diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index 73f6c9c1c5..d61a95293f 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -2027,66 +2027,66 @@
 {"batchId": "6e5656e9a4774f7cb7c2dd0a7e9a02cd", "completedAt": "2026-09-21T09:15:59.518569+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:10:31.270764+00:00", "framework": "vllm-customized", "intentId": "b099cc7526e640bfa03f3ba1f6baab7a", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "reason": null, "reconciledAt": "2026-09-21T09:16:01.185191+00:00", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4997718", "taskType": "text-generation"}
 {"batchId": "6e5656e9a4774f7cb7c2dd0a7e9a02cd", "completedAt": "2026-09-21T09:15:59.518647+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:10:31.272240+00:00", "framework": "vllm", "intentId": "53f834294c2049a3bf39cbcf98f4fd36", "lastModified": "2026-08-24T18:06:52+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "reason": null, "reconciledAt": "2026-09-21T09:16:01.236307+00:00", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4997802", "taskType": "text-generation"}
 {"batchId": "6e5656e9a4774f7cb7c2dd0a7e9a02cd", "completedAt": "2026-09-21T09:15:59.518650+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:10:31.272315+00:00", "framework": "vllm", "intentId": "ea88d79137ce44629aae4d90e89fe2e2", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T09:16:01.184934+00:00", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4997803", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179744+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cebf29d75d19425ab7500d52de47e22d", "lastModified": "2026-08-24T18:50:21+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179851+00:00", "framework": "vllm-mlu", "intentId": "483c2de1ca8242bf97d991b99d1e23d1", "lastModified": "2026-08-24T19:08:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179908+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c8b86cbd048b41e39e71e32ac6023276", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179954+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0cfedc5191f8418782cdc02a9fa9e439", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179997+00:00", "framework": "vllm", "intentId": "0130519d24ea4c1d86c609de7b0ca5b9", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180046+00:00", "framework": "vllm", "intentId": "774fd2ceda874ff794766116780afdfc", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180093+00:00", "framework": "vllm_tokenizer_patch", "intentId": "30a8009900a64d058e80daddcdc26591", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180133+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cedacae33c6241b78dc2ce1ff52e5e02", "lastModified": "2026-08-24T18:26:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a16-per-channel", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180172+00:00", "framework": "vllm_tokenizer_patch", "intentId": "92a1d2471fcb4928857081e5cacb7979", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180209+00:00", "framework": "vllm_tokenizer_patch", "intentId": "67f1f7f9b00d4c5fb6a94a6549dc7029", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180247+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0e3feab2ec33411381fb1e70956d1f45", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180284+00:00", "framework": "vllm_tokenizer_patch", "intentId": "025f51980c4b4d5caf3b6b40fa2540d6", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180322+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1712e8238a61476ca273ed1e7b8b2797", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180361+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ed4c907896a54e1ebe2f3cb5354a9c0d", "lastModified": "2026-08-24T19:38:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180398+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ef93338bc67548aaaf3157dc52b57af8", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180436+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3eb3862c5c404577bf0477c6a5033ed3", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180473+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5f1fe6d70439435f803d5bd089378f1f", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180510+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5c3cd9969c1d496cbd07155f782a7021", "lastModified": "2026-08-24T19:06:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180547+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ed6726d8408144679f5a829e846819d6", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180585+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ff4edb1a9a9145ecbd88677369335d19", "lastModified": "2026-09-08T15:40:32+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180622+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6cefdc45ab1c4438a35889bb2d39d04f", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180679+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4551e336aefa44659d7a0366005124d5", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180729+00:00", "framework": "vllm_tokenizer_patch", "intentId": "786011fbd35c438aaae75632690dfda7", "lastModified": "2026-08-24T18:12:10+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180779+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4241bc1ce45548039978c82c234e21e0", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180827+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3b20980706fd4225832af55ba4586d19", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180876+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9e7d85f911374332a0e719441310563a", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180925+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7bbf261e8e10485c97b454e57cd28d3d", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180973+00:00", "framework": "vllm_tokenizer_patch", "intentId": "161328b90b49478ab7df9ee63a7320dd", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181022+00:00", "framework": "vllm_tokenizer_patch", "intentId": "30c755a648ad47deb838870232517675", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181071+00:00", "framework": "vllm", "intentId": "643f1eab670c497a9790c9ae0982d5de", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181128+00:00", "framework": "vllm", "intentId": "d30c2db4e5f14a809197642e6944f9ad", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181186+00:00", "framework": "vllm", "intentId": "59649f620bcb4e2d86728caee76f4a9d", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181243+00:00", "framework": "vllm", "intentId": "7e83dbbbe4bc4b0f8fb3410da1167b75", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181300+00:00", "framework": "vllm", "intentId": "535ed840395048af9bcab3e63395eb56", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181357+00:00", "framework": "vllm", "intentId": "7aeed3007c7d4de4b04b445fa2e4d899", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181413+00:00", "framework": "vllm", "intentId": "b110bf2debdd46cf970266821192ff6c", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181470+00:00", "framework": "vllm", "intentId": "9a97a09afd2b424f950eabc251ef3ee0", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181526+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "0490a32718464dafa578d182e5076ba8", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181571+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5067a7ba3e8e437e84f417207fb181f9", "lastModified": "2026-08-31T03:35:12+00:00", "modelAddress": "https://modelscope.cn/models/logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181614+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e3f161ec29f4b48ac6def3270193141", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181657+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f20d46c42b37427dbb35998ca3f88954", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181705+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7e54f925535242768a87e12bb7a272dd", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181747+00:00", "framework": "vllm-patch-tokenizer", "intentId": "60cbcd36e23e4c199c39880210e0041a", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181789+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f7f7fb52c86948328d168ded39ff4074", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181830+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ffb0f726bb2c446182f369338de17612", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181871+00:00", "framework": "vllm-patch-tokenizer", "intentId": "db953abb739849b796903ecdd8d8f0d9", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181913+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7488ab81df5a477dad937b6ea33d9c5c", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181955+00:00", "framework": "vllm-patch-tokenizer", "intentId": "eec978de6bc04a438560170243741c9e", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181996+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c34ba90388f541339be232a032b6010b", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182038+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1c204fa4586549d79adeb6933f80fe86", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182080+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fff814e469f04c879411026a88d6cd2f", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182121+00:00", "framework": "vllm", "intentId": "3bdbcbaa45e14d2d9cb71b59a7bb3a32", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182169+00:00", "framework": "vllm", "intentId": "d936013e49804d9e82761a174a41286a", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182216+00:00", "framework": "vllm", "intentId": "999b7f2bd6f44cb7b852ebac767907d4", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182263+00:00", "framework": "vllm-customized", "intentId": "a3da45d05ad44f85879d42efa91bd525", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182321+00:00", "framework": "vllm-customized", "intentId": "eafb6b95490040ab96f0390c6f8da95e", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182378+00:00", "framework": "vllm-customized", "intentId": "880e378268844e5792aec3647a92d3f4", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182436+00:00", "framework": "vllm-customized", "intentId": "194b7748643e44be8cb50bf2c07c8ac9", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182494+00:00", "framework": "vllm-customized", "intentId": "5849cd82ac2b483ab49a8f56fdc1f6ec", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182551+00:00", "framework": "vllm-customized", "intentId": "212579130407482280177f253e6b13e8", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695944+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179851+00:00", "framework": "vllm-mlu", "intentId": "483c2de1ca8242bf97d991b99d1e23d1", "lastModified": "2026-08-24T19:08:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4997863", "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695948+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179908+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c8b86cbd048b41e39e71e32ac6023276", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4997864", "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695954+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179997+00:00", "framework": "vllm", "intentId": "0130519d24ea4c1d86c609de7b0ca5b9", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4997865", "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696104+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182551+00:00", "framework": "vllm-customized", "intentId": "212579130407482280177f253e6b13e8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696102+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182494+00:00", "framework": "vllm-customized", "intentId": "5849cd82ac2b483ab49a8f56fdc1f6ec", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696099+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182436+00:00", "framework": "vllm-customized", "intentId": "194b7748643e44be8cb50bf2c07c8ac9", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696097+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182378+00:00", "framework": "vllm-customized", "intentId": "880e378268844e5792aec3647a92d3f4", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696094+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182321+00:00", "framework": "vllm-customized", "intentId": "eafb6b95490040ab96f0390c6f8da95e", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696091+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182263+00:00", "framework": "vllm-customized", "intentId": "a3da45d05ad44f85879d42efa91bd525", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696088+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182216+00:00", "framework": "vllm", "intentId": "999b7f2bd6f44cb7b852ebac767907d4", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696086+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182169+00:00", "framework": "vllm", "intentId": "d936013e49804d9e82761a174a41286a", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696083+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182121+00:00", "framework": "vllm", "intentId": "3bdbcbaa45e14d2d9cb71b59a7bb3a32", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696081+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182080+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fff814e469f04c879411026a88d6cd2f", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696078+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.182038+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1c204fa4586549d79adeb6933f80fe86", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696076+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181996+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c34ba90388f541339be232a032b6010b", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696073+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181955+00:00", "framework": "vllm-patch-tokenizer", "intentId": "eec978de6bc04a438560170243741c9e", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696070+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181913+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7488ab81df5a477dad937b6ea33d9c5c", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696068+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181871+00:00", "framework": "vllm-patch-tokenizer", "intentId": "db953abb739849b796903ecdd8d8f0d9", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696065+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181830+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ffb0f726bb2c446182f369338de17612", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696062+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181789+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f7f7fb52c86948328d168ded39ff4074", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696059+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181747+00:00", "framework": "vllm-patch-tokenizer", "intentId": "60cbcd36e23e4c199c39880210e0041a", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696056+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181705+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7e54f925535242768a87e12bb7a272dd", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696054+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181657+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f20d46c42b37427dbb35998ca3f88954", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696051+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181614+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e3f161ec29f4b48ac6def3270193141", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696048+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181571+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5067a7ba3e8e437e84f417207fb181f9", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696045+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181526+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "0490a32718464dafa578d182e5076ba8", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696042+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181470+00:00", "framework": "vllm", "intentId": "9a97a09afd2b424f950eabc251ef3ee0", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696039+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181413+00:00", "framework": "vllm", "intentId": "b110bf2debdd46cf970266821192ff6c", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696036+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181357+00:00", "framework": "vllm", "intentId": "7aeed3007c7d4de4b04b445fa2e4d899", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696034+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181300+00:00", "framework": "vllm", "intentId": "535ed840395048af9bcab3e63395eb56", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696031+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181243+00:00", "framework": "vllm", "intentId": "7e83dbbbe4bc4b0f8fb3410da1167b75", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696028+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181186+00:00", "framework": "vllm", "intentId": "59649f620bcb4e2d86728caee76f4a9d", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696026+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181128+00:00", "framework": "vllm", "intentId": "d30c2db4e5f14a809197642e6944f9ad", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696022+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181071+00:00", "framework": "vllm", "intentId": "643f1eab670c497a9790c9ae0982d5de", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696020+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.181022+00:00", "framework": "vllm_tokenizer_patch", "intentId": "30c755a648ad47deb838870232517675", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696017+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180973+00:00", "framework": "vllm_tokenizer_patch", "intentId": "161328b90b49478ab7df9ee63a7320dd", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696014+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180925+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7bbf261e8e10485c97b454e57cd28d3d", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696012+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180876+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9e7d85f911374332a0e719441310563a", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696009+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180827+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3b20980706fd4225832af55ba4586d19", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696006+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180779+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4241bc1ce45548039978c82c234e21e0", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696004+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180729+00:00", "framework": "vllm_tokenizer_patch", "intentId": "786011fbd35c438aaae75632690dfda7", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.696001+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180679+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4551e336aefa44659d7a0366005124d5", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695998+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180622+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6cefdc45ab1c4438a35889bb2d39d04f", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695996+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180585+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ff4edb1a9a9145ecbd88677369335d19", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695993+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180547+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ed6726d8408144679f5a829e846819d6", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695991+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180510+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5c3cd9969c1d496cbd07155f782a7021", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695988+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180473+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5f1fe6d70439435f803d5bd089378f1f", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695985+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180436+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3eb3862c5c404577bf0477c6a5033ed3", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695982+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180398+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ef93338bc67548aaaf3157dc52b57af8", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695980+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180361+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ed4c907896a54e1ebe2f3cb5354a9c0d", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695976+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180322+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1712e8238a61476ca273ed1e7b8b2797", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695974+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180284+00:00", "framework": "vllm_tokenizer_patch", "intentId": "025f51980c4b4d5caf3b6b40fa2540d6", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695972+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180247+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0e3feab2ec33411381fb1e70956d1f45", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695969+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180209+00:00", "framework": "vllm_tokenizer_patch", "intentId": "67f1f7f9b00d4c5fb6a94a6549dc7029", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695967+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180172+00:00", "framework": "vllm_tokenizer_patch", "intentId": "92a1d2471fcb4928857081e5cacb7979", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695964+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180133+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cedacae33c6241b78dc2ce1ff52e5e02", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695961+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180093+00:00", "framework": "vllm_tokenizer_patch", "intentId": "30a8009900a64d058e80daddcdc26591", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695958+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.180046+00:00", "framework": "vllm", "intentId": "774fd2ceda874ff794766116780afdfc", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695951+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179954+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0cfedc5191f8418782cdc02a9fa9e439", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695921+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179744+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cebf29d75d19425ab7500d52de47e22d", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
 {"batchId": "6e5656e9a4774f7cb7c2dd0a7e9a02cd", "completedAt": "2026-09-21T09:15:59.518656+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:10:31.272436+00:00", "framework": "vllm", "intentId": "127f2e6c11c841c4a499a259419c0d52", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
 {"batchId": "6e5656e9a4774f7cb7c2dd0a7e9a02cd", "completedAt": "2026-09-21T09:15:59.518653+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:10:31.272376+00:00", "framework": "vllm", "intentId": "b62fadbfa7a04d389cea1c696a7bd9a5", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
 {"batchId": "6e5656e9a4774f7cb7c2dd0a7e9a02cd", "completedAt": "2026-09-21T09:15:59.518644+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:10:31.272171+00:00", "framework": "vllm", "intentId": "cb9f7e19d2a04f5bb8625940edfb6dac", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
@@ -2330,60 +2330,3 @@
 {"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913975+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342414+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9a25b374aa534e66b5814c8cbc3d9944", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
 {"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913970+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342339+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd21d9669f0344bf92bfba43f2718fea", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
 {"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913966+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8a9d6c4b42ec4fbabc1451982b668aa0", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913963+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342264+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1e2f4ae26340433ba848c828a32c8037", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913960+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342226+00:00", "framework": "vllm_tokenizer_patch", "intentId": "119fadf5a18f49219be7591c4ab05efe", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913957+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342188+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a865966dac654e718af93b88021a317d", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913953+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342151+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c325c22a7b5243718e5b4802060b4a78", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913950+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342112+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d6f012237fc44b4ca50964d7564ce9c2", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913946+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342074+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b5c8312512a44121b2bab7b1eb657a99", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913943+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342037+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ec983485c729450196906ea0bd55c7b9", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913933+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341919+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d7fe2a4d519a43b7a87e57f06ed6c672", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913926+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341822+00:00", "framework": "vllm", "intentId": "d68a85d02d64402f97de86717c422232", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913922+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341772+00:00", "framework": "vllm", "intentId": "285e69eaf8da4d1fa03807805fd02a33", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913917+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341718+00:00", "framework": "vllm_tokenizer_patch", "intentId": "35a96e7094bc4b2ab305fa4795c8326e", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913894+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341582+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4ecceef8c3e34e69b5633c14fd76e0d6", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466082+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127288+00:00", "framework": "vllm", "intentId": "65cef4d446084037bb13153d52b7c872", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466079+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127231+00:00", "framework": "vllm", "intentId": "a7743eff51694235ba4577c5edb0a5c8", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466076+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127174+00:00", "framework": "vllm", "intentId": "d8aff6a5552345c6aabfa8a2186a5135", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466072+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127117+00:00", "framework": "vllm", "intentId": "d8e33d1823b949bcaf896a8daec722ec", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466070+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127060+00:00", "framework": "vllm", "intentId": "dea98d25c0704d2490b41d65e43aecdc", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466067+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127002+00:00", "framework": "vllm", "intentId": "1dd7d3d2d17947428d51853e127b5a37", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466064+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126952+00:00", "framework": "vllm", "intentId": "31f45bd2446042318bf83c44f8ffdbc2", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466061+00:00", "configFingerprint": "5227b42f4cdd7539bb62412569c7d9c8b3cc2e321cdbac3654c73c95c5bc8a7b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126903+00:00", "framework": "vllm", "intentId": "0dc8605254ac478496cee133f7b44cb8", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466058+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126853+00:00", "framework": "vllm", "intentId": "6206050e79f24ed389d89018c92af3f8", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466055+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126803+00:00", "framework": "vllm", "intentId": "b3feabdf9bb94163b2f7b4a49eb1a0b3", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466053+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126736+00:00", "framework": "vllm", "intentId": "3f374cb15c944e88aa8f0b3f4e20620e", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466049+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126684+00:00", "framework": "vllm", "intentId": "0cd796e77e424fbca904186c720141cb", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466046+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126620+00:00", "framework": "vllm", "intentId": "55e5105a51c8499b86389567f4db558a", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466043+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126563+00:00", "framework": "vllm", "intentId": "dd85fce80e5545eaaf294e74d29381ee", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466040+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126505+00:00", "framework": "vllm", "intentId": "1439f29f08524d2ba67072c192b474d7", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466037+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126446+00:00", "framework": "vllm-customized", "intentId": "ec2a9bb610ab4ac7b59e5c762b2c13c9", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466034+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126388+00:00", "framework": "vllm-customized", "intentId": "953db7690844414ebc53e2bb995b392b", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466030+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126325+00:00", "framework": "vllm-customized", "intentId": "c543636f514d461ca96beda2bce5e0cd", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466027+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126258+00:00", "framework": "vllm-customized", "intentId": "a9408af601934ff19c0934155b331caa", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466024+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126200+00:00", "framework": "vllm-customized", "intentId": "5331e795426a45ae912a46a138ffab8c", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466018+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126084+00:00", "framework": "vllm-customized", "intentId": "49f939dda5c64ba881971afbaca2e265", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466015+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126027+00:00", "framework": "vllm-customized", "intentId": "8267f723d7f24c9bb934cb82b77e04e0", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466011+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125969+00:00", "framework": "vllm-customized", "intentId": "f0773bdaf3714cb3beadadbdc2ba7a05", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466008+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125912+00:00", "framework": "vllm-customized", "intentId": "7ac62c3d6d254551b1196a595ee8d817", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466004+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125854+00:00", "framework": "vllm-customized", "intentId": "c2397a88a700409884255cd4ceac9e78", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466001+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125796+00:00", "framework": "vllm-customized", "intentId": "eefa8f825dba45839d0c0fd8c8317b75", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465997+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125737+00:00", "framework": "vllm-customized", "intentId": "661457e8fda14a4e87f94b2ae7fbd37c", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465995+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125642+00:00", "framework": "vllm-customized", "intentId": "a805cd2d97ec422da4481e978d11ac33", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465991+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125584+00:00", "framework": "vllm-customized", "intentId": "a8ed45a1df7c48e1b397f5702e9385d2", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465988+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125526+00:00", "framework": "vllm-customized", "intentId": "610bfc3cde544bd688248ef7ec7c32a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465985+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125468+00:00", "framework": "vllm-customized", "intentId": "10d2af58fce14a56b9343f75381d0b9f", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465973+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125409+00:00", "framework": "vllm-customized", "intentId": "ac863f030f584455907bf3d1744a74f1", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465969+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125349+00:00", "framework": "vllm-customized", "intentId": "00ceebf321ff4788bac1eb507aa38445", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465965+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125277+00:00", "framework": "vllm-customized", "intentId": "2676465be98249de9e19d1984aa38ebc", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465948+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125132+00:00", "framework": "vllm-customized", "intentId": "a26ea7938dc94d4091a4cbe156cc1ab0", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315329+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767639+00:00", "framework": "vllm-customized", "intentId": "e23c9fd8517b4dac849715ba32859ee2", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315327+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767575+00:00", "framework": "vllm-customized", "intentId": "7af34205855749fda78ab521eb660c4a", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315324+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767482+00:00", "framework": "vllm-customized", "intentId": "99921f6d1e394490a08418b051c47861", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315322+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767379+00:00", "framework": "vllm-customized", "intentId": "12f740f583274bd3a3e8587e8ad23b08", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315319+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767275+00:00", "framework": "vllm-customized", "intentId": "1371336dbd9041afba53ddb4f4c9578c", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315316+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767216+00:00", "framework": "vllm-customized", "intentId": "575c313d68de4214b53f571b834d579b", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315313+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767156+00:00", "framework": "vllm-customized", "intentId": "7ed95f4066fb4cccaf76a0f013a59c9b", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315311+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767094+00:00", "framework": "vllm-customized", "intentId": "08d6e38a9ca043c3ada5fcd606c32a2d", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315308+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767038+00:00", "framework": "vllm", "intentId": "963fce0f5a0945f78b05c123e03cb6ca", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315305+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.766983+00:00", "framework": "vllm", "intentId": "2776908a67e849898da6f2586f3c95b3", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json
index fff34ee15c..af945773cf 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,10 +1,10 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 2166
+    "unified_success_first": 2169
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 17,
-    "text-generation|Ascend_910-b3|vllm": 37,
+    "text-generation|Ascend_910-b3|vllm": 38,
     "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 147,
     "text-generation|Ascend_910-b4|llamacpp": 13,
     "text-generation|Ascend_910-b4|vllm": 26,
@@ -13,7 +13,7 @@
     "text-generation|Biren_166m|vllm_fix_tokenizer": 121,
     "text-generation|Cambricon_mlu-370-x4|vllm": 69,
     "text-generation|Cambricon_mlu-370-x4|vllm-customized": 5,
-    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82,
+    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 83,
     "text-generation|Cambricon_mlu-370-x8|vllm": 55,
     "text-generation|Cambricon_mlu-370-x8|vllm-customized": 54,
     "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 96,
@@ -26,7 +26,7 @@
     "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 3,
     "text-generation|Iluvatar_mrv-100|vllm": 62,
     "text-generation|Kunlunxin_p-800|vllm": 48,
-    "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 182,
+    "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 183,
     "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 76,
     "text-generation|MetaX_c-500|vllm": 104,
     "text-generation|Mthreads_s4000|llamacpp": 17,
@@ -38,8 +38,8 @@
     "text-generation|hygon_k100-ai|vllm": 26,
     "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 123
   },
-  "acceptedSinceRefresh": 2166,
-  "acceptedTotal": 2166,
-  "generatedAt": "2026-09-21T09:15:59.449866+00:00",
+  "acceptedSinceRefresh": 2169,
+  "acceptedTotal": 2169,
+  "generatedAt": "2026-09-21T09:27:59.634197+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index ff5c717650..62c40e5cde 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -1174,3 +1174,6 @@
 {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T20:09:24.405809+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986872", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"}
 {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T20:09:24.421834+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "submitTime": "2026-09-21T09:19:32.873304+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4997863", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "submitTime": "2026-09-21T09:19:32.876555+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997864", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "modelId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "submitTime": "2026-09-21T09:19:32.868721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997865", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
diff --git a/manifest.json b/manifest.json
index 3008ebd847..29193abe33 100644
--- a/manifest.json
+++ b/manifest.json
@@ -10,16 +10,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "f4afc5dbbf57b883780778e798518d72ad1770b7d52c2f9efa7ac7bca07813f7",
     ".modelhub_state/recent_outcomes.jsonl": "29645852c80da99cdb708760921f2785d26a1b7f12d289cc38563a12f682ce62",
     ".modelhub_state/recovery_active_tasks.jsonl": "c33633da6f1e4c1da942ed887ad921257d1b79ac562126e3c78df78a4c239258",
-    ".modelhub_state/recovery_intents.jsonl": "0de1a1f0047a55fafa83cca5a07d3cf86233dee016a40d8c0b2574e8a6145a3c",
-    ".modelhub_state/routing_intelligence.json": "221af1e2f162ee569e9b02e5910eac54398430330fbd5ff8d49661663cfb6560",
+    ".modelhub_state/recovery_intents.jsonl": "270b9b2e5c8b4c51e12d057954006044a476cd2b7aa122138bf77bc88c945dac",
+    ".modelhub_state/routing_intelligence.json": "ee93b37b258842826203a9eab7522dc5b7dd0051bdac67b7b53f7bb023b4576f",
     ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
     ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
-    "ledger/submissions.jsonl": "9e4cecb0ff8fca4444dc8867bda75fd6c6f8b11127bdae8649a955bf0768ce00",
-    "outcomes/submissions.jsonl": "a6a924d069331c7b8a90b5878c8291c803847257cdea461f59afc4151038e3a5"
+    "ledger/submissions.jsonl": "2ced7b80e59a51b52d62d76b0248a9911549f17c553470b41e49a99581e66f30",
+    "outcomes/submissions.jsonl": "881045402010314785a3d7b4215ac63e23701bb85d687a34b9f71e3b2bcd9065"
   },
-  "generation": 11359,
-  "phase": "intent",
+  "generation": 11360,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-21T09:19:21.381656+00:00",
+  "updatedAt": "2026-09-21T09:27:59.837304+00:00",
   "writerId": "8b35139af6674067a339a670222d4b67"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index 58f7931196..e322526a33 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -1134,3 +1134,6 @@
 {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "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": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "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": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:10:32.259004+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4997718", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:13:51.958882+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997802", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:13:58.610056+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997803", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13594088584, "estimatedRequiredGiB": 15.203, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 13603621925, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12247782400, "modelscopeTags": ["license:apache-2.0", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 13603621925}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:19:32.873304+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4997863", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231252716, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T08:44:09.587569+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233101396}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:19:32.876555+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997864", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "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": 1233118759, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233118759}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:19:32.868721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997865", "taskType": "text-generation", "verifyResult": null}