state: generation 37043 (intent)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -504,7 +504,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-10-25T20:03:31.381151+00:00",
+  "generatedAt": "2026-10-25T20:04:23.413508+00:00",
   "summary": {
     "activeBlockCount": 25,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -452,7 +452,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-10-25T20:03:31.455496+00:00",
+  "generatedAt": "2026-10-25T20:04:23.533758+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-10-25T20:03:31.455496+00:00",
+  "catalogUpdatedAt": "2026-10-25T20:04:23.533758+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-10-25T20:03:31.455496+00:00",
+  "generatedAt": "2026-10-25T20:04:23.533758+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6447,6 +6447,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-10-25T20:03:31.455496+00:00",
+  "taskTreeUpdatedAt": "2026-10-25T20:04:23.533758+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-10-25T19:47:09.926989+00:00",
+  "generatedAt": "2026-10-25T20:04:23.319487+00:00",
-  "lastSyncTime": "2026-10-25T19:47:09.645385+00:00",
+  "lastSyncTime": "2026-10-25T20:04:23.040305+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -934,11 +934,11 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 1,
         "failureBreakdown": {
-          "ambiguous_runtime": 161,
+          "ambiguous_runtime": 162,
           "memory_capacity": 1,
           "参数/模板问题": 12
         },
-        "failureCount": 174,
+        "failureCount": 175,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "pendingCount": 0,
@@ -948,8 +948,8 @@
         "successRate": 0.0,
         "targetGpu": "Biren_166m",
         "taskType": "text-generation",
-        "total": 174,
+        "total": 175,
-        "unresolvedFailureCount": 173
+        "unresolvedFailureCount": 174
       },
       "Biren_166m|vllm|text-generation": {
         "attributableFailureCount": 51,
@@ -3358,7 +3358,7 @@
         "decisionSuccessRate": 0.0348,
         "decisionTotal": 201,
         "failureBreakdown": {
-          "ambiguous_runtime": 449,
+          "ambiguous_runtime": 450,
           "backend_operator": 11,
           "framework_architecture_unsupported": 59,
           "memory_capacity": 11,
@@ -3367,15 +3367,15 @@
           "tokenizer_compatibility": 100,
           "参数/模板问题": 48
         },
-        "failureCount": 727,
+        "failureCount": 728,
         "failureRate": 0.9905,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 36,
         "successCount": 7,
         "successRate": 0.0095,
-        "total": 734,
+        "total": 735,
-        "unresolvedFailureCount": 497
+        "unresolvedFailureCount": 498
       },
       "vllm_tokenizer_patch": {
         "attributableFailureCount": 181,
@@ -3406,7 +3406,7 @@
         "unresolvedFailureCount": 361
       }
     },
-    "generatedAt": "2026-10-25T19:47:09.912397+00:00",
+    "generatedAt": "2026-10-25T20:04:23.263580+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 134,
@@ -3470,7 +3470,7 @@
         "decisionSuccessRate": 0.1142,
         "decisionTotal": 219,
         "failureBreakdown": {
-          "ambiguous_runtime": 305,
+          "ambiguous_runtime": 306,
           "backend_operator": 4,
           "context_length": 10,
           "framework_architecture_unsupported": 126,
@@ -3484,15 +3484,15 @@
           "日志缺失": 62,
           "验证失败": 27
         },
-        "failureCount": 817,
+        "failureCount": 818,
         "failureRate": 0.9703,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 2,
         "successCount": 25,
         "successRate": 0.0297,
-        "total": 842,
+        "total": 843,
-        "unresolvedFailureCount": 621
+        "unresolvedFailureCount": 622
       },
       "Cambricon_mlu-370-x4": {
         "attributableFailureCount": 771,
@@ -7740,6 +7740,29 @@
         "total": 2,
         "unresolvedFailureCount": 2
       },
+      "Biren_166m|vllm_fix_tokenizer|text-generation|pulvis|none": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "modelType": "pulvis",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Biren_166m",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -35398,6 +35421,30 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "Biren_166m|vllm_fix_tokenizer|text-generation|pulvis|none|23": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "loadSizeLog2Bucket": 23,
+        "modelType": "pulvis",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Biren_166m",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none|31": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -63191,15 +63238,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 18096,
+    "terminalRecords": 18097,
-    "totalRecords": 18640,
+    "totalRecords": 18641,
     "totals": {
       "attributableFailureCount": 6387,
       "decisionFailureRate": 0.8663,
       "decisionSuccessRate": 0.1337,
       "decisionTotal": 7373,
       "failureBreakdown": {
-        "ambiguous_runtime": 4699,
+        "ambiguous_runtime": 4700,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 137,
@@ -63215,21 +63262,20 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 17110,
+      "failureCount": 17111,
       "failureRate": 0.9455,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 972,
       "successCount": 986,
       "successRate": 0.0545,
-      "total": 18096,
+      "total": 18097,
-      "unresolvedFailureCount": 9751
+      "unresolvedFailureCount": 9752
     },
     "warnings": [
+      "GPU Vastai_va16 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 Mthreads_s4000 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 Kunlunxin_p-800 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_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -63238,7 +63284,8 @@
       "GPU Sunrise_pt-200-x1 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 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 Iluvatar_bi-150 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。",
       "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 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -63286,6 +63333,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 18640,
+  "summarizedRecords": 18641,
   "version": 1
 }

.modelhub_state/recovery_intents.jsonl

@@ -3858,6 +3858,18 @@
 {"batchId": "c1703992f4724ef18189b781ad942c10", "completedAt": "2026-10-25T20:02:43.035001+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:02:40.890836+00:00", "framework": "vllm_tokenizer_patch", "intentId": "aca4423d34c948b49b433ff12bd320fb", "lastModified": "2026-10-21T15:22:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Trinity-Mini-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-25T20:03:36.518814+00:00", "repoId": "cyankiwi/Trinity-Mini-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5789210", "taskType": "text-generation"}
 {"batchId": "c1703992f4724ef18189b781ad942c10", "completedAt": "2026-10-25T20:02:43.035007+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:02:40.890910+00:00", "framework": "vllm_tokenizer_patch", "intentId": "337c9738a99e4ec5989f9aa146958575", "lastModified": "2026-10-21T17:19:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-25T20:03:36.517585+00:00", "repoId": "cyankiwi/KAT-Dev-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5789211", "taskType": "text-generation"}
 {"batchId": "5ea30092656b41ab9a09dace8fdc0224", "completedAt": "2026-10-25T20:03:34.491408+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:03:32.165951+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c5e12b50b8b948eab66e62b1da122164", "lastModified": "2026-10-21T15:27:56+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T20:03:36.517571+00:00", "repoId": "cyankiwi/Jan-v1-4B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5789237", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391224+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fed6bfac5b8746c1bcd8990a444c258f", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391323+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2040fe02f8f94d18b80b934c56774b16", "lastModified": "2026-10-21T16:02:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4.3-36B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391365+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f72295e5eae44ffb9c73d11f8b97093b", "lastModified": "2026-10-21T15:42:33+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Instruct-AWQ-8bit", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391403+00:00", "framework": "vllm_fix_tokenizer", "intentId": "468fb87637d2496181c355c8795c16d1", "lastModified": "2026-10-22T14:13:07+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5", "repoId": "InternScience/Sage-A1.5", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391450+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b9643d87966e456c9e193949306f0d51", "lastModified": "2026-10-21T15:33:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-8bit", "repoId": "cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391494+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5e67880f18264d18b72115c48c119fb8", "lastModified": "2026-10-21T15:39:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Dev-72B-AWQ-8bit", "repoId": "cyankiwi/Kimi-Dev-72B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391538+00:00", "framework": "vllm_fix_tokenizer", "intentId": "01f2cfe6470c49aa8487bd036724c9e7", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391581+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4deeab6c14344572957600b9ade644c7", "lastModified": "2026-10-21T16:25:01+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "repoId": "cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391623+00:00", "framework": "vllm_fix_tokenizer", "intentId": "814f7d3c2cd34b958d91f2fa93f2fda3", "lastModified": "2026-10-21T19:49:11+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391665+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5d926f6416284db29e2ee14cc4a3a119", "lastModified": "2026-10-25T15:32:31+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-7B-FP8", "repoId": "IFM/Jais-3-7B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391707+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2294407c26ac4c72928a7a119a7ef7af", "lastModified": "2026-10-21T15:59:12+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
+{"batchId": "e896b5d3e16e4c0686b150bc152b75e7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:04:24.391749+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9a5c692120e34b58a0804bdb0b38a134", "lastModified": "2026-10-25T15:33:35+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-3.7B-FP8", "repoId": "IFM/Jais-3-3.7B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
 {"batchId": "5ea30092656b41ab9a09dace8fdc0224", "completedAt": "2026-10-25T20:03:34.491433+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:03:32.166315+00:00", "framework": "vllm_fix_tokenizer", "intentId": "88df6f15ef01463e8199218b528c2b3a", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
 {"batchId": "5ea30092656b41ab9a09dace8fdc0224", "completedAt": "2026-10-25T20:03:34.491430+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:03:32.166271+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3d5124c7ccd94540bd2ac2c1849966b2", "repoId": "IFM/Jais-3-7B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
 {"batchId": "5ea30092656b41ab9a09dace8fdc0224", "completedAt": "2026-10-25T20:03:34.491427+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T20:03:32.166227+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b0dee4feff334b08addbc0d5a00159e5", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.04.4",
   "checksums": {
     ".modelhub_state/account_capacity.json": "c31585c1069308de2c1cc9ff51496b495486ae67148c1369f849dae7291eef2f",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "0588798a9eb10f5a1fce252802b2902eb1d8c6029a2262d13d1dbb46f4e3d46f",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "f7d1f153c5041b4aac7268f4d2e5fe06ee67883a548c583fe4a1759957834b47",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "6ba8362d50a3d90005117bd7d08525c8a01da4acb2c6026b8a93f2a619c49811",
+    ".modelhub_state/market_intelligence.json": "9917f6bd64f00b0d39c1b154c48007835d83ec8e29ead02a97361a58d8286239",
-    ".modelhub_state/official_capabilities.json": "2bd4ce1024ee10d62cd495eb47469a58a711446f01ce31c30fd0de52e3cb667a",
+    ".modelhub_state/official_capabilities.json": "cdcf3cb04d9fac217c8e3d10485c952666000b45cdc067ae2507cf1b99e03645",
-    ".modelhub_state/outcome_checkpoint.json": "e4ee3b73eff4056feddb2678e13c7a546048e6c760d5cc0a146c579c693a1fa8",
+    ".modelhub_state/outcome_checkpoint.json": "c6f890f2c249f6077b845c9328ba4ac6bce6cc904ed021095231d553a898d393",
     ".modelhub_state/queue_cleanup_latest.json": "fe69e0a76e63159c4290786a63dc0ab16b85e3a2990fe6358e3ee0885577d6e5",
     ".modelhub_state/recent_outcomes.jsonl": "0c551aa86b5247d03b8a40341c91e68a725e39a408781c95464f00f6d16f73ea",
     ".modelhub_state/recovery_active_tasks.jsonl": "54fd0e652d16b3e3af1f8e136bd00e284a862a478ad80a60d4666c27f310ec40",
-    ".modelhub_state/recovery_intents.jsonl": "6dfb66fea30fc68a80bc7f19c7defed11584bfe05d44ea27ca03bfb6da0304e0",
+    ".modelhub_state/recovery_intents.jsonl": "660812815fc8aee2928786f3c06e18575d00c1ff2b62de76ba299bb1c4427639",
     ".modelhub_state/routing_intelligence.json": "8eedd4a6b29595411a040fc71ec3d645c8043e256fc536bb290ec6346be5a087",
     ".modelhub_state/submission_exclusions.jsonl": "3db506f4d37bc78a9069d6022969e3718fa3eb1dad129907c99f63d5a7300ba1",
     ".modelhub_state/worker_crashes.jsonl": "0fc6c3913ba6a3ff00019bfaff56ce222acc4b192a4ed26e7f61a0bec8699b05",
     "ledger/submissions.jsonl": "0e18fac7f5fa235858dd7304e472f5154870125d2c1dc07c3af5b67119a792d8",
-    "outcomes/submissions.jsonl": "e53c7835f8f1a33b1eb597b4e6ea050564ab7c1b59674772b976c54ba1c81f4f"
+    "outcomes/submissions.jsonl": "aa9387b2097e3027539188f0ef2a36fde6361c97c2099d99d41eccfbc852479d"
   },
-  "generation": 37042,
+  "generation": 37043,
-  "phase": "cycle",
+  "phase": "intent",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-25T20:03:36.766503+00:00",
+  "updatedAt": "2026-10-25T20:04:24.555956+00:00",
   "writerId": "7ff73e6204284f23bc2b88b7c29d21d9"
 }

outcomes/submissions.jsonl

@@ -317,7 +317,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347942+00:00", "modelId": "Qwen/Qwen3Guard-Stream-0.6B", "modelProfile": {"architectures": ["Qwen3ForGuardModel"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1194258680, "estimatedRequiredGiB": 1.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 1210817078, "modelscopeLicense": "apache-2.0", "modelscopeParams": 597111296, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1210817078}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.161347+00:00", "targetGpu": "Biren_166m", "taskId": "5320007", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347712+00:00", "modelId": "primitive-ai/Kolibri-1-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45807306768, "estimatedRequiredGiB": 51.228, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 45837930112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 44223812896, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 45837930112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.948239+00:00", "targetGpu": "Biren_166m", "taskId": "5320001", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347948+00:00", "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 47737939154, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.950443+00:00", "targetGpu": "Biren_166m", "taskId": "5319999", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347762+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "e05a79eb8dafd7faea50fd5995a6ec7c38f0fd9997536089164c0b07bdf79d6c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.071683+00:00", "targetGpu": "Biren_166m", "taskId": "5320003", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.348106+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.153341+00:00", "targetGpu": "Biren_166m", "taskId": "5320009", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347661+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T04:22:26.358545+00:00", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.068600+00:00", "targetGpu": "Biren_166m", "taskId": "5320004", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347974+00:00", "modelId": "NovelAI/genji-jp-6b-v2-legacy", "modelProfile": {"architectures": ["GPTJForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12101796384, "estimatedRequiredGiB": 52.535, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gptj", "modelscopeFileSize": 47007134557, "modelscopeLicense": "gpl-3.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-3.0", "model_type:gptj", "library:gguf", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 47007134557}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.047082+00:00", "targetGpu": "Biren_166m", "taskId": "5320002", "taskType": "text-generation", "verifyResult": null}
@@ -1085,7 +1084,7 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T19:04:46.044104+00:00", "modelId": "InternScience/Sage-A1.5-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39365363088, "estimatedRequiredGiB": 44.025, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 39392487901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "task:text-generation", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 39392487901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T11:04:02.412822+00:00", "targetGpu": "Biren_166m", "taskId": "5779345", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T19:40:32.536539+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 23.921, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 21404443971, "modelscopeLicense": "other", "modelscopeParams": 14768307200, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 21404443971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T11:39:21.767581+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5780290", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T19:47:09.645364+00:00", "modelId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13849505352, "estimatedRequiredGiB": 15.501, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13869693303, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9409813744, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.5", "custom_tag:code", "custom_tag:agent", "custom_tag:sft", "custom_tag:omnicoder", "custom_tag:tesslate"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 13869693303}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T11:46:49.387847+00:00", "targetGpu": "Vastai_va16", "taskId": "5780488", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 14125731418}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T12:03:59.435452+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5780854", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T20:04:23.040283+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 14125731418}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T12:03:59.435452+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5780854", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115826811, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115826811}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T13:45:12.332015+00:00", "targetGpu": "Vastai_va16", "taskId": "5783152", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RecursiveSI/flint-int4", "modelProfile": {"architectures": ["FlintForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22568912600, "estimatedRequiredGiB": 25.235, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "flint", "modelscopeFileSize": 22580274594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3572482016, "modelscopeTags": ["license:apache-2.0", "model_type:flint", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:int4", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22580274594}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T14:04:13.128555+00:00", "targetGpu": "Vastai_va16", "taskId": "5783573", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115840957, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115840957}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T14:13:21.040155+00:00", "targetGpu": "Vastai_va16", "taskId": "5783720", "taskType": "text-generation", "verifyResult": null}