state: generation 16796 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3261,7 +3261,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-26T20:37:53.157789+00:00",
+  "generatedAt": "2026-09-26T20:43:11.243624+00:00",
   "summary": {
     "activeBlockCount": 164,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -1,8 +1,8 @@
 {
-  "communityAttemptedAt": "2026-09-26T20:28:42.571372+00:00",
+  "communityAttemptedAt": "2026-09-26T20:43:54.260490+00:00",
   "communityError": null,
   "communitySample": {},
-  "communityUpdatedAt": "2026-09-26T20:28:42.571372+00:00",
+  "communityUpdatedAt": "2026-09-26T20:43:54.260490+00:00",
   "frameworkAttemptedAt": "2026-09-26T18:41:56.359307+00:00",
   "frameworkError": null,
   "frameworkStats": {
@@ -396,7 +396,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-26T20:42:08.851053+00:00",
+  "generatedAt": "2026-09-26T20:43:54.260490+00:00",
   "gpuStats": {
     "Ascend_910-b4": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-26T20:42:08.851053+00:00",
+  "catalogUpdatedAt": "2026-09-26T20:43:54.260490+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-26T20:42:08.851053+00:00",
+  "generatedAt": "2026-09-26T20:43:54.260490+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6265,6 +6265,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-26T20:42:08.851053+00:00",
+  "taskTreeUpdatedAt": "2026-09-26T20:43:54.260490+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-26T20:25:43.917474+00:00",
+  "generatedAt": "2026-09-26T20:43:11.166063+00:00",
-  "lastSyncTime": "2026-09-26T20:25:43.664889+00:00",
+  "lastSyncTime": "2026-09-26T20:43:10.857789+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3870,12 +3870,12 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 24,
         "failureBreakdown": {
-          "ambiguous_runtime": 34,
+          "ambiguous_runtime": 35,
           "framework_architecture_unsupported": 23,
           "memory_capacity": 1,
           "参数/模板问题": 1
         },
-        "failureCount": 59,
+        "failureCount": 60,
         "failureRate": 1.0,
         "framework": "vllm",
         "pendingCount": 0,
@@ -3885,8 +3885,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 59,
+        "total": 60,
-        "unresolvedFailureCount": 35
+        "unresolvedFailureCount": 36
       },
       "Cambricon_mlu-370-x8|unknown|feature_emb": {
         "attributableFailureCount": 0,
@@ -5961,7 +5961,7 @@
         "decisionSuccessRate": 0.0261,
         "decisionTotal": 3720,
         "failureBreakdown": {
-          "ambiguous_runtime": 1574,
+          "ambiguous_runtime": 1575,
           "architecture_compatibility": 112,
           "attention_backend": 3,
           "backend_operator": 93,
@@ -5975,15 +5975,15 @@
           "tokenizer_compatibility": 416,
           "参数/模板问题": 50
         },
-        "failureCount": 6117,
+        "failureCount": 6118,
         "failureRate": 0.9844,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 870,
         "successCount": 97,
         "successRate": 0.0156,
-        "total": 6214,
+        "total": 6215,
-        "unresolvedFailureCount": 1624
+        "unresolvedFailureCount": 1625
       },
       "vllm-customized": {
         "attributableFailureCount": 13,
@@ -6133,7 +6133,7 @@
         "unresolvedFailureCount": 196
       }
     },
-    "generatedAt": "2026-09-26T20:25:43.905349+00:00",
+    "generatedAt": "2026-09-26T20:43:11.109898+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 102,
@@ -6225,7 +6225,7 @@
         "decisionSuccessRate": 0.0894,
         "decisionTotal": 817,
         "failureBreakdown": {
-          "ambiguous_runtime": 489,
+          "ambiguous_runtime": 490,
           "architecture_compatibility": 53,
           "context_length": 48,
           "framework_architecture_unsupported": 297,
@@ -6238,15 +6238,15 @@
           "日志缺失": 13,
           "验证失败": 42
         },
-        "failureCount": 1590,
+        "failureCount": 1591,
         "failureRate": 0.9561,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 16,
         "successCount": 73,
         "successRate": 0.0439,
-        "total": 1663,
+        "total": 1664,
-        "unresolvedFailureCount": 830
+        "unresolvedFailureCount": 831
       },
       "Cambricon_mlu-370-x8": {
         "attributableFailureCount": 60,
@@ -11319,9 +11319,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 4
+          "ambiguous_runtime": 5
         },
-        "failureCount": 4,
+        "failureCount": 5,
         "failureRate": 1.0,
         "framework": "vllm",
         "modelType": "llama",
@@ -11333,8 +11333,8 @@
         "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": {
         "attributableFailureCount": 0,
@@ -33929,6 +33929,30 @@
         "total": 5,
         "unresolvedFailureCount": 5
       },
+      "Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|27": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "loadSizeLog2Bucket": 27,
+        "modelType": "llama",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "compressed-tensors",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Cambricon_mlu-370-x4",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|30": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -50930,15 +50954,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17047,
+    "terminalRecords": 17048,
-    "totalRecords": 17268,
+    "totalRecords": 17269,
     "totals": {
       "attributableFailureCount": 6114,
       "decisionFailureRate": 0.8636,
       "decisionSuccessRate": 0.1364,
       "decisionTotal": 7080,
       "failureBreakdown": {
-        "ambiguous_runtime": 4408,
+        "ambiguous_runtime": 4409,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 128,
@@ -50954,30 +50978,30 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16081,
+      "failureCount": 16082,
       "failureRate": 0.9433,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 937,
       "successCount": 966,
       "successRate": 0.0567,
-      "total": 17047,
+      "total": 17048,
-      "unresolvedFailureCount": 9030
+      "unresolvedFailureCount": 9031
     },
     "warnings": [
       "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_mrv-100 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 MetaX_c-500 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 Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Cambricon_mlu-370-x8 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 Ascend_910-b4 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
       "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 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -50990,6 +51014,7 @@
       "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。",
       "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 Cambricon_mlu-370-x4|vllm-mlu|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-x8|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 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 Ascend_910-b4|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 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51015,11 +51040,10 @@
       "组合 Cambricon_mlu-370-x4|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 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 Cambricon_mlu-370-x8|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-x8|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 MetaX_c-500|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": 17268,
+  "summarizedRecords": 17269,
   "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": "db47ddb4cb63d53ac64a2f5e80780dff91168824d98062b2ad67fcc96417d953",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "4876a65ade63479dc851b646309a0c22cf3af4449a01d3b26df87491fc171255",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "ae46009c7f526cceec83233a16b876f6c1aeef05fcaadcc501384c7cba51c01d",
+    ".modelhub_state/market_intelligence.json": "1c4eebe2ac519f5b875cf5278dfcdde6b6b96c03342ab121f497744f97e9e0cf",
-    ".modelhub_state/official_capabilities.json": "d34d1a790864ceb26d8a2830b96b3bf173aa77356bf56b631030b256147a16c2",
+    ".modelhub_state/official_capabilities.json": "a35875452e6ef60eeca5541279d6ad23a7a904ee71f6951f491475df56f4c2f7",
-    ".modelhub_state/outcome_checkpoint.json": "bf65ecf6939ac6f4af609113af4bbeff162c191b7e4543505ecb0c8dc777c668",
+    ".modelhub_state/outcome_checkpoint.json": "59e10e36020dacc9882d22707b45bba5024ebe95b72c251f1befca70c793a775",
     ".modelhub_state/queue_cleanup_latest.json": "69b07b4c7f0e1a61310077a9b0cf5b45c959484d402ad60f0304381993afe5e7",
     ".modelhub_state/recent_outcomes.jsonl": "fc824b550dd2cad27bf01dd347e6709336ab8153748ad6b4ef4b0591070dd1dc",
-    ".modelhub_state/recovery_active_tasks.jsonl": "09188b09f5746edb4b852079899909bf502868cfb1efc00c03c7e7bcc2ebce55",
+    ".modelhub_state/recovery_active_tasks.jsonl": "ad61b373a6fb42eefc1d370dabeb6e9b5dac661fa1a4849c47756c61d5593d66",
-    ".modelhub_state/recovery_intents.jsonl": "ba05bb8359c1d46c7f3637c46b85da4d70da0b8c631870dc284f00089bd72fef",
+    ".modelhub_state/recovery_intents.jsonl": "5f4dae4393c47e6e190bf1d936571a588fdd5e710bcaadd4e9746746bd13649c",
     ".modelhub_state/routing_intelligence.json": "519577e231ce3934d8378cbf1f13f1356f0576991f528675ded72ec2b8b3c804",
     ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
     ".modelhub_state/worker_crashes.jsonl": "ccd40ad86ab5068ea1c3520a48fa733cf2e4b357ae5abb95ff00728d5d1b5487",
     "ledger/submissions.jsonl": "147bc1ffeef99da1f8b8622f72019c684d7f128074a57c2d73e174eafc38ae1d",
-    "outcomes/submissions.jsonl": "7930cbebe1be15cdba419d58431f6656ebbc39c6b1b27541580f0bd17e296048"
+    "outcomes/submissions.jsonl": "be1006f7084c5a406158cab27e940087c1a9c2d2dab42c25f10a1921db96797f"
   },
-  "generation": 16795,
+  "generation": 16796,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-26T20:42:09.657740+00:00",
+  "updatedAt": "2026-09-26T20:44:04.774193+00:00",
   "writerId": "08206cb1993a433e83f1d3e297db2d2e"
 }

outcomes/submissions.jsonl

@@ -360,7 +360,6 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:21:49.901883+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "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": 7860673858}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.922099+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970574", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:21:49.902090+00:00", "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.856488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970570", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.902083+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142341, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:41.835421+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970584", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901746+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "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": 223236688}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:42.084586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970594", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901918+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-20T04:14:42.093442+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901870+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:15:36.946953+00:00", "targetGpu": "Vastai_va16", "taskId": "4970616", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856383+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T04:26:45.109939+00:00", "targetGpu": "Vastai_va16", "taskId": "4970729", "taskType": "text-generation", "verifyResult": null}