state: generation 21575 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -2758,7 +2758,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-10-06T21:47:58.757127+00:00",
+  "generatedAt": "2026-10-06T22:49:30.638827+00:00",
   "summary": {
     "activeBlockCount": 139,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -434,7 +434,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-10-06T22:46:29.456668+00:00",
+  "generatedAt": "2026-10-06T22:51:28.560886+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-10-06T22:46:29.456668+00:00",
+  "catalogUpdatedAt": "2026-10-06T22:51:28.560886+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-10-06T22:46:29.456668+00:00",
+  "generatedAt": "2026-10-06T22:51:28.560886+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6424,6 +6424,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-10-06T22:46:29.456668+00:00",
+  "taskTreeUpdatedAt": "2026-10-06T22:51:28.560886+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-10-06T20:38:38.329289+00:00",
+  "generatedAt": "2026-10-06T22:49:30.543549+00:00",
-  "lastSyncTime": "2026-10-06T20:38:38.063592+00:00",
+  "lastSyncTime": "2026-10-06T22:49:30.255985+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -2298,25 +2298,6 @@
         "targetGpu": "Mthreads_s4000",
         "taskType": "text-generation"
       },
-      "mthreads_s4000|vllm|text-generation|model_type:qwen3_vl": {
-        "architectureSignature": "model_type:qwen3_vl",
-        "architectures": [],
-        "evidenceCount": 1,
-        "expiresAt": "2026-10-06T21:23:21+00:00",
-        "framework": "vllm",
-        "latestFailureAt": "2026-09-06T21:23:21+00:00",
-        "latestSuccessfulAt": null,
-        "matchType": "model_type",
-        "modelType": "qwen3_vl",
-        "sourceModelIds": [
-          "metax-tech/Qwen3-VL-8B-Instruct_W8A8"
-        ],
-        "sourceTaskIds": [
-          "4591579"
-        ],
-        "targetGpu": "Mthreads_s4000",
-        "taskType": "text-generation"
-      },
       "mthreads_s4000|vllm|text-generation|model_type:rwkv7": {
         "architectureSignature": "model_type:rwkv7",
         "architectures": [],
@@ -2782,7 +2763,7 @@
       }
     },
     "architectureCompatibilitySummary": {
-      "activeBlockCount": 140,
+      "activeBlockCount": 139,
       "byGpuFramework": {
         "Ascend_910-b3|vllm": 9,
         "Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2801,7 +2782,7 @@
         "Kunlunxin_p-800|vllm": 10,
         "Kunlunxin_p-800|vllm_tokenizer_patch": 9,
         "MetaX_c-500|vllm": 1,
-        "Mthreads_s4000|vllm": 6,
+        "Mthreads_s4000|vllm": 5,
         "Sunrise_pt-200-x1|vllm": 3,
         "Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
         "Vastai_va16|vllm": 13,
@@ -4663,7 +4644,7 @@
         "decisionSuccessRate": 0.0395,
         "decisionTotal": 659,
         "failureBreakdown": {
-          "ambiguous_runtime": 133,
+          "ambiguous_runtime": 134,
           "architecture_compatibility": 20,
           "backend_operator": 43,
           "context_length": 46,
@@ -4676,7 +4657,7 @@
           "tokenizer_compatibility": 79,
           "参数/模板问题": 9
         },
-        "failureCount": 778,
+        "failureCount": 779,
         "failureRate": 0.9677,
         "framework": "vllm",
         "pendingCount": 0,
@@ -4686,8 +4667,8 @@
         "successRate": 0.0323,
         "targetGpu": "MetaX_c-500",
         "taskType": "text-generation",
-        "total": 804,
+        "total": 805,
-        "unresolvedFailureCount": 142
+        "unresolvedFailureCount": 143
       },
       "MetaX_c-500|vllm|unknown": {
         "attributableFailureCount": 1,
@@ -5484,7 +5465,7 @@
         "decisionSuccessRate": 0.0278,
         "decisionTotal": 3771,
         "failureBreakdown": {
-          "ambiguous_runtime": 1600,
+          "ambiguous_runtime": 1601,
           "architecture_compatibility": 112,
           "attention_backend": 3,
           "backend_operator": 94,
@@ -5498,15 +5479,15 @@
           "tokenizer_compatibility": 420,
           "参数/模板问题": 50
         },
-        "failureCount": 6195,
+        "failureCount": 6196,
         "failureRate": 0.9833,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 879,
         "successCount": 105,
         "successRate": 0.0167,
-        "total": 6300,
+        "total": 6301,
-        "unresolvedFailureCount": 1650
+        "unresolvedFailureCount": 1651
       },
       "vllm-customized": {
         "attributableFailureCount": 15,
@@ -5656,7 +5637,7 @@
         "unresolvedFailureCount": 235
       }
     },
-    "generatedAt": "2026-10-06T20:38:38.314877+00:00",
+    "generatedAt": "2026-10-06T22:49:30.468064+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 119,
@@ -5936,7 +5917,7 @@
         "decisionSuccessRate": 0.1804,
         "decisionTotal": 815,
         "failureBreakdown": {
-          "ambiguous_runtime": 305,
+          "ambiguous_runtime": 306,
           "architecture_compatibility": 21,
           "backend_operator": 43,
           "context_length": 59,
@@ -5951,15 +5932,15 @@
           "日志缺失": 15,
           "验证失败": 48
         },
-        "failureCount": 1439,
+        "failureCount": 1440,
-        "failureRate": 0.9073,
+        "failureRate": 0.9074,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 5,
         "successCount": 147,
-        "successRate": 0.0927,
+        "successRate": 0.0926,
-        "total": 1586,
+        "total": 1587,
-        "unresolvedFailureCount": 766
+        "unresolvedFailureCount": 767
       },
       "Mthreads_s4000": {
         "attributableFailureCount": 84,
@@ -20630,6 +20611,29 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "MetaX_c-500|vllm|text-generation|gemma3|none": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "modelType": "gemma3",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "MetaX_c-500",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "MetaX_c-500|vllm|text-generation|gpt_oss|compressed-tensors": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -51204,6 +51208,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "MetaX_c-500|vllm|text-generation|gemma3|none|35": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "loadSizeLog2Bucket": 35,
+        "modelType": "gemma3",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "MetaX_c-500",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "MetaX_c-500|vllm|text-generation|gpt_oss|compressed-tensors|35": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -57593,15 +57621,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17344,
+    "terminalRecords": 17345,
-    "totalRecords": 17568,
+    "totalRecords": 17569,
     "totals": {
       "attributableFailureCount": 6236,
       "decisionFailureRate": 0.8644,
       "decisionSuccessRate": 0.1356,
       "decisionTotal": 7214,
       "failureBreakdown": {
-        "ambiguous_runtime": 4550,
+        "ambiguous_runtime": 4551,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 129,
@@ -57617,15 +57645,15 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16366,
+      "failureCount": 16367,
       "failureRate": 0.9436,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 952,
       "successCount": 978,
       "successRate": 0.0564,
-      "total": 17344,
+      "total": 17345,
-      "unresolvedFailureCount": 9178
+      "unresolvedFailureCount": 9179
     },
     "warnings": [
       "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -57634,14 +57662,14 @@
       "GPU hygon_k100-ai 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 Ascend_910-b3 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 Iluvatar_mrv-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 Cambricon_mlu-370-x8 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 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 Iluvatar_bi-100 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
       "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 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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57685,6 +57713,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 17568,
+  "summarizedRecords": 17569,
   "version": 1
 }

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.04.4",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "8f1352c815e13a23379f6ed8f6ed0cfa616e1d0cf492f2176ec69356b4646ae2",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "7c61d831138f4f7fbf97cf214c51ae52f8f7edb7e7d67af42c29c58713443b34",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "1fba755561f3b361af74027149065de9986f947116e48d064e9f00454e3efb58",
+    ".modelhub_state/market_intelligence.json": "fb9d08dd5b6a67f1a28b1083877f947812968620efbdd2afa3e8d1e65399ecfb",
-    ".modelhub_state/official_capabilities.json": "42a384b90b2fed7718e1fe19f508d161d4be823a871000357a6e57d686c0ec2b",
+    ".modelhub_state/official_capabilities.json": "012ec875b8d899cb5e3f9f27637ef632641c4b7466920afd796cf2b8e9bda2d2",
-    ".modelhub_state/outcome_checkpoint.json": "4043853adc6db53ef28d873827418e041119ff2a9535cf53bd6b93269ecec4a7",
+    ".modelhub_state/outcome_checkpoint.json": "bf1e1e9cd6d045e616224a1139442d652c039734a793b81c912b409ccf404f87",
     ".modelhub_state/queue_cleanup_latest.json": "811650bde1021c3ae4227111e561fcae79b8445c1c6034885200e4ffbf955099",
     ".modelhub_state/recent_outcomes.jsonl": "ac1c51b9a94e2169f287e9224a1482891df92776f70358b8eb416d7aa995d25f",
-    ".modelhub_state/recovery_active_tasks.jsonl": "7b55f8c93c6eb822784fc34889191635231eaad0a3b21e720d072363cd304b44",
+    ".modelhub_state/recovery_active_tasks.jsonl": "e492d972372a6fc38dfd53d7a8f6910f3cc4666801a5aa130e48ce1ace859146",
-    ".modelhub_state/recovery_intents.jsonl": "0394df6adeb5f70de73ac76193fee333a80ee7585c5de3bb2d3c8677c918bbf8",
+    ".modelhub_state/recovery_intents.jsonl": "5da5e4290dc0dce31a36163f4c9259f546f8f1f333dc545848b2079bcccd1117",
     ".modelhub_state/routing_intelligence.json": "47d23c5b51149c8894f474dd3b08f8e2cb621df198006bd80d30522c0258d20c",
     ".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
     ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
     "ledger/submissions.jsonl": "6bf74c5fb3f9a185432fc79920687dc3bd2c30ced8ac948712dedca17a1ee49a",
-    "outcomes/submissions.jsonl": "1f2c1c5a65a26b3a028e466a176607caf01faa1002e46095d5a637a6e2279429"
+    "outcomes/submissions.jsonl": "82df39c5ce5d33645a57b82ef782c9b9f07d6ec3cf6a096bb095175a8a437b16"
   },
-  "generation": 21574,
+  "generation": 21575,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-06T22:48:28.806257+00:00",
+  "updatedAt": "2026-10-06T22:51:34.334554+00:00",
   "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
 }

outcomes/submissions.jsonl

@@ -144,7 +144,6 @@
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766033+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671236+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "2026-09-20T03:58:35.447710+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970349", "taskType": "text-generation", "verifyResult": null}