state: generation 17098 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3261,7 +3261,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-27T05:58:13.058442+00:00",
+  "generatedAt": "2026-09-27T06:04:51.309985+00:00",
   "summary": {
     "activeBlockCount": 164,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -396,7 +396,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-27T06:03:48.788559+00:00",
+  "generatedAt": "2026-09-27T06:05:36.163643+00:00",
   "gpuStats": {
     "Ascend_910-b4": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-27T06:03:48.788559+00:00",
+  "catalogUpdatedAt": "2026-09-27T06:05:36.163643+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-27T06:03:48.788559+00:00",
+  "generatedAt": "2026-09-27T06:05:36.163643+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6190,6 +6190,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-27T06:03:48.788559+00:00",
+  "taskTreeUpdatedAt": "2026-09-27T06:05:36.163643+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-27T04:31:49.086558+00:00",
+  "generatedAt": "2026-09-27T06:04:51.226698+00:00",
-  "lastSyncTime": "2026-09-27T04:31:48.760568+00:00",
+  "lastSyncTime": "2026-09-27T06:04:50.958739+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3871,12 +3871,12 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 24,
         "failureBreakdown": {
-          "ambiguous_runtime": 38,
+          "ambiguous_runtime": 39,
           "framework_architecture_unsupported": 23,
           "memory_capacity": 1,
           "参数/模板问题": 1
         },
-        "failureCount": 63,
+        "failureCount": 64,
         "failureRate": 1.0,
         "framework": "vllm",
         "pendingCount": 0,
@@ -3886,8 +3886,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 63,
+        "total": 64,
-        "unresolvedFailureCount": 39
+        "unresolvedFailureCount": 40
       },
       "Cambricon_mlu-370-x8|unknown|feature_emb": {
         "attributableFailureCount": 0,
@@ -5962,7 +5962,7 @@
         "decisionSuccessRate": 0.0261,
         "decisionTotal": 3720,
         "failureBreakdown": {
-          "ambiguous_runtime": 1578,
+          "ambiguous_runtime": 1579,
           "architecture_compatibility": 112,
           "attention_backend": 3,
           "backend_operator": 93,
@@ -5976,15 +5976,15 @@
           "tokenizer_compatibility": 416,
           "参数/模板问题": 50
         },
-        "failureCount": 6122,
+        "failureCount": 6123,
         "failureRate": 0.9844,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 871,
         "successCount": 97,
         "successRate": 0.0156,
-        "total": 6219,
+        "total": 6220,
-        "unresolvedFailureCount": 1628
+        "unresolvedFailureCount": 1629
       },
       "vllm-customized": {
         "attributableFailureCount": 13,
@@ -6134,7 +6134,7 @@
         "unresolvedFailureCount": 197
       }
     },
-    "generatedAt": "2026-09-27T04:31:49.074572+00:00",
+    "generatedAt": "2026-09-27T06:04:51.214272+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 102,
@@ -6226,7 +6226,7 @@
         "decisionSuccessRate": 0.0894,
         "decisionTotal": 817,
         "failureBreakdown": {
-          "ambiguous_runtime": 493,
+          "ambiguous_runtime": 494,
           "architecture_compatibility": 53,
           "context_length": 48,
           "framework_architecture_unsupported": 297,
@@ -6239,15 +6239,15 @@
           "日志缺失": 13,
           "验证失败": 42
         },
-        "failureCount": 1595,
+        "failureCount": 1596,
-        "failureRate": 0.9562,
+        "failureRate": 0.9563,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 16,
         "successCount": 73,
-        "successRate": 0.0438,
+        "successRate": 0.0437,
-        "total": 1668,
+        "total": 1669,
-        "unresolvedFailureCount": 835
+        "unresolvedFailureCount": 836
       },
       "Cambricon_mlu-370-x8": {
         "attributableFailureCount": 60,
@@ -11343,9 +11343,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 7
+          "ambiguous_runtime": 8
         },
-        "failureCount": 7,
+        "failureCount": 8,
         "failureRate": 1.0,
         "framework": "vllm",
         "modelType": "llama",
@@ -11357,8 +11357,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 7,
+        "total": 8,
-        "unresolvedFailureCount": 7
+        "unresolvedFailureCount": 8
       },
       "Cambricon_mlu-370-x4|vllm|text-generation|llama|none": {
         "attributableFailureCount": 0,
@@ -34152,9 +34152,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 4
+          "ambiguous_runtime": 5
         },
-        "failureCount": 4,
+        "failureCount": 5,
         "failureRate": 1.0,
         "framework": "vllm",
         "loadSizeLog2Bucket": 33,
@@ -34167,8 +34167,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 4,
+        "total": 5,
-        "unresolvedFailureCount": 4
+        "unresolvedFailureCount": 5
       },
       "Cambricon_mlu-370-x4|vllm|text-generation|llama|none|30": {
         "attributableFailureCount": 0,
@@ -51171,15 +51171,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17055,
+    "terminalRecords": 17056,
-    "totalRecords": 17276,
+    "totalRecords": 17277,
     "totals": {
       "attributableFailureCount": 6114,
       "decisionFailureRate": 0.8636,
       "decisionSuccessRate": 0.1364,
       "decisionTotal": 7080,
       "failureBreakdown": {
-        "ambiguous_runtime": 4414,
+        "ambiguous_runtime": 4415,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 128,
@@ -51195,15 +51195,15 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16089,
+      "failureCount": 16090,
       "failureRate": 0.9434,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 938,
       "successCount": 966,
       "successRate": 0.0566,
-      "total": 17055,
+      "total": 17056,
-      "unresolvedFailureCount": 9037
+      "unresolvedFailureCount": 9038
     },
     "warnings": [
       "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -51211,15 +51211,15 @@
       "GPU Ascend_910-b4 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 MetaX_c-500 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 Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 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 hygon_k100-ai 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 Kunlunxin_p-800 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
       "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 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51243,7 +51243,6 @@
       "组合 Cambricon_mlu-370-x4|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|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 hygon_k100-ai|vllm-patch-tokenizer|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_fix_tokenizer|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 Mthreads_s4000|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_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51257,10 +51256,11 @@
       "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 Mthreads_s4000|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_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 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
+      "组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
+      "组合 Vastai_va16|vllm_fix_tokenizer|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": 17276,
+  "summarizedRecords": 17277,
   "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": "9c682a3166ab6d7cd53791dad758bdd0529b29f785c4a872a4dbcac17888bb22",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "6f31ebde28d7dc3ae3bc1f84b76c2961b904d3d9920eba3e5c0af208eace9360",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "546fe5027cdfdcc05038374be63266e41113ee0b8e38ffcb2654510bde75aee4",
+    ".modelhub_state/market_intelligence.json": "af90631875798939f87b371f7d55141212874e8dc03e2425a0b4b333d02b4f1d",
-    ".modelhub_state/official_capabilities.json": "2525dcb873ecbd62e46fbad3928442e0ca8b4acb54c89ccf224988f6460b99d8",
+    ".modelhub_state/official_capabilities.json": "5452cf562e5f874f7a722a091b6b8510ca7f0159192b1e41a12e8304f89adbfa",
-    ".modelhub_state/outcome_checkpoint.json": "39ccf229815ac385b96bff98a937b44d78461ed396fe260dd05d34ccea44182d",
+    ".modelhub_state/outcome_checkpoint.json": "7650d5d213d20c36ee37ba3be33b72454d423504c90fc601e020b9f2b2b27e40",
     ".modelhub_state/queue_cleanup_latest.json": "b69db35ea5af4823fabc8c6619e19c96122a741133f3b8872b1f872f790bc44e",
     ".modelhub_state/recent_outcomes.jsonl": "ee660e2e4dd35948a82b7313a4633d5f5bc6f9dbea4bd4efbc7fdd8fa633478f",
-    ".modelhub_state/recovery_active_tasks.jsonl": "0702982b523b67edf04819ef08a82052454fa6a0a790475f96787120373fdd09",
+    ".modelhub_state/recovery_active_tasks.jsonl": "9a2c62b3d9b2eda0b39c0faa72adc90524d2a32c8668f7c3ff81f94c89ad8b60",
-    ".modelhub_state/recovery_intents.jsonl": "b5d9946958d400788b9a9cf69ce3015cdc3aa7886cc6c961f3e187783c912fcf",
+    ".modelhub_state/recovery_intents.jsonl": "c371743c666f2415f69ae448b16c31a875239f682703bce757e52120b0d2cf52",
     ".modelhub_state/routing_intelligence.json": "ebb91dffa792ca34d1b70741792a67397b3e1b5cdc53a0685b27091fd0cffe86",
     ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
     ".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10",
     "ledger/submissions.jsonl": "9c81a6b4d3cd8b4832b1644a04e732d0e29d5ce9635ee6f738f72afc7c0be6e1",
-    "outcomes/submissions.jsonl": "98d23c0b5b8ac847c464c746e07949b779475779f0f59984b36e6b8ab7481a15"
+    "outcomes/submissions.jsonl": "6fe1f1082aebb26650f3ce3020ed573d58e29727606a8c841fb0214770d8fc9e"
   },
-  "generation": 17097,
+  "generation": 17098,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-27T06:03:49.476164+00:00",
+  "updatedAt": "2026-09-27T06:05:39.942160+00:00",
   "writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea"
 }

outcomes/submissions.jsonl

@@ -440,7 +440,6 @@
 {"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": "2026-09-21T10:33:30.477723+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:20.876763+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991856", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477654+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-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": 9093251901, "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": 9093251901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.095468+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991859", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477648+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:37.185982+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991860", "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": "2026-09-21T10:33:30.477787+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479112, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:49.174012+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991865", "taskType": "text-generation", "verifyResult": null}