diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index a0cc9ccfac..731e57b3f6 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -2593,7 +2593,7 @@
 {"batchId": "bdb3433b107044be89ac60f41de26384", "completedAt": "2026-09-30T19:00:30.348719+00:00", "configFingerprint": "8120661075bb80389dd6d7b11ccbb58a0586dc072989d5570471de11994360d9", "configSource": "modelhub_live", "createdAt": "2026-09-30T19:00:27.614655+00:00", "framework": "llamacpp", "intentId": "0e7bfbad0dad4298b373def28dc6693c", "lastModified": "2026-09-30T18:36:19+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM2", "reason": null, "reconciledAt": "2026-09-30T19:08:16.574225+00:00", "repoId": "webAI-Official/TwIL-LM2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5200518", "taskType": "text-generation"}
 {"batchId": "bdb3433b107044be89ac60f41de26384", "completedAt": "2026-09-30T19:00:30.348723+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-30T19:00:27.614757+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f3bdfa0dc014403cbb6ef7b1f3938539", "lastModified": "2026-09-30T18:30:18+00:00", "modelAddress": "https://modelscope.cn/models/bench-labs/pulvis-v1", "reason": null, "reconciledAt": "2026-09-30T19:08:16.573934+00:00", "repoId": "bench-labs/pulvis-v1", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5200517", "taskType": "text-generation"}
 {"batchId": "bdb3433b107044be89ac60f41de26384", "completedAt": "2026-09-30T19:00:30.348726+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-30T19:00:27.614812+00:00", "framework": "vllm_tokenizer_patch", "intentId": "633adccab48c4d4bbc8f607a6bfd8bbc", "lastModified": "2026-09-30T18:36:41+00:00", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-G1k-2.9B-20260930", "reason": null, "reconciledAt": "2026-09-30T19:08:16.578726+00:00", "repoId": "RWKV/RWKV7-G1k-2.9B-20260930", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5200519", "taskType": "text-generation"}
-{"batchId": "b1379bf2a3e7435882fe38f2cd3ed3f6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-30T19:16:56.779960+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cf028da9e52c4ec4ba405fa5d9e3570f", "lastModified": "2026-09-30T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/K2-Horizon-3.7B-8bit", "repoId": "mlx-community/K2-Horizon-3.7B-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
+{"batchId": "b1379bf2a3e7435882fe38f2cd3ed3f6", "completedAt": "2026-09-30T19:16:59.101039+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-30T19:16:56.779960+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cf028da9e52c4ec4ba405fa5d9e3570f", "lastModified": "2026-09-30T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/K2-Horizon-3.7B-8bit", "reason": null, "repoId": "mlx-community/K2-Horizon-3.7B-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5200707", "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 913e5c564a..04d4f463b0 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,6 +1,6 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 2732
+    "unified_success_first": 2733
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 19,
@@ -8,7 +8,7 @@
     "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 181,
     "text-generation|Ascend_910-b4|llamacpp": 16,
     "text-generation|Ascend_910-b4|vllm": 32,
-    "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 208,
+    "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 209,
     "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": 2732,
-  "acceptedTotal": 2732,
-  "generatedAt": "2026-09-30T19:00:30.249854+00:00",
+  "acceptedSinceRefresh": 2733,
+  "acceptedTotal": 2733,
+  "generatedAt": "2026-09-30T19:16:59.050567+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index acf2fd1958..19dd82b01a 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -977,3 +977,4 @@
 {"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/mlx-community/K2-Horizon-3.7B-8bit", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "submitTime": "2026-09-30T19:16:58.857252+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200707", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
diff --git a/manifest.json b/manifest.json
index 8a441d1cdc..4deb6de8d3 100644
--- a/manifest.json
+++ b/manifest.json
@@ -10,16 +10,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "c1930ca8fdcacb5490295c7c7dc06f8ef1bd9c45953bf68d684e316cf0b931fd",
     ".modelhub_state/recent_outcomes.jsonl": "0ab1d5c5cfd855068e4f18ef6f8e3076175a93fcf632e662039eca492632e3b0",
     ".modelhub_state/recovery_active_tasks.jsonl": "b0e452a1a4a25c4fcccc8126ed33d1bfac9073095b0cee8e31f60ce88cff0398",
-    ".modelhub_state/recovery_intents.jsonl": "690b0e86c9a94fa7ea161e051f00c0f0183f74092d415b5ab38461dcb2b31f02",
-    ".modelhub_state/routing_intelligence.json": "3acee467c619e03f81a7d6346fdd514a8353da0af5ce8fae0943a1fa2b5cc8f2",
+    ".modelhub_state/recovery_intents.jsonl": "74135690a8f0ab158c9e8b9e569ecf5465482f0a1638d841ed48c263f99c25e2",
+    ".modelhub_state/routing_intelligence.json": "09cc69960b345ef40104091dc4737ddc82df87d637c93fb6b2c12b4e9f5ead9e",
     ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
     ".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
-    "ledger/submissions.jsonl": "fb1809be2c7f5be2db15c8cd016061ede6196b72cf872322e62f2a76ecaea3fb",
-    "outcomes/submissions.jsonl": "e539395f40fea9e609294ac12eb8b1a80a121e1d2d68723e6d82e3fe740f39dd"
+    "ledger/submissions.jsonl": "363153d14d53065505370f73337e239f58b6ab270b895ce5f2d573671c48d7a8",
+    "outcomes/submissions.jsonl": "5d5d5cac46c4439c47acddda44aa63739ba7b791f837ab93af971b025b0b2618"
   },
-  "generation": 18906,
-  "phase": "intent",
+  "generation": 18907,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-30T19:16:57.006505+00:00",
+  "updatedAt": "2026-09-30T19:16:59.207069+00:00",
   "writerId": "a812d0e025c3474eb16b828a4d987334"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index c8909cf941..31ec39d8a0 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -769,3 +769,4 @@
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8120661075bb80389dd6d7b11ccbb58a0586dc072989d5570471de11994360d9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2694119616, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T19:00:30.051413+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5200518", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T19:00:30.054397+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200517", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T19:00:30.056861+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200519", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T19:16:58.857252+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200707", "taskType": "text-generation", "verifyResult": null}