state: generation 11670 (intent)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -2768,7 +2768,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-21T19:49:38.240370+00:00",
+  "generatedAt": "2026-09-21T19:52:34.527546+00:00",
   "summary": {
     "activeBlockCount": 139,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -434,7 +434,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-21T19:51:22.388222+00:00",
+  "generatedAt": "2026-09-21T19:52:47.663317+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-21T19:51:22.388222+00:00",
+  "catalogUpdatedAt": "2026-09-21T19:52:47.663317+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-21T19:51:22.388222+00:00",
+  "generatedAt": "2026-09-21T19:52:47.663317+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6886,6 +6886,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-21T19:51:22.388222+00:00",
+  "taskTreeUpdatedAt": "2026-09-21T19:52:47.663317+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-21T19:49:38.160009+00:00",
+  "generatedAt": "2026-09-21T19:52:34.453108+00:00",
-  "lastSyncTime": "2026-09-21T19:49:37.657161+00:00",
+  "lastSyncTime": "2026-09-21T19:52:34.157602+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3347,16 +3347,16 @@
         "unresolvedFailureCount": 20
       },
       "Cambricon_mlu-370-x4|vllm|text-generation": {
-        "attributableFailureCount": 3,
+        "attributableFailureCount": 4,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 3,
+        "decisionTotal": 4,
         "failureBreakdown": {
           "ambiguous_runtime": 1,
-          "framework_architecture_unsupported": 3,
+          "framework_architecture_unsupported": 4,
           "参数/模板问题": 1
         },
-        "failureCount": 5,
+        "failureCount": 6,
         "failureRate": 1.0,
         "framework": "vllm",
         "pendingCount": 0,
@@ -3366,7 +3366,7 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 5,
+        "total": 6,
         "unresolvedFailureCount": 2
       },
       "Cambricon_mlu-370-x8|unknown|feature_emb": {
@@ -5421,17 +5421,17 @@
         "unresolvedFailureCount": 6446
       },
       "vllm": {
-        "attributableFailureCount": 3541,
+        "attributableFailureCount": 3542,
         "decisionFailureRate": 0.9758,
         "decisionSuccessRate": 0.0242,
-        "decisionTotal": 3629,
+        "decisionTotal": 3630,
         "failureBreakdown": {
           "ambiguous_runtime": 1497,
           "architecture_compatibility": 112,
           "attention_backend": 1,
           "backend_operator": 84,
           "context_length": 161,
-          "framework_architecture_unsupported": 1308,
+          "framework_architecture_unsupported": 1309,
           "memory_capacity": 722,
           "model_load": 207,
           "platform_infrastructure": 865,
@@ -5440,14 +5440,14 @@
           "tokenizer_compatibility": 412,
           "参数/模板问题": 46
         },
-        "failureCount": 5949,
+        "failureCount": 5950,
         "failureRate": 0.9854,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 865,
         "successCount": 88,
         "successRate": 0.0146,
-        "total": 6037,
+        "total": 6038,
         "unresolvedFailureCount": 1543
       },
       "vllm-customized": {
@@ -5594,7 +5594,7 @@
         "unresolvedFailureCount": 107
       }
     },
-    "generatedAt": "2026-09-21T19:49:38.148216+00:00",
+    "generatedAt": "2026-09-21T19:52:34.442165+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 99,
@@ -5681,15 +5681,15 @@
         "unresolvedFailureCount": 483
       },
       "Cambricon_mlu-370-x4": {
-        "attributableFailureCount": 716,
+        "attributableFailureCount": 717,
-        "decisionFailureRate": 0.9075,
+        "decisionFailureRate": 0.9076,
-        "decisionSuccessRate": 0.0925,
+        "decisionSuccessRate": 0.0924,
-        "decisionTotal": 789,
+        "decisionTotal": 790,
         "failureBreakdown": {
           "ambiguous_runtime": 435,
           "architecture_compatibility": 53,
           "context_length": 48,
-          "framework_architecture_unsupported": 272,
+          "framework_architecture_unsupported": 273,
           "memory_capacity": 218,
           "model_load": 5,
           "platform_infrastructure": 15,
@@ -5699,14 +5699,14 @@
           "日志缺失": 13,
           "验证失败": 40
         },
-        "failureCount": 1505,
+        "failureCount": 1506,
-        "failureRate": 0.9537,
+        "failureRate": 0.9538,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 15,
         "successCount": 73,
-        "successRate": 0.0463,
+        "successRate": 0.0462,
-        "total": 1578,
+        "total": 1579,
         "unresolvedFailureCount": 774
       },
       "Cambricon_mlu-370-x8": {
@@ -9548,6 +9548,29 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|none": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "modelType": "spark2_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Cambricon_mlu-370-x4",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -26457,6 +26480,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|none|31": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "loadSizeLog2Bucket": 31,
+        "modelType": "spark2_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Cambricon_mlu-370-x4",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none|33": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -37590,20 +37637,20 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 16387,
+    "terminalRecords": 16388,
-    "totalRecords": 16581,
+    "totalRecords": 16582,
     "totals": {
-      "attributableFailureCount": 5908,
+      "attributableFailureCount": 5909,
       "decisionFailureRate": 0.862,
       "decisionSuccessRate": 0.138,
-      "decisionTotal": 6854,
+      "decisionTotal": 6855,
       "failureBreakdown": {
         "ambiguous_runtime": 4024,
         "architecture_compatibility": 212,
         "attention_backend": 1,
         "backend_operator": 104,
         "context_length": 321,
-        "framework_architecture_unsupported": 2086,
+        "framework_architecture_unsupported": 2087,
         "memory_capacity": 1199,
         "model_load": 499,
         "platform_infrastructure": 925,
@@ -37614,31 +37661,31 @@
         "日志缺失": 719,
         "验证失败": 674
       },
-      "failureCount": 15441,
+      "failureCount": 15442,
       "failureRate": 0.9423,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 925,
       "successCount": 946,
       "successRate": 0.0577,
-      "total": 16387,
+      "total": 16388,
       "unresolvedFailureCount": 8608
     },
     "warnings": [
       "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。",
-      "GPU Cambricon_mlu-370-x8 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 MetaX_c-500 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 Iluvatar_bi-100 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-b3 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 Cambricon_mlu-370-x4 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-x8 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-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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
       "组合 Iluvatar_bi-150|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 Sunrise_pt-200-x1|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 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。",
@@ -37678,6 +37725,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 16581,
+  "summarizedRecords": 16582,
   "version": 1
 }

.modelhub_state/recovery_intents.jsonl

@@ -2277,6 +2277,15 @@
 {"batchId": "77c487ce74c3435d8ab3a649afb198ab", "completedAt": "2026-09-21T19:37:12.837537+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:37:11.217795+00:00", "framework": "vllm-mlu", "intentId": "53881eb74f5b4ec1b37f865a0ee40757", "lastModified": "2026-09-21T18:28:31+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g8-v2_C", "reason": null, "reconciledAt": "2026-09-21T19:49:57.781030+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006370", "taskType": "text-generation"}
 {"batchId": "77c487ce74c3435d8ab3a649afb198ab", "completedAt": "2026-09-21T19:37:12.837540+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:37:11.217856+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6c39e8b19e53420794e745818fa2b66d", "lastModified": "2026-09-21T18:48:50+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge", "reason": null, "reconciledAt": "2026-09-21T19:49:57.779299+00:00", "repoId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5006368", "taskType": "text-generation"}
 {"batchId": "bd2f89ade5594cb3a4fa1b1374160b5c", "completedAt": "2026-09-21T19:49:53.915435+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:49:52.077460+00:00", "framework": "vllm-customized", "intentId": "cf78d4eb48ba4de58804bb206289e065", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "reason": null, "reconciledAt": "2026-09-21T19:49:57.781836+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876137+00:00", "framework": "vllm-mlu", "intentId": "14120764334f415fbbb6d698ba797998", "lastModified": "2026-09-21T18:44:33+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876279+00:00", "framework": "vllm-mlu", "intentId": "476fc3cc899c4b0896270e04522502cf", "lastModified": "2026-09-21T18:38:06+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "repoId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876348+00:00", "framework": "vllm-mlu", "intentId": "e81974ce47694f2c92c2974811589ed2", "lastModified": "2026-09-21T18:45:44+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876412+00:00", "framework": "vllm-mlu", "intentId": "c3826f59b3094840bb6c028deb8c8ac5", "lastModified": "2026-09-21T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "repoId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876476+00:00", "framework": "vllm-mlu", "intentId": "9b992f2c1caf49c6bb1e5e5ef453247e", "lastModified": "2026-09-21T18:42:39+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "repoId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876539+00:00", "framework": "vllm-mlu", "intentId": "27e8dc70907e4f918a747df6e5d6b4ca", "lastModified": "2026-09-21T18:39:37+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "repoId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876602+00:00", "framework": "vllm", "intentId": "27db0d5b0ed2446a9087527b204e962b", "lastModified": "2026-09-21T18:48:50+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge", "repoId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876654+00:00", "framework": "vllm", "intentId": "a805e242301145ed90037bde1881f57f", "lastModified": "2026-09-21T18:24:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "repoId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
+{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876728+00:00", "framework": "vllm", "intentId": "e77e8806b18040e1be44cfa579fd0eed", "lastModified": "2026-09-21T18:27:54+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
 {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
 {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
 {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691776+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.136949+00:00", "framework": "vllm", "intentId": "cff6b666a842431faf928f94c2086fdf", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.20.2",
   "checksums": {
     ".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "ce63be601c08b4a80c4e6589959baeb81298c5a6b63c945731656a93f57abbc4",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "0e0f100ca4f237791120af4db2b37b46c7e2215fba6b1bb0e0856f39c98f1fc1",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "dd5c70837c4892e7c109b3d2b616e851ba6a2a46a94821651f97992506fd6092",
+    ".modelhub_state/market_intelligence.json": "c6f1ab32ff6accb8d38251a97bab4ea0d31d315506295117a8962328f77e4ee2",
-    ".modelhub_state/official_capabilities.json": "b7c90ef73cca9591b2e11ff343b512e19ab1023114f14029adf91f532fea1efd",
+    ".modelhub_state/official_capabilities.json": "de6b0067d9f342cfa1d8ec02cc3c9e0347d1f0d46e29e2211d37e65fb98344a3",
-    ".modelhub_state/outcome_checkpoint.json": "0c16dad55bbb523148961becb7bf3e8a026f45508be98fe50d3e0e78d6c039e7",
+    ".modelhub_state/outcome_checkpoint.json": "f31ae2c0f5bf9f13e351483e00ddd81b10ef4e16337af0ff95802bba684c82fd",
     ".modelhub_state/queue_cleanup_latest.json": "fab470f2bbf8c39d73c8917d9fdab78c775c47a597aa2530a529e5a7ae55d4ec",
     ".modelhub_state/recent_outcomes.jsonl": "0e8003011fc7ffe4b589f4c251a9a27dcc4a692e1ded9860e25289e730723bf3",
     ".modelhub_state/recovery_active_tasks.jsonl": "1057a601486516c53d5efdf513a02643a318e7aa96623dff426b8cc49d75550f",
-    ".modelhub_state/recovery_intents.jsonl": "7d81e7f54448c724d128137a0828724c60db1d9c0c9502abae3718dffe0d6d38",
+    ".modelhub_state/recovery_intents.jsonl": "e36fdbea1bb0c2fc53c2505b68385f9d5bb289fc2af728d3d64aad29df2086e8",
     ".modelhub_state/routing_intelligence.json": "88f03d2f2a619505829a070f10901d9a1c82078e71bdd7b11c5ce7f2e94793b2",
     ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
     ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
     "ledger/submissions.jsonl": "a0a2062f110bafef7c0ea6ea997810dd96def0b9d8acb691f3676c7dc075d57c",
-    "outcomes/submissions.jsonl": "160b4bfac796e658ebdb2faf1e9a31e43378ac999d9d1598c751f1739ae46c57"
+    "outcomes/submissions.jsonl": "f65f61ea5cb87fdaa1659f162a4a29f1408db1b5b882c84884ba39bc283736ab"
   },
-  "generation": 11669,
+  "generation": 11670,
-  "phase": "cycle",
+  "phase": "intent",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-21T19:51:33.297863+00:00",
+  "updatedAt": "2026-09-21T19:52:49.027955+00:00",
   "writerId": "8b35139af6674067a339a670222d4b67"
 }

outcomes/submissions.jsonl

@@ -371,7 +371,6 @@
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647657+00:00", "modelId": "aisingapore/Llama-SEA-LION-v2-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.961, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16071447395, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16071447395}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.096766+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969079", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647811+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.078583+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969077", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647611+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.074544+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969076", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647756+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.140617+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969085", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647863+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.150681+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969083", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647805+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.247958+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969088", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647605+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11002488632, "estimatedRequiredGiB": 12.322, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 10176447713, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6340437856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:escha", "custom_tag:sglang", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "escha", "repositoryOnDiskBytes": 11025855102}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.244608+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969089", "taskType": "text-generation", "verifyResult": null}
@@ -1005,7 +1004,7 @@
 {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657126+00:00", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:46:27.357049+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000226", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657110+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "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": 4096479058, "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": 4096479058}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:46:34.674727+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000249", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657141+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "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": 7860673720}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:48:23.283753+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000251", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:50:46.187626+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5000279", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T19:52:34.157576+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:50:46.187626+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5000279", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:54:31.274098+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5000347", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4018332584, "estimatedRequiredGiB": 4.494, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4020783717, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4020783717}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:57:55.153765+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5000419", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29274355224, "estimatedRequiredGiB": 32.761, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 29314389092, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 29314389092}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:57:55.143712+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5000420", "taskType": "text-generation", "verifyResult": null}