diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index a11ce95b96..0d9691e871 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -2605,7 +2605,7 @@
 {"batchId": "30991ffef4b34949a6e34885a0c4444e", "completedAt": "2026-10-01T18:36:12.806294+00:00", "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configSource": "modelhub_live", "createdAt": "2026-10-01T18:34:19.542976+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5c256572faf548c0907e34a347f5db2c", "lastModified": "2026-10-01T18:21:35+00:00", "modelAddress": "https://modelscope.cn/models/PleIAs/baguettotron-600m", "reason": null, "reconciledAt": "2026-10-01T19:53:51.468421+00:00", "repoId": "PleIAs/baguettotron-600m", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5220158", "taskType": "text-generation"}
 {"batchId": "d099bcd8d8b34bdb8eec69bcc38a4982", "completedAt": "2026-10-01T18:56:27.303005+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-01T18:54:34.681255+00:00", "framework": "vllm_tokenizer_patch", "intentId": "abe56c843c524b29a2e943ad3e2e6f01", "lastModified": "2026-10-01T18:21:35+00:00", "modelAddress": "https://modelscope.cn/models/PleIAs/baguettotron-600m", "reason": null, "reconciledAt": "2026-10-01T19:53:51.469053+00:00", "repoId": "PleIAs/baguettotron-600m", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5220400", "taskType": "text-generation"}
 {"batchId": "4bcf4db8101642ba960fd0aae9c6011c", "completedAt": "2026-10-01T19:43:06.414001+00:00", "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configSource": "modelhub_live", "createdAt": "2026-10-01T19:41:17.973051+00:00", "framework": "vllm_tokenizer_patch", "intentId": "11a5ff4cff9440c2a6afd24ef40ba198", "lastModified": "2026-10-01T19:34:54+00:00", "modelAddress": "https://modelscope.cn/models/PleIAs/Baguettotron-MoE", "reason": null, "reconciledAt": "2026-10-01T19:53:51.515914+00:00", "repoId": "PleIAs/Baguettotron-MoE", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5221051", "taskType": "text-generation"}
-{"batchId": "b2102bd9b9df4f00a65b121fa9a87aed", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-01T20:02:01.345201+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6f4336eab1ca418ebe326cdade954706", "lastModified": "2026-10-01T19:34:54+00:00", "modelAddress": "https://modelscope.cn/models/PleIAs/Baguettotron-MoE", "repoId": "PleIAs/Baguettotron-MoE", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
+{"batchId": "b2102bd9b9df4f00a65b121fa9a87aed", "completedAt": "2026-10-01T20:02:04.614202+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-01T20:02:01.345201+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6f4336eab1ca418ebe326cdade954706", "lastModified": "2026-10-01T19:34:54+00:00", "modelAddress": "https://modelscope.cn/models/PleIAs/Baguettotron-MoE", "reason": null, "repoId": "PleIAs/Baguettotron-MoE", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5221297", "taskType": "text-generation"}
 {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925444+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba30792e89b44ef5804d5f3613d7df71", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
 {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925408+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69aec4d25f21464c860135eb90d77735", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
 {"batchId": "af702292a17240468562311292c55106", "completedAt": "2026-09-29T11:50:56.209408+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-29T11:50:53.929909+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c488d875b85a4d699fe135674c2b940b", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json
index 93b3d02bc9..c19573e2ea 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,6 +1,6 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 2744
+    "unified_success_first": 2745
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 20,
@@ -8,7 +8,7 @@
     "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 182,
     "text-generation|Ascend_910-b4|llamacpp": 16,
     "text-generation|Ascend_910-b4|vllm": 33,
-    "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 211,
+    "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 212,
     "text-generation|Biren_166m|vllm": 81,
     "text-generation|Biren_166m|vllm_fix_tokenizer": 149,
     "text-generation|Cambricon_mlu-370-x4|vllm": 73,
@@ -39,8 +39,8 @@
     "text-generation|hygon_k100-ai|vllm": 27,
     "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 152
   },
-  "acceptedSinceRefresh": 2744,
-  "acceptedTotal": 2744,
-  "generatedAt": "2026-10-01T19:43:06.359227+00:00",
+  "acceptedSinceRefresh": 2745,
+  "acceptedTotal": 2745,
+  "generatedAt": "2026-10-01T20:02:04.562048+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index cfdf0b9348..fbc3078343 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -948,3 +948,4 @@
 {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:01:50.847636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5097139", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:18:32.495861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/PleIAs/Baguettotron-MoE", "modelId": "PleIAs/Baguettotron-MoE", "submitTime": "2026-10-01T20:02:02.754254+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5221297", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
diff --git a/manifest.json b/manifest.json
index 5dc7e61a58..65197287ef 100644
--- a/manifest.json
+++ b/manifest.json
@@ -10,16 +10,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "ec9c714dde635223eb7f5550481af3a4ff97e6326f9bfe9026419293fd2022b3",
     ".modelhub_state/recent_outcomes.jsonl": "2523ec2f7019354108df01107e7f0a74a17201a51201d3993b38b265a6fafd64",
     ".modelhub_state/recovery_active_tasks.jsonl": "800682652d3ccb2b980e80393c5800c6f6187c4eb3fd4c6debc9c189875b896d",
-    ".modelhub_state/recovery_intents.jsonl": "09868368e57aa56ef5d916bfe6c7965c6f3f4f9d09d02f84ed49873684202d69",
-    ".modelhub_state/routing_intelligence.json": "c64701dd20d203315ca24adbbe74d90b8e309c02593c8cdcd78e3aede4cc0c4c",
+    ".modelhub_state/recovery_intents.jsonl": "d1a91392ade906f8358191dd44ed13889391fdaa9f6d52185b326c6432dfaa6e",
+    ".modelhub_state/routing_intelligence.json": "4cab060aa87c62b99c0f5f10e414a79361ce90d66fd3ab7f01b38511e88cd04c",
     ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
     ".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
-    "ledger/submissions.jsonl": "1e2234d83f709867316fd62a76a167e170fb0d25aa01bd22d76f258243c5c367",
-    "outcomes/submissions.jsonl": "4b0737ac12ac323c6657c021efa92a3b37c6a2eae09b4a725f06830888f9156f"
+    "ledger/submissions.jsonl": "8c167d40b3c3581bcab13ddf02528f2f4102b7018a0177680ae8992802894700",
+    "outcomes/submissions.jsonl": "d9f1c2a7646dff2615293dbeacdb58af2c000b7ac14b5bffbedcf662a1a74f9b"
   },
-  "generation": 19361,
-  "phase": "intent",
+  "generation": 19362,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-01T20:02:01.480015+00:00",
+  "updatedAt": "2026-10-01T20:02:04.724617+00:00",
   "writerId": "a812d0e025c3474eb16b828a4d987334"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index ea0158a73f..90c5040591 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -741,3 +741,4 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T18:36:11.048269+00:00", "targetGpu": "MetaX_c-500", "taskId": "5220158", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T18:56:27.055637+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5220400", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T19:43:04.553246+00:00", "targetGpu": "MetaX_c-500", "taskId": "5221051", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T20:02:02.754254+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5221297", "taskType": "text-generation", "verifyResult": null}