhub_state/official_capabilities.json
+++ b/.modelhub_state/official_capabilities.json
--- a/.modelhub_state/outcome_checkpoint.json
+++ b/.modelhub_state/outcome_checkpoint.json
@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-14T19:20:42.039571+00:00",
-  "lastSyncTime": "2026-09-14T19:20:41.809242+00:00",
+  "generatedAt": "2026-09-14T19:41:18.806767+00:00",
+  "lastSyncTime": "2026-09-14T19:41:18.606689+00:00",
  "recentLimit": 300,
  "report": {
    "architectureCompatibilityBlocks": {
@@ -2134,10 +2134,10 @@
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
-          "ambiguous_runtime": 39,
+          "ambiguous_runtime": 40,
          "参数/模板问题": 2
        },
-        "failureCount": 41,
+        "failureCount": 42,
        "failureRate": 1.0,
        "framework": "vllm_fix_tokenizer",
        "pendingCount": 0,
@@ -2147,8 +2147,8 @@
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
-        "total": 41,
-        "unresolvedFailureCount": 41
+        "total": 42,
+        "unresolvedFailureCount": 42
      },
      "MetaX_c-500|unknown|text-generation": {
        "attributableFailureCount": 0,
@@ -2685,7 +2685,7 @@
        "decisionSuccessRate": 0.0,
        "decisionTotal": 53,
        "failureBreakdown": {
-          "ambiguous_runtime": 41,
+          "ambiguous_runtime": 42,
          "backend_operator": 2,
          "framework_architecture_unsupported": 8,
          "model_load": 1,
@@ -2693,15 +2693,15 @@
          "tokenizer_compatibility": 42,
          "参数/模板问题": 8
        },
-        "failureCount": 106,
+        "failureCount": 107,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 4,
        "successCount": 0,
        "successRate": 0.0,
-        "total": 106,
-        "unresolvedFailureCount": 49
+        "total": 107,
+        "unresolvedFailureCount": 50
      },
      "vllm_tokenizer_patch": {
        "attributableFailureCount": 0,
@@ -2722,7 +2722,7 @@
        "unresolvedFailureCount": 1
      }
    },
-    "generatedAt": "2026-09-14T19:20:42.035024+00:00",
+    "generatedAt": "2026-09-14T19:41:18.800840+00:00",
    "gpuSummaries": {
      "Ascend_910-b3": {
        "attributableFailureCount": 36,
@@ -2917,20 +2917,20 @@
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
-          "ambiguous_runtime": 80,
+          "ambiguous_runtime": 81,
          "memory_capacity": 1,
          "参数/模板问题": 2,
          "验证失败": 23
        },
-        "failureCount": 106,
+        "failureCount": 107,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
-        "total": 106,
-        "unresolvedFailureCount": 105
+        "total": 107,
+        "unresolvedFailureCount": 106
      },
      "MetaX_c-500": {
        "attributableFailureCount": 56,
@@ -4129,6 +4129,29 @@
        "total": 3,
        "unresolvedFailureCount": 3
      },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|none": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "modelType": "qwen2",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
@@ -7348,6 +7371,30 @@
        "total": 2,
        "unresolvedFailureCount": 2
      },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|none|31": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "loadSizeLog2Bucket": 31,
+        "modelType": "qwen2",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
@@ -8882,15 +8929,15 @@
        "unresolvedFailureCount": 0
      }
    },
-    "terminalRecords": 1865,
-    "totalRecords": 1958,
+    "terminalRecords": 1866,
+    "totalRecords": 1959,
    "totals": {
      "attributableFailureCount": 564,
      "decisionFailureRate": 0.8995,
      "decisionSuccessRate": 0.1005,
      "decisionTotal": 627,
      "failureBreakdown": {
-        "ambiguous_runtime": 443,
+        "ambiguous_runtime": 444,
        "backend_operator": 44,
        "framework_architecture_unsupported": 361,
        "memory_capacity": 12,
@@ -8902,15 +8949,15 @@
        "参数/模板问题": 116,
        "验证失败": 673
      },
-      "failureCount": 1802,
+      "failureCount": 1803,
      "failureRate": 0.9662,
      "pendingCount": 0,
      "pendingRate": 0.0,
      "platformFailureCount": 6,
      "successCount": 63,
      "successRate": 0.0338,
-      "total": 1865,
-      "unresolvedFailureCount": 1232
+      "total": 1866,
+      "unresolvedFailureCount": 1233
    },
    "warnings": [
      "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -8948,6 +8995,6 @@
    ]
  },
  "storageMode": "decision_state_only",
-  "summarizedRecords": 1958,
+  "summarizedRecords": 1959,
  "version": 1
 }
--- a/.modelhub_state/recovery_active_tasks.jsonl
+++ b/.modelhub_state/recovery_active_tasks.jsonl
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
--- a/manifest.json
+++ b/manifest.json
@@ -1,24 +1,24 @@
 {
  "agentVersion": "2026.09.04.4",
  "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "f7bf4c27ff0636a8aac7297b8110e36bf2eb14dadaff2a844cf146fcb3a8ed49",
-    ".modelhub_state/architecture_history_backfill.json": "86b9126278dd275b3b663881b280541c93566afe3bd0d7ff512eabe00e76bdd9",
-    ".modelhub_state/market_intelligence.json": "ef7d799edc33e02024bf3395ead007e04fec2975815d58b26e37d6b60fd816ed",
-    ".modelhub_state/official_capabilities.json": "cc9053f9228da10a7362143ccf1d0070fc75a9b72a6ca69fa4892954c4cb7851",
-    ".modelhub_state/outcome_checkpoint.json": "7ca25ca823085a515519c4bc015a942de7662a01bd0fb80fba09e9cd5b29a4ee",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "c374d2890b6dea3f71119fc41178353d43a28109c22227b1b2f8c87985712eeb",
+    ".modelhub_state/architecture_history_backfill.json": "1529e8b37e1e113adc5004771f7a51a71a019fd51cc7a7664cca65f7ff80c8e9",
+    ".modelhub_state/market_intelligence.json": "fc327a964cfa7dda4bd5e9f09328af7554a57cc8fb6c1b5836e8ed3360e95800",
+    ".modelhub_state/official_capabilities.json": "a0e0c350f14fb9b95150844669b1ced642623b584ebb9e76fd784948465f0c69",
+    ".modelhub_state/outcome_checkpoint.json": "aaf006c1f34b5bd512d08218b17a48b2a123d9b19d8b239933a379de9849ce68",
    ".modelhub_state/queue_cleanup_latest.json": "2db00f279cdac43f8f1cc1f62cd63046aca30c207631791fe39472e61beff82c",
    ".modelhub_state/recent_outcomes.jsonl": "3e24fc4737c55e3b6e844dc62b00d58cb1695b8187a84877e351d8333743bcd4",
-    ".modelhub_state/recovery_active_tasks.jsonl": "b106add91f6fcf764858a8691c5898bbfaef18677427efcb1d1d0d20ae98cf45",
-    ".modelhub_state/recovery_intents.jsonl": "45bdc7506d986c26d3dd7311989e647fdead5b0524b486b7330acac6700c01ef",
+    ".modelhub_state/recovery_active_tasks.jsonl": "0d442fd41a5cc0b11fe9b051a678a1968f2571f45247e3b53f20d2a8146176ac",
+    ".modelhub_state/recovery_intents.jsonl": "c08bebd59bde3e14f8f3280e04792c8263cdd2d6a07aaaa071eb763822950c65",
    ".modelhub_state/routing_intelligence.json": "af4cb97462e92efabd50c6673f315901489af2f9a73ba74131b4920a83deca74",
    ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
    ".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
    "ledger/submissions.jsonl": "fcdbf0ebd90f868e698be9fa236188e86ab9c2336badd34a3c1c80b85e4856c8",
-    "outcomes/submissions.jsonl": "59ce2cf35bcd4f2a912ff79cb17689e4d012bcc35e4310c7ce46cadb678b7450"
+    "outcomes/submissions.jsonl": "8fb890b879b6dd4490ac0ca12c60afc318a53eff41db7b050e6034788ded80f8"
  },
-  "generation": 7332,
+  "generation": 7333,
  "phase": "cycle",
  "schemaVersion": 1,
-  "updatedAt": "2026-09-14T19:40:17.936791+00:00",
+  "updatedAt": "2026-09-14T19:43:48.882820+00:00",
  "writerId": "69701e73196b4ac2b3fad0f412335168"
 }
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -439,7 +439,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395862+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.655185+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746453", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395920+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28168623119, "estimatedRequiredGiB": 31.505, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 28190535646, "modelscopeLicense": null, "modelscopeParams": 7584230528, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 28190535646}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.684861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746455", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395914+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ_K", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 79395122602, "estimatedRequiredGiB": 88.75, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 79412319434, "modelscopeLicense": "other", "modelscopeParams": 19984155322, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:jangtq-k", "custom_tag:mixed-precision", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:conversational", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:quantization", "custom_tag:230b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 79412319434}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.618999+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746456", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395892+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-09T21:08:32.656390+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746454", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218174+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 35648665467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.859936+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749146", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218150+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838972, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838972}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.850913+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749148", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218196+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778320, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.864784+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749147", "taskType": "text-generation", "verifyResult": null}