state: generation 21593 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -2758,7 +2758,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-10-06T23:19:16.965488+00:00",
+  "generatedAt": "2026-10-06T23:26:35.620755+00:00",
   "summary": {
     "activeBlockCount": 139,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -434,7 +434,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-10-06T23:25:30.875167+00:00",
+  "generatedAt": "2026-10-06T23:27:59.355856+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-10-06T23:25:30.875167+00:00",
+  "catalogUpdatedAt": "2026-10-06T23:27:59.355856+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-10-06T23:25:30.875167+00:00",
+  "generatedAt": "2026-10-06T23:27:59.355856+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6283,6 +6283,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-10-06T23:25:30.875167+00:00",
+  "taskTreeUpdatedAt": "2026-10-06T23:27:59.355856+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-10-06T22:49:30.543549+00:00",
+  "generatedAt": "2026-10-06T23:26:35.522047+00:00",
-  "lastSyncTime": "2026-10-06T22:49:30.255985+00:00",
+  "lastSyncTime": "2026-10-06T23:26:35.259297+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3198,10 +3198,10 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 1,
         "failureBreakdown": {
-          "ambiguous_runtime": 125,
+          "ambiguous_runtime": 126,
           "memory_capacity": 1
         },
-        "failureCount": 126,
+        "failureCount": 127,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "pendingCount": 0,
@@ -3211,8 +3211,8 @@
         "successRate": 0.0,
         "targetGpu": "Biren_166m",
         "taskType": "text-generation",
-        "total": 126,
+        "total": 127,
-        "unresolvedFailureCount": 125
+        "unresolvedFailureCount": 126
       },
       "Biren_166m|vllm|text-generation": {
         "attributableFailureCount": 50,
@@ -4427,10 +4427,10 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 160,
+          "ambiguous_runtime": 161,
           "参数/模板问题": 3
         },
-        "failureCount": 163,
+        "failureCount": 164,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "pendingCount": 0,
@@ -4440,8 +4440,8 @@
         "successRate": 0.0,
         "targetGpu": "Kunlunxin_p-800",
         "taskType": "text-generation",
-        "total": 163,
+        "total": 164,
-        "unresolvedFailureCount": 163
+        "unresolvedFailureCount": 164
       },
       "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
         "attributableFailureCount": 61,
@@ -5589,7 +5589,7 @@
         "decisionSuccessRate": 0.0281,
         "decisionTotal": 178,
         "failureBreakdown": {
-          "ambiguous_runtime": 358,
+          "ambiguous_runtime": 360,
           "backend_operator": 9,
           "framework_architecture_unsupported": 47,
           "memory_capacity": 10,
@@ -5598,15 +5598,15 @@
           "tokenizer_compatibility": 95,
           "参数/模板问题": 13
         },
-        "failureCount": 569,
+        "failureCount": 571,
         "failureRate": 0.9913,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 25,
         "successCount": 5,
         "successRate": 0.0087,
-        "total": 574,
+        "total": 576,
-        "unresolvedFailureCount": 371
+        "unresolvedFailureCount": 373
       },
       "vllm_tokenizer_patch": {
         "attributableFailureCount": 150,
@@ -5637,7 +5637,7 @@
         "unresolvedFailureCount": 235
       }
     },
-    "generatedAt": "2026-10-06T22:49:30.468064+00:00",
+    "generatedAt": "2026-10-06T23:26:35.506170+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 119,
@@ -5700,7 +5700,7 @@
         "decisionSuccessRate": 0.1147,
         "decisionTotal": 218,
         "failureBreakdown": {
-          "ambiguous_runtime": 269,
+          "ambiguous_runtime": 270,
           "backend_operator": 4,
           "context_length": 10,
           "framework_architecture_unsupported": 125,
@@ -5714,15 +5714,15 @@
           "日志缺失": 62,
           "验证失败": 27
         },
-        "failureCount": 767,
+        "failureCount": 768,
-        "failureRate": 0.9684,
+        "failureRate": 0.9685,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 2,
         "successCount": 25,
-        "successRate": 0.0316,
+        "successRate": 0.0315,
-        "total": 792,
+        "total": 793,
-        "unresolvedFailureCount": 572
+        "unresolvedFailureCount": 573
       },
       "Cambricon_mlu-370-x4": {
         "attributableFailureCount": 759,
@@ -5869,7 +5869,7 @@
         "decisionSuccessRate": 0.066,
         "decisionTotal": 106,
         "failureBreakdown": {
-          "ambiguous_runtime": 249,
+          "ambiguous_runtime": 250,
           "backend_operator": 23,
           "framework_architecture_unsupported": 37,
           "memory_capacity": 3,
@@ -5882,15 +5882,15 @@
           "日志缺失": 1,
           "验证失败": 23
         },
-        "failureCount": 420,
+        "failureCount": 421,
         "failureRate": 0.9836,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 7,
         "successRate": 0.0164,
-        "total": 427,
+        "total": 428,
-        "unresolvedFailureCount": 320
+        "unresolvedFailureCount": 321
       },
       "Kunlunxin_r-200-8f": {
         "attributableFailureCount": 0,
@@ -9556,9 +9556,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 15
+          "ambiguous_runtime": 16
         },
-        "failureCount": 15,
+        "failureCount": 16,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "modelType": "qwen3_5",
@@ -9570,8 +9570,8 @@
         "successRate": 0.0,
         "targetGpu": "Biren_166m",
         "taskType": "text-generation",
-        "total": 15,
+        "total": 16,
-        "unresolvedFailureCount": 15
+        "unresolvedFailureCount": 16
       },
       "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none": {
         "attributableFailureCount": 0,
@@ -17981,6 +17981,29 @@
         "total": 2,
         "unresolvedFailureCount": 2
       },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma3|none": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "modelType": "gemma3",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4_unified|none": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -25046,9 +25069,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 12
+          "ambiguous_runtime": 13
         },
-        "failureCount": 12,
+        "failureCount": 13,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "lastPlatformFailureAt": null,
@@ -25060,8 +25083,8 @@
         "successRate": 0.0,
         "targetGpu": "Biren_166m",
         "taskType": "text-generation",
-        "total": 12,
+        "total": 13,
-        "unresolvedFailureCount": 12
+        "unresolvedFailureCount": 13
       },
       "Cambricon_mlu-370-x4|unknown|text-generation": {
         "attributableFailureCount": 0,
@@ -26300,9 +26323,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 4
+          "ambiguous_runtime": 5
         },
-        "failureCount": 4,
+        "failureCount": 5,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00",
@@ -26315,8 +26338,8 @@
         "successRate": 0.0,
         "targetGpu": "Biren_166m",
         "taskType": "text-generation",
-        "total": 4,
+        "total": 5,
-        "unresolvedFailureCount": 4
+        "unresolvedFailureCount": 5
       },
       "Biren_166m|vllm_fix_tokenizer|text-generation|smollm3|none": {
         "attributableFailureCount": 0,
@@ -34749,9 +34772,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 8
+          "ambiguous_runtime": 9
         },
-        "failureCount": 8,
+        "failureCount": 9,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "loadSizeLog2Bucket": 34,
@@ -34764,8 +34787,8 @@
         "successRate": 0.0,
         "targetGpu": "Biren_166m",
         "taskType": "text-generation",
-        "total": 8,
+        "total": 9,
-        "unresolvedFailureCount": 8
+        "unresolvedFailureCount": 9
       },
       "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|35": {
         "attributableFailureCount": 0,
@@ -47007,6 +47030,30 @@
         "total": 2,
         "unresolvedFailureCount": 2
       },
+      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma3|none|35": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "loadSizeLog2Bucket": 35,
+        "modelType": "gemma3",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Kunlunxin_p-800",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -57621,15 +57668,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17345,
+    "terminalRecords": 17347,
-    "totalRecords": 17569,
+    "totalRecords": 17571,
     "totals": {
       "attributableFailureCount": 6236,
       "decisionFailureRate": 0.8644,
       "decisionSuccessRate": 0.1356,
       "decisionTotal": 7214,
       "failureBreakdown": {
-        "ambiguous_runtime": 4551,
+        "ambiguous_runtime": 4553,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 129,
@@ -57645,15 +57692,15 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16367,
+      "failureCount": 16369,
       "failureRate": 0.9436,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 952,
       "successCount": 978,
       "successRate": 0.0564,
-      "total": 17345,
+      "total": 17347,
-      "unresolvedFailureCount": 9179
+      "unresolvedFailureCount": 9181
     },
     "warnings": [
       "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -57662,14 +57709,14 @@
       "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU 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 Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
       "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57713,6 +57760,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 17569,
+  "summarizedRecords": 17571,
   "version": 1
 }

.modelhub_state/recent_outcomes.jsonl

@@ -240,6 +240,7 @@
 {"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-21T18:39:29.750819+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-09-20T12:58:28.353096+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 16568142065}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:05:59.142974+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997663", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-30T11:55:48.444086+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093198689}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:02:30.537080+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997592", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-23T05:26:10.454831+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219876272, "estimatedRequiredGiB": 0.25, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223261617, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223261617}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:02:30.534692+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997591", "taskType": "text-generation", "verifyResult": -1}
+{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T23:26:35.259297+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29326959151, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:image-editing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326959151}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:59:28.154388+00:00", "targetGpu": "Biren_166m", "taskId": "4997528", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T21:35:04.154893+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231252716, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233101396, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233101396}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:46:11.874749+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997349", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T02:39:29.759242+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952488643, "estimatedRequiredGiB": 33.497, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29972714678, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29972714678}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:43:01.453596+00:00", "targetGpu": "Biren_166m", "taskId": "4997304", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-22T21:35:04.154848+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:39:50.946521+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997284", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-22T08:25:19.951625+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "failed", "status": "success", "submitTime": "2026-09-21T04:37:44.469638+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4993963", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-21T04:36:00.569175+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:35:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4576912", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569197+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969802", "taskType": "text-generation", "verifyResult": null}
-{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569297+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969335", "taskType": "text-generation", "verifyResult": null}

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.04.4",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "4fc07d6730d984498c60310ad4c4349e96835326eef6d9f621ac26ebc444a276",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "ce3253f1aa157547eb682eb0eff27f5f34545074903cbe923efa7d9689219c32",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "f957eb5859a3e5269370bdcfdca7341308c19823d70e6f59c1b8d06702b2f4a4",
+    ".modelhub_state/market_intelligence.json": "7b2de83fbfa1eabc6acf8029b417492a9f9029df653a10a338c831ca0fec37c6",
-    ".modelhub_state/official_capabilities.json": "2e8fcc596e410a2fc483085b85581625b405ea1265a9efa3d6cc3101f48b8490",
+    ".modelhub_state/official_capabilities.json": "3bd49b164d26b491abe85678a099c6e02ecf08d437b3926d20ff3aa33b71348e",
-    ".modelhub_state/outcome_checkpoint.json": "bf1e1e9cd6d045e616224a1139442d652c039734a793b81c912b409ccf404f87",
+    ".modelhub_state/outcome_checkpoint.json": "b109bef090a2bb0e5440381e90783f54afe6519569af64aa64cf2f929a070490",
     ".modelhub_state/queue_cleanup_latest.json": "811650bde1021c3ae4227111e561fcae79b8445c1c6034885200e4ffbf955099",
-    ".modelhub_state/recent_outcomes.jsonl": "ac1c51b9a94e2169f287e9224a1482891df92776f70358b8eb416d7aa995d25f",
+    ".modelhub_state/recent_outcomes.jsonl": "4a4250a6ef15d95503aa4f24be053821f3f4fa20018d122db3dc175d621fbe08",
-    ".modelhub_state/recovery_active_tasks.jsonl": "4ecfa1a3155010f1534f59a32b033bed098aa508dfc59d50f279e7b101d7aa54",
+    ".modelhub_state/recovery_active_tasks.jsonl": "10926cb54844067bd3af80f8ec1f1d49780beeb056330e42a912eac1c6e603f5",
-    ".modelhub_state/recovery_intents.jsonl": "8441fcbe1a5a99f12edf6bf42dd39a649778d0057ccafa114ee0f62fc585dc9a",
+    ".modelhub_state/recovery_intents.jsonl": "bf379a088544d6fae57a16b226f2fd3e5a7b46eaec4247726f4038858f5c1fde",
     ".modelhub_state/routing_intelligence.json": "9b646e2e89c87c292a86549a9b08f7d460fca35c575c5473290c4d5e06262380",
     ".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
     ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
     "ledger/submissions.jsonl": "06ed61449ad7d7ebf5f47f68d2789e137dd37687f9619a367defffadc5c3c8da",
-    "outcomes/submissions.jsonl": "bd79992ae8385c899474d7bc1ef68d042ee28ea9c71c0ef0ef1647bb0afa4c9b"
+    "outcomes/submissions.jsonl": "2d7a27d1be98f88de97cbfa3941d542fd59928e46ccaa82e9e6079ecc8ce0348"
   },
-  "generation": 21592,
+  "generation": 21593,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-06T23:25:32.087024+00:00",
+  "updatedAt": "2026-10-06T23:28:05.956637+00:00",
   "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
 }

outcomes/submissions.jsonl

@@ -142,7 +142,6 @@
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:10:38.766169+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:17.694934+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969317", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:10:38.766358+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:17.840209+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766033+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null}
@@ -207,7 +206,6 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:50:30.559229+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:29:25.981023+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997054", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559176+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:33:57.835795+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997190", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559312+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29326959151, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:image-editing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326959151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:43:01.432709+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997305", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T17:22:47.256894+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29326959151, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:image-editing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326959151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:59:28.154388+00:00", "targetGpu": "Biren_166m", "taskId": "4997528", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T17:22:47.256807+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T09:07:46.198212+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997684", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T18:39:29.750789+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29326959151, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:image-editing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326959151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T10:34:34.644445+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999238", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T19:05:56.948982+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T10:52:01.384099+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999444", "taskType": "text-generation", "verifyResult": null}