state: generation 13338 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3044,7 +3044,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-23T03:18:47.757513+00:00",
+  "generatedAt": "2026-09-23T03:22:39.850248+00:00",
   "summary": {
     "activeBlockCount": 153,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -396,7 +396,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-23T03:21:38.106840+00:00",
+  "generatedAt": "2026-09-23T03:22:50.654634+00:00",
   "gpuStats": {
     "Ascend_910-b4": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-23T03:21:38.106840+00:00",
+  "catalogUpdatedAt": "2026-09-23T03:22:50.654634+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-23T03:21:38.106840+00:00",
+  "generatedAt": "2026-09-23T03:22:50.654634+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6685,6 +6685,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-23T03:21:38.106840+00:00",
+  "taskTreeUpdatedAt": "2026-09-23T03:22:50.654634+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-23T02:43:28.816899+00:00",
+  "generatedAt": "2026-09-23T03:22:39.773217+00:00",
-  "lastSyncTime": "2026-09-23T02:43:25.562726+00:00",
+  "lastSyncTime": "2026-09-23T03:22:39.362176+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -4700,10 +4700,10 @@
         "unresolvedFailureCount": 132
       },
       "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
-        "attributableFailureCount": 40,
+        "attributableFailureCount": 41,
-        "decisionFailureRate": 0.8889,
+        "decisionFailureRate": 0.8913,
-        "decisionSuccessRate": 0.1111,
+        "decisionSuccessRate": 0.1087,
-        "decisionTotal": 45,
+        "decisionTotal": 46,
         "failureBreakdown": {
           "ambiguous_runtime": 5,
           "backend_operator": 8,
@@ -4712,20 +4712,20 @@
           "model_load": 12,
           "platform_infrastructure": 1,
           "repository_structure": 2,
-          "runtime_memory": 2,
+          "runtime_memory": 3,
           "参数/模板问题": 14
         },
-        "failureCount": 60,
+        "failureCount": 61,
-        "failureRate": 0.9231,
+        "failureRate": 0.9242,
         "framework": "vllm_tokenizer_patch",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 5,
-        "successRate": 0.0769,
+        "successRate": 0.0758,
         "targetGpu": "Kunlunxin_p-800",
         "taskType": "text-generation",
-        "total": 65,
+        "total": 66,
         "unresolvedFailureCount": 19
       },
       "Kunlunxin_p-800|vllm|text-generation": {
@@ -5860,10 +5860,10 @@
         "unresolvedFailureCount": 313
       },
       "vllm_tokenizer_patch": {
-        "attributableFailureCount": 107,
+        "attributableFailureCount": 108,
-        "decisionFailureRate": 0.9304,
+        "decisionFailureRate": 0.931,
-        "decisionSuccessRate": 0.0696,
+        "decisionSuccessRate": 0.069,
-        "decisionTotal": 115,
+        "decisionTotal": 116,
         "failureBreakdown": {
           "ambiguous_runtime": 147,
           "backend_operator": 8,
@@ -5873,22 +5873,22 @@
           "model_load": 15,
           "platform_infrastructure": 2,
           "repository_structure": 3,
-          "runtime_memory": 2,
+          "runtime_memory": 3,
           "tokenizer_compatibility": 2,
           "参数/模板问题": 28
         },
-        "failureCount": 284,
+        "failureCount": 285,
-        "failureRate": 0.9726,
+        "failureRate": 0.9727,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 2,
         "successCount": 8,
-        "successRate": 0.0274,
+        "successRate": 0.0273,
-        "total": 292,
+        "total": 293,
         "unresolvedFailureCount": 175
       }
     },
-    "generatedAt": "2026-09-23T02:43:28.804947+00:00",
+    "generatedAt": "2026-09-23T03:22:39.761537+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 102,
@@ -6114,10 +6114,10 @@
         "unresolvedFailureCount": 717
       },
       "Kunlunxin_p-800": {
-        "attributableFailureCount": 54,
+        "attributableFailureCount": 55,
-        "decisionFailureRate": 0.9153,
+        "decisionFailureRate": 0.9167,
-        "decisionSuccessRate": 0.0847,
+        "decisionSuccessRate": 0.0833,
-        "decisionTotal": 59,
+        "decisionTotal": 60,
         "failureBreakdown": {
           "ambiguous_runtime": 210,
           "backend_operator": 11,
@@ -6126,19 +6126,19 @@
           "model_load": 13,
           "platform_infrastructure": 1,
           "repository_structure": 2,
-          "runtime_memory": 2,
+          "runtime_memory": 3,
           "参数/模板问题": 32,
           "日志缺失": 1,
           "验证失败": 23
         },
-        "failureCount": 321,
+        "failureCount": 322,
         "failureRate": 0.9847,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 5,
         "successRate": 0.0153,
-        "total": 326,
+        "total": 327,
         "unresolvedFailureCount": 266
       },
       "Kunlunxin_r-200-8f": {
@@ -17055,14 +17055,15 @@
         "unresolvedFailureCount": 0
       },
       "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|none": {
-        "attributableFailureCount": 1,
+        "attributableFailureCount": 2,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 1,
+        "decisionTotal": 2,
         "failureBreakdown": {
-          "model_load": 1
+          "model_load": 1,
+          "runtime_memory": 1
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "modelType": "llama",
@@ -17074,7 +17075,7 @@
         "successRate": 0.0,
         "targetGpu": "Kunlunxin_p-800",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
         "unresolvedFailureCount": 0
       },
       "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
@@ -40555,6 +40556,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|none|36": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "runtime_memory": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_tokenizer_patch",
+        "loadSizeLog2Bucket": 36,
+        "modelType": "llama",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|32": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -45897,13 +45922,13 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 16799,
+    "terminalRecords": 16800,
-    "totalRecords": 17017,
+    "totalRecords": 17018,
     "totals": {
-      "attributableFailureCount": 6013,
+      "attributableFailureCount": 6014,
       "decisionFailureRate": 0.8622,
       "decisionSuccessRate": 0.1378,
-      "decisionTotal": 6974,
+      "decisionTotal": 6975,
       "failureBreakdown": {
         "ambiguous_runtime": 4286,
         "architecture_compatibility": 212,
@@ -45915,25 +45940,26 @@
         "model_load": 526,
         "platform_infrastructure": 931,
         "repository_structure": 740,
-        "runtime_memory": 91,
+        "runtime_memory": 92,
         "tokenizer_compatibility": 669,
         "参数/模板问题": 3213,
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 15838,
+      "failureCount": 15839,
       "failureRate": 0.9428,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 931,
       "successCount": 961,
       "successRate": 0.0572,
-      "total": 16799,
+      "total": 16800,
       "unresolvedFailureCount": 8894
     },
     "warnings": [
       "GPU Iluvatar_mrv-100 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 Biren_166m 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 Cambricon_mlu-370-x8 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。",
@@ -45944,7 +45970,6 @@
       "GPU Vastai_va16 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 Mthreads_s4000 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。",
       "组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -45968,6 +45993,7 @@
       "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
+      "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 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 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -45981,11 +46007,10 @@
       "组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 MetaX_c-500|vllm|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 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
+      "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
-      "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 17017,
+  "summarizedRecords": 17018,
   "version": 1
 }

ledger/submissions.jsonl

@@ -395,7 +395,6 @@
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-20T03:41:49.638140+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970038", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-20T03:41:49.641475+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970041", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "submitTime": "2026-09-20T03:53:33.649508+00:00", "targetGpu": "Vastai_va16", "taskId": "4970244", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
-{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "submitTime": "2026-09-20T03:53:33.678855+00:00", "targetGpu": "Vastai_va16", "taskId": "4970238", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "submitTime": "2026-09-20T03:53:33.665289+00:00", "targetGpu": "Vastai_va16", "taskId": "4970240", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "modelId": "inceptionai/Jais-2-8B-Chat", "submitTime": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "submitTime": "2026-09-20T03:53:59.235830+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970247", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
@@ -412,7 +411,6 @@
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-20T04:01:42.646836+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970409", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "modelId": "RedHatAI/starcoder2-3b-FP8", "submitTime": "2026-09-20T04:09:56.479634+00:00", "targetGpu": "Vastai_va16", "taskId": "4970501", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "modelId": "inceptionai/Jais-2-8B-Chat", "submitTime": "2026-09-20T04:10:03.058495+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970512", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
-{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "submitTime": "2026-09-20T04:11:06.667095+00:00", "targetGpu": "Vastai_va16", "taskId": "4970526", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "submitTime": "2026-09-20T04:11:06.683086+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970527", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
 {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "submitTime": "2026-09-20T04:14:34.933362+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970576", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "submitTime": "2026-09-20T04:14:34.792755+00:00", "targetGpu": "Vastai_va16", "taskId": "4970571", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.22.1",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "d466319023715cb123d021dbd045810465de5a6ff506de407165a7c21abf0a5f",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "bff7e008da5563f77d90233f5af7a09d1199a6d13d0ed3ee917f5b630e15247e",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "14f673498731ead91972dad29a27942bafa58b504c75c24a70f27fec9adc6b88",
+    ".modelhub_state/market_intelligence.json": "975dedd95a44142c6d839e1d9aca108bd0ec3b108bca14b111a04290819c9b67",
-    ".modelhub_state/official_capabilities.json": "8963d8a4e40baf4ee7b422f028f5be7de86cd7a418f543de67cf50c957ab339c",
+    ".modelhub_state/official_capabilities.json": "ef5c9ad340b47588daa1fb789bf85e9b38c5d7b0368d3ca611658061202c53f1",
-    ".modelhub_state/outcome_checkpoint.json": "55743fdfd5f46db594c372d4535774209ab9afba22b19b91c6e7d64cf2fe9956",
+    ".modelhub_state/outcome_checkpoint.json": "6037d7de8f8810cc1469a4d4d2e34c6de7365cf2b1ab68b62d2d73695d866733",
     ".modelhub_state/queue_cleanup_latest.json": "abeedea8ce654c253250bcfd506d9b5eab392b53faf9867483b77b9a5c85233b",
     ".modelhub_state/recent_outcomes.jsonl": "ef30e009ef3f131ccb91f0e3765f80d2af5c61777924c86d28a680581208505c",
-    ".modelhub_state/recovery_active_tasks.jsonl": "f1249692df4dd58d8b541f413f38d4b2279e9dfa54d1d2c465bdd64a7e4f40f6",
+    ".modelhub_state/recovery_active_tasks.jsonl": "f086d165057a5e0a4caf29393cce3a4c0179ab9e816ddc15062b25411d63c26c",
-    ".modelhub_state/recovery_intents.jsonl": "dd87e02085716669cb09761f1514dc109a82b2c420ac01b7fd4e1eb9e2fa9022",
+    ".modelhub_state/recovery_intents.jsonl": "b73f649c7a6427608eb81238e189aa63b258f70c24e3da3c62fbb571feb15f3e",
     ".modelhub_state/routing_intelligence.json": "8c3626c55553fe91ab8593de694769500c237524899f51a12cde15748d826a29",
     ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
     ".modelhub_state/worker_crashes.jsonl": "619eac16f716b2420672872ff4ce92d452f5fced4f96e8dbb37f9ce511b53c5b",
-    "ledger/submissions.jsonl": "693b569e60f0df26e60e589e1fdb7cb8e17b3a09c65e51dcff63ab0fc8d786b7",
+    "ledger/submissions.jsonl": "6123097885eb2268ab325ad67a70a3a5dbac0510610b3c046fea58f247fbed48",
-    "outcomes/submissions.jsonl": "757bc0ad91f40a24ac4f0346c3057838ee328c1c49296f2a31c7aa75946f2415"
+    "outcomes/submissions.jsonl": "b6b1ad139794b2731a2170e07b1b0a8538c2e446c6951e6415a0366cf640e5cf"
   },
-  "generation": 13337,
+  "generation": 13338,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-23T03:21:38.716635+00:00",
+  "updatedAt": "2026-09-23T03:22:52.134002+00:00",
   "writerId": "328f98096427428498653b568f0d5041"
 }

outcomes/submissions.jsonl

@@ -475,7 +475,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T20:49:19.683352+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788612744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:37:15.035344+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4979019", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T20:49:19.683365+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "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": 2033824885}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:37:15.024523+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4979018", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:49:19.683309+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860631926, "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": 7860631926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:37:15.056589+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4979021", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:49:19.683268+00:00", "modelId": "BSC-LT/ALIA-40b", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 80867821352, "estimatedRequiredGiB": 90.437, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 80921299838, "modelscopeLicense": "apache-2.0", "modelscopeParams": 40433885184, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 80921299838}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:46:10.202639+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4979108", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:06:45.850274+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:01:42.205703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979280", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:33:11.158023+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "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": 4404161034, "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": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:19:23.910185+00:00", "targetGpu": "Vastai_va16", "taskId": "4979588", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T22:24:01.251269+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232060880, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233909203, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233909203}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:22:13.035851+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980360", "taskType": "text-generation", "verifyResult": null}