diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index ab5a69cb..4d5c423b 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -718,7 +718,7 @@
 {"batchId": "0e32c5e26c8d44099e98d9aa33f7f603", "completedAt": "2026-09-13T09:53:58.544809+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-13T09:53:52.178709+00:00", "framework": "vllm", "intentId": "24987ebd202c4babb950725a15399f0f", "lastModified": "2026-09-04T07:05:18+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "reason": null, "reconciledAt": "2026-09-13T13:53:40.761432+00:00", "repoId": "XHToken/Spark-X2.5-4B-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "4823778", "taskType": "text-generation"}
 {"batchId": "9e6a1f526fb04501aa7f550cc49f1407", "completedAt": "2026-09-13T10:16:19.691013+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-13T10:16:11.657494+00:00", "framework": "vllm", "intentId": "6569e532bda1461a8a111716e35090f8", "lastModified": "2026-09-04T07:05:18+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "reason": null, "reconciledAt": "2026-09-13T13:53:40.762230+00:00", "repoId": "XHToken/Spark-X2.5-4B-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4824251", "taskType": "text-generation"}
 {"batchId": "bf455b91f89142ef8f8904ab621e1033", "completedAt": "2026-09-13T12:09:27.439030+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:09:14.647471+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a8ef73dce3b9478da9cdd9450f6ed391", "lastModified": "2026-09-04T07:05:18+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "reason": null, "reconciledAt": "2026-09-13T13:53:40.764115+00:00", "repoId": "XHToken/Spark-X2.5-4B-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "4827491", "taskType": "text-generation"}
-{"batchId": "56e5fc4839014add86cc21b36a660ba5", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-13T14:02:32.779350+00:00", "framework": "vllm-mlu", "intentId": "a1c4897661b84b7195a5437c097752a4", "lastModified": "2026-09-04T07:05:18+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "repoId": "XHToken/Spark-X2.5-4B-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
+{"batchId": "56e5fc4839014add86cc21b36a660ba5", "completedAt": "2026-09-13T14:02:39.643118+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-13T14:02:32.779350+00:00", "framework": "vllm-mlu", "intentId": "a1c4897661b84b7195a5437c097752a4", "lastModified": "2026-09-04T07:05:18+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "reason": null, "repoId": "XHToken/Spark-X2.5-4B-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4829151", "taskType": "text-generation"}
 {"batchId": "9ea43510e22a43e9991959f19dd0f4a2", "completedAt": "2026-09-13T12:43:37.101071+00:00", "configFingerprint": "7d273c6d9a11c4e826d64fc44d3ae14d805bd3b1e6e663d4dd0b45567cfc5e3f", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:43:27.207464+00:00", "framework": "llamacpp", "intentId": "ab083753c716462fbb8b0529ac182658", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
 {"batchId": "9370c3290d2242cebbdd1924870f426b", "completedAt": "2026-09-13T12:41:31.618354+00:00", "configFingerprint": "d7cf4e4fcae21f022bbcb9f71b3bb0ab37d6331cf8fd1cd3ad4ba75043690051", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:41:17.857077+00:00", "framework": "llamacpp", "intentId": "8c62b06728694cd9b6f7c5c378f53285", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
 {"batchId": "1d3a5688cae04410969668a2e438424a", "completedAt": "2026-09-13T12:39:25.398487+00:00", "configFingerprint": "8135df5d785d2b4d7f379eb6c4b8713fe5fc1b96448a3403e4b313662765fa3b", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:39:15.319689+00:00", "framework": "llamacpp", "intentId": "0b3c0d11e71240179f6fa3afe28d4021", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "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 f5d73fc7..6feb1451 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,6 +1,6 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 853
+    "unified_success_first": 854
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 12,
@@ -9,7 +9,7 @@
     "text-generation|Ascend_910-b4|llamacpp": 9,
     "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 33,
     "text-generation|Biren_166m|vllm": 55,
-    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 30,
+    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 31,
     "text-generation|Cambricon_mlu-370-x8|vllm": 13,
     "text-generation|Cambricon_mlu-370-x8|vllm-customized": 2,
     "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 68,
@@ -26,8 +26,8 @@
     "text-generation|hygon_k100-ai|llamacpp": 12,
     "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 48
   },
-  "acceptedSinceRefresh": 853,
-  "acceptedTotal": 853,
-  "generatedAt": "2026-09-13T12:43:37.062995+00:00",
+  "acceptedSinceRefresh": 854,
+  "acceptedTotal": 854,
+  "generatedAt": "2026-09-13T14:02:39.608250+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index 9c87d115..95969256 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -793,3 +793,4 @@
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T15:58:20.200513+00:00", "targetGpu": "Vastai_va16", "taskId": "4722293", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "modelId": "OpenBMB/BitCPM-CANN-8B", "submitTime": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-09T21:08:22.097030+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746441", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T14:02:33.487789+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4829151", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
diff --git a/manifest.json b/manifest.json
index 77aaf280..09de4d37 100644
--- a/manifest.json
+++ b/manifest.json
@@ -9,16 +9,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "5b0dc54b913434ae76ea5833cabfa7c00f3e8191ff58197626eeea4fbe7a9af1",
     ".modelhub_state/recent_outcomes.jsonl": "261040cb0b506c915609dda977d7be3d82acc11edfff94fab271025c2e8594d4",
     ".modelhub_state/recovery_active_tasks.jsonl": "07f43e60c3b51c43ef2ac6721d235034a93083af48316f2a6ef82609756e5882",
-    ".modelhub_state/recovery_intents.jsonl": "499a37b01603e0493fe799f3830f5163468f03942f1a6a53aa3eb158fe7cca9c",
-    ".modelhub_state/routing_intelligence.json": "c676612ee86c9cadeb60464165c636857dacc1827858bd254c92284a746c1c02",
+    ".modelhub_state/recovery_intents.jsonl": "b9bb14c3655b7b5c81d7bea5cd027ac085412afa3fb0753046c5918f68074a9c",
+    ".modelhub_state/routing_intelligence.json": "734675c7fba079915bbfc4af7263b061a640099267c6af02c24074b9ddf0aca4",
     ".modelhub_state/submission_exclusions.jsonl": "75ddc8b4d313a8cecec2f373afc57298143d78e0eb907ca44f420d7bf9c55263",
     ".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
-    "ledger/submissions.jsonl": "c71b7954a3ed73ca8a0b695a01675ceb5c6aef90f6737f5b5dc39fa53e3a6d39",
-    "outcomes/submissions.jsonl": "60fd1690abaf373600c2bb048e14f9f4f3e5840ecdee836241ad60c84174dbbb"
+    "ledger/submissions.jsonl": "588e093cb725b904ac8eaa73167848a92b08fa966434ce484969a30ea868cd55",
+    "outcomes/submissions.jsonl": "8f6ead5bfab0bff441b2ba1f015fc8905daa21db86b2572b82ddb2075973ba0a"
   },
-  "generation": 6750,
-  "phase": "intent",
+  "generation": 6751,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-13T14:02:32.868237+00:00",
+  "updatedAt": "2026-09-13T14:02:39.699935+00:00",
   "writerId": "69701e73196b4ac2b3fad0f412335168"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index c6d99fa8..c4b17083 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -636,3 +636,4 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T09:53:52.905331+00:00", "targetGpu": "MetaX_c-500", "taskId": "4823778", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T10:16:13.410881+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4824251", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T12:09:15.680573+00:00", "targetGpu": "Vastai_va16", "taskId": "4827491", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T14:02:33.487789+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4829151", "taskType": "text-generation", "verifyResult": null}