diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index 8bd66ff8e..46e56bd94 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -1738,72 +1738,72 @@
 {"batchId": "748c2571b3404f7eacf07d9209eb073f", "completedAt": "2026-09-20T18:47:13.376634+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:39:27.655629+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8fdb400a0dfe4775a7ddfa4fd588864d", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T18:51:33.444278+00:00", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4985663", "taskType": "text-generation"}
 {"batchId": "748c2571b3404f7eacf07d9209eb073f", "completedAt": "2026-09-20T18:47:13.376663+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:39:27.656025+00:00", "framework": "vllm-mlu", "intentId": "1c5d70f0fac74c119617484ebf63526b", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "reason": null, "reconciledAt": "2026-09-20T18:51:33.444554+00:00", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985692", "taskType": "text-generation"}
 {"batchId": "070db734079f4aca9551a5cf6b84acd8", "completedAt": "2026-09-20T18:51:31.954982+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:47:14.182259+00:00", "framework": "vllm-customized", "intentId": "470923c8dd894be8b6a39eded0a3d13b", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "reason": null, "reconciledAt": "2026-09-20T18:51:33.442005+00:00", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985774", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.632970+00:00", "framework": "vllm_tokenizer_patch", "intentId": "29415d6fcf7b49b6b5b680ff029f57bc", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633081+00:00", "framework": "vllm-mlu", "intentId": "53d05c77376e4e39a82e4d4fb2f6fb31", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633137+00:00", "framework": "vllm-mlu", "intentId": "7c3ff29f2362400ea07ddc1d051bdd80", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633188+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e170d093182d4b55963ec22fdaec989b", "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": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633230+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e56bbb79d2af49aba071bbc0f132defb", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633269+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4d87448a072f43939da6f1dd9042e10a", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633308+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd269724b144421fbfa386856b5f7d44", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633346+00:00", "framework": "vllm_tokenizer_patch", "intentId": "562eb0277eb04deea7243014bf92bc2f", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633383+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f46e393f4d834972a6beb8d113afd971", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633421+00:00", "framework": "vllm_tokenizer_patch", "intentId": "339b9502c51447ef9ec16d113552671f", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633458+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5d14d53c805b4be2adf7af31fd8204d6", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633496+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d55960e2d4174e288ef45d4334d7f1e1", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633533+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d308cad63b6f450ba3f7f80526ee7c1d", "lastModified": "2026-08-24T19:40:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633585+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4c28895945674ca7b91d54723ff863d5", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633635+00:00", "framework": "vllm", "intentId": "304721cce5eb4813a7078592dc16a4f6", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633702+00:00", "framework": "vllm", "intentId": "be04f7a784f84f20bb7062cbca8724ba", "lastModified": "2026-08-31T14:36:00+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633761+00:00", "framework": "vllm", "intentId": "8a86c35a8bed4a26949ca18c523b18c8", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633818+00:00", "framework": "vllm", "intentId": "3347a771c9fe4d06941f2cc163197ab7", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633875+00:00", "framework": "vllm", "intentId": "6c9369f65d524741b094df4a57675243", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633931+00:00", "framework": "vllm", "intentId": "4bb5bb82553f4bb9afa64a2cf73be5d0", "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, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633989+00:00", "framework": "vllm", "intentId": "a39c2113e7374b3a92d8ab5419528c81", "lastModified": "2026-08-26T20:08:51+00:00", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634091+00:00", "framework": "vllm", "intentId": "4fa5f82106984218a9f29d98b9dcc809", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634148+00:00", "framework": "vllm", "intentId": "5dad35547b464dabb1ba3c3cc232e47e", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634204+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c440ef54fa3043d2b0de67ee3d143782", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634248+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1fa64f9af840479d91e82bc23d00716d", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634292+00:00", "framework": "vllm_fix_tokenizer", "intentId": "75941df9c92c4eba964806c3694a543c", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634335+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed9e23f23d964907af0b614676fb193f", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634379+00:00", "framework": "vllm_fix_tokenizer", "intentId": "03d7a74f48d248e4a30895ce1b5c3cd6", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634422+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8d50b356d2b74c93bbdafa4fadb2f942", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634465+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2a1225e1abe64a518c9816fcf65a158d", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634508+00:00", "framework": "vllm-patch-tokenizer", "intentId": "59ca23712857479fba56ff3a8d7e96af", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634551+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5a77ae1f99374ee58e36d8947d894167", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634593+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a3173fc554304e6ea1497dac76ac3cf9", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634636+00:00", "framework": "vllm-patch-tokenizer", "intentId": "bfb928b9cc52431ab442c61ee4e545c0", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634685+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f6e1affc710f4602a1e6f63a0fdedf0f", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634727+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c6a03b817144486f95b02ee507817756", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634769+00:00", "framework": "vllm-patch-tokenizer", "intentId": "52fa13a2386a473f83d97d6d5c379e07", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634811+00:00", "framework": "vllm-patch-tokenizer", "intentId": "99ed4c0273284d67979c3a391cdecd5b", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634853+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a7ee602476d8428da3fa564f7a8e1724", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634896+00:00", "framework": "vllm-patch-tokenizer", "intentId": "41f7c65309204d08bbfe08340e24e2c5", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634939+00:00", "framework": "vllm-patch-tokenizer", "intentId": "abd721f8f3c64bd7ab44f27c7b0c7ee6", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634982+00:00", "framework": "vllm-patch-tokenizer", "intentId": "889c0d2c369041d9b6d6d0aded14b595", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635024+00:00", "framework": "vllm-patch-tokenizer", "intentId": "63190001dd954e5e9032f752b0e7cbb6", "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": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635066+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9fb39de03c9244a9865d8adddc396ac0", "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": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635108+00:00", "framework": "vllm-patch-tokenizer", "intentId": "075e6d2eba034de2ae341bcbb8ab2db0", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635151+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4592ed487edf42beaba3cd5861adce3a", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635193+00:00", "framework": "vllm-patch-tokenizer", "intentId": "566758a6357f4f6bb144d89c39c444fb", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635236+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e1e13bfe2def4fb28ecac0872a94ea9a", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635278+00:00", "framework": "vllm", "intentId": "17a87c01dc3c4d808bbdc9f3642e9f88", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635327+00:00", "framework": "vllm", "intentId": "3692fcabaea3455f88031bc99bcda614", "lastModified": "2026-08-24T19:54:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635375+00:00", "framework": "vllm", "intentId": "8053a91bf7a147aeb15d80f54e16f458", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635423+00:00", "framework": "vllm", "intentId": "529d4a0a4415467393914fc525620382", "lastModified": "2026-08-24T20:02:14+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635471+00:00", "framework": "vllm", "intentId": "96a2b16b1b3948629fb955abc9f4a239", "lastModified": "2026-09-11T15:31:18+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635518+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4eed6acd64d841bf9a0554b939cecd34", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635562+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f83def65cc1a4fd9b11a7a76fbf6616f", "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": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635602+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3281c8ff3b274012b98e00585fa82d25", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635642+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6567432b556a4a79bab994a74f6cdf9f", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635686+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63929a1cbfd6427ca335ffdf0965b243", "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": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635726+00:00", "framework": "vllm-customized", "intentId": "5264b955e5a344d0b64b5f18cc1e0c02", "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": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635786+00:00", "framework": "vllm-customized", "intentId": "52b81e6028c9474aa912a908dd823761", "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": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635844+00:00", "framework": "vllm-customized", "intentId": "15086f61087b4b3cab0f3b5ec4da46cc", "lastModified": "2026-08-24T20:26:05+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635902+00:00", "framework": "vllm-customized", "intentId": "a02ceaa273bf47209596ad95bf273320", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635960+00:00", "framework": "vllm-customized", "intentId": "0573f4bda9c846b786872eb57a10cf62", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636018+00:00", "framework": "vllm-customized", "intentId": "3c2871c6a7d94965861f0e37d7014653", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636075+00:00", "framework": "vllm-customized", "intentId": "56028211ea4f4948957f28560878403f", "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": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636132+00:00", "framework": "vllm-customized", "intentId": "34ac1cf1319a4fa08b40890c707b3370", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339180+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.632970+00:00", "framework": "vllm_tokenizer_patch", "intentId": "29415d6fcf7b49b6b5b680ff029f57bc", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "reason": null, "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4985843", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339203+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633081+00:00", "framework": "vllm-mlu", "intentId": "53d05c77376e4e39a82e4d4fb2f6fb31", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4985841", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339207+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633137+00:00", "framework": "vllm-mlu", "intentId": "7c3ff29f2362400ea07ddc1d051bdd80", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4985846", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339210+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633188+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e170d093182d4b55963ec22fdaec989b", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "reason": null, "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4985844", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339213+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633230+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e56bbb79d2af49aba071bbc0f132defb", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "reason": null, "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4985847", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339224+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633308+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd269724b144421fbfa386856b5f7d44", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4985848", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339228+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633346+00:00", "framework": "vllm_tokenizer_patch", "intentId": "562eb0277eb04deea7243014bf92bc2f", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "reason": null, "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4985845", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339237+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633458+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5d14d53c805b4be2adf7af31fd8204d6", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "reason": null, "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4985842", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339304+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634593+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a3173fc554304e6ea1497dac76ac3cf9", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "reason": null, "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4985871", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339338+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635108+00:00", "framework": "vllm-patch-tokenizer", "intentId": "075e6d2eba034de2ae341bcbb8ab2db0", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "reason": null, "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4985872", "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339398+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636132+00:00", "framework": "vllm-customized", "intentId": "34ac1cf1319a4fa08b40890c707b3370", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339395+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636075+00:00", "framework": "vllm-customized", "intentId": "56028211ea4f4948957f28560878403f", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339392+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636018+00:00", "framework": "vllm-customized", "intentId": "3c2871c6a7d94965861f0e37d7014653", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339389+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635960+00:00", "framework": "vllm-customized", "intentId": "0573f4bda9c846b786872eb57a10cf62", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339386+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635902+00:00", "framework": "vllm-customized", "intentId": "a02ceaa273bf47209596ad95bf273320", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339384+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635844+00:00", "framework": "vllm-customized", "intentId": "15086f61087b4b3cab0f3b5ec4da46cc", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339381+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635786+00:00", "framework": "vllm-customized", "intentId": "52b81e6028c9474aa912a908dd823761", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339378+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635726+00:00", "framework": "vllm-customized", "intentId": "5264b955e5a344d0b64b5f18cc1e0c02", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339375+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635686+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63929a1cbfd6427ca335ffdf0965b243", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339372+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635642+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6567432b556a4a79bab994a74f6cdf9f", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339369+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635602+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3281c8ff3b274012b98e00585fa82d25", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339367+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635562+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f83def65cc1a4fd9b11a7a76fbf6616f", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339364+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635518+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4eed6acd64d841bf9a0554b939cecd34", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339361+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635471+00:00", "framework": "vllm", "intentId": "96a2b16b1b3948629fb955abc9f4a239", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339358+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635423+00:00", "framework": "vllm", "intentId": "529d4a0a4415467393914fc525620382", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339355+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635375+00:00", "framework": "vllm", "intentId": "8053a91bf7a147aeb15d80f54e16f458", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339353+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635327+00:00", "framework": "vllm", "intentId": "3692fcabaea3455f88031bc99bcda614", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339350+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635278+00:00", "framework": "vllm", "intentId": "17a87c01dc3c4d808bbdc9f3642e9f88", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339347+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635236+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e1e13bfe2def4fb28ecac0872a94ea9a", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339344+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635193+00:00", "framework": "vllm-patch-tokenizer", "intentId": "566758a6357f4f6bb144d89c39c444fb", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339341+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635151+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4592ed487edf42beaba3cd5861adce3a", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339336+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635066+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9fb39de03c9244a9865d8adddc396ac0", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339332+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635024+00:00", "framework": "vllm-patch-tokenizer", "intentId": "63190001dd954e5e9032f752b0e7cbb6", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339329+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634982+00:00", "framework": "vllm-patch-tokenizer", "intentId": "889c0d2c369041d9b6d6d0aded14b595", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339326+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634939+00:00", "framework": "vllm-patch-tokenizer", "intentId": "abd721f8f3c64bd7ab44f27c7b0c7ee6", "repoId": "RedHatAI/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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339323+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634896+00:00", "framework": "vllm-patch-tokenizer", "intentId": "41f7c65309204d08bbfe08340e24e2c5", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339320+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634853+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a7ee602476d8428da3fa564f7a8e1724", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339318+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634811+00:00", "framework": "vllm-patch-tokenizer", "intentId": "99ed4c0273284d67979c3a391cdecd5b", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339315+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634769+00:00", "framework": "vllm-patch-tokenizer", "intentId": "52fa13a2386a473f83d97d6d5c379e07", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339312+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634727+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c6a03b817144486f95b02ee507817756", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339309+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634685+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f6e1affc710f4602a1e6f63a0fdedf0f", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339306+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634636+00:00", "framework": "vllm-patch-tokenizer", "intentId": "bfb928b9cc52431ab442c61ee4e545c0", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339301+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634551+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5a77ae1f99374ee58e36d8947d894167", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339299+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634508+00:00", "framework": "vllm-patch-tokenizer", "intentId": "59ca23712857479fba56ff3a8d7e96af", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339296+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634465+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2a1225e1abe64a518c9816fcf65a158d", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339293+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634422+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8d50b356d2b74c93bbdafa4fadb2f942", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339290+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634379+00:00", "framework": "vllm_fix_tokenizer", "intentId": "03d7a74f48d248e4a30895ce1b5c3cd6", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339287+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634335+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed9e23f23d964907af0b614676fb193f", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339285+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634292+00:00", "framework": "vllm_fix_tokenizer", "intentId": "75941df9c92c4eba964806c3694a543c", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339282+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634248+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1fa64f9af840479d91e82bc23d00716d", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339279+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634204+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c440ef54fa3043d2b0de67ee3d143782", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339275+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634148+00:00", "framework": "vllm", "intentId": "5dad35547b464dabb1ba3c3cc232e47e", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339271+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634091+00:00", "framework": "vllm", "intentId": "4fa5f82106984218a9f29d98b9dcc809", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339268+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633989+00:00", "framework": "vllm", "intentId": "a39c2113e7374b3a92d8ab5419528c81", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339265+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633931+00:00", "framework": "vllm", "intentId": "4bb5bb82553f4bb9afa64a2cf73be5d0", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339262+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633875+00:00", "framework": "vllm", "intentId": "6c9369f65d524741b094df4a57675243", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339259+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633818+00:00", "framework": "vllm", "intentId": "3347a771c9fe4d06941f2cc163197ab7", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339256+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633761+00:00", "framework": "vllm", "intentId": "8a86c35a8bed4a26949ca18c523b18c8", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339253+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633702+00:00", "framework": "vllm", "intentId": "be04f7a784f84f20bb7062cbca8724ba", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339251+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633635+00:00", "framework": "vllm", "intentId": "304721cce5eb4813a7078592dc16a4f6", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339246+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633585+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4c28895945674ca7b91d54723ff863d5", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339244+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633533+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d308cad63b6f450ba3f7f80526ee7c1d", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339240+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633496+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d55960e2d4174e288ef45d4334d7f1e1", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339234+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633421+00:00", "framework": "vllm_tokenizer_patch", "intentId": "339b9502c51447ef9ec16d113552671f", "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": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339231+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633383+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f46e393f4d834972a6beb8d113afd971", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "fab8fc98780349e99e8b3476b735dd02", "completedAt": "2026-09-20T19:01:16.339216+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633269+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4d87448a072f43939da6f1dd9042e10a", "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": "070db734079f4aca9551a5cf6b84acd8", "completedAt": "2026-09-20T18:51:31.955066+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:47:14.183624+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1724a619ac5248c590d484cf71f3b79f", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
 {"batchId": "070db734079f4aca9551a5cf6b84acd8", "completedAt": "2026-09-20T18:51:31.955063+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:47:14.183569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1fcbdc0dc1f24b90b55e899f6560a152", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
 {"batchId": "070db734079f4aca9551a5cf6b84acd8", "completedAt": "2026-09-20T18:51:31.955060+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:47:14.183515+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a6a4fe8617024da4ab3f3de4da172270", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
@@ -2048,59 +2048,3 @@
 {"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687359+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859811+00:00", "framework": "vllm", "intentId": "3f3e28bd1b2843f699372a73315960ff", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
 {"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687356+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859764+00:00", "framework": "vllm", "intentId": "398624f702064c77b849bbdb5a25038d", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
 {"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687353+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859717+00:00", "framework": "vllm", "intentId": "7e2065f7dfac49bbbd76030107983b24", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687350+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859669+00:00", "framework": "vllm", "intentId": "6ff43cc5b136417a84d686d7226d6fb8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687347+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859618+00:00", "framework": "vllm", "intentId": "58a654da6c6f47a3a036aad95a414fce", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687344+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859571+00:00", "framework": "vllm", "intentId": "be7b582b99a94df8bc47478b65c3a54a", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687341+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859523+00:00", "framework": "vllm", "intentId": "e7a6c55dc6124cf99f25d57ca751db45", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687338+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859476+00:00", "framework": "vllm", "intentId": "45633ede07234a4495535d550ca52e90", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687336+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859428+00:00", "framework": "vllm", "intentId": "79edcc6d0fb7438cb126f0eec62d4a01", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687333+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859381+00:00", "framework": "vllm", "intentId": "2e84962954314aba8ce6b86838d41ad6", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687330+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859333+00:00", "framework": "vllm", "intentId": "3b4fd9463f9d41dc8343618cf681d196", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687327+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859285+00:00", "framework": "vllm", "intentId": "9d21f1875f2b4d7bb850fa5c9c91cea0", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687323+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859237+00:00", "framework": "vllm", "intentId": "9ecb10721bd24e4b814494e34860e0b0", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687321+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859194+00:00", "framework": "vllm-patch-tokenizer", "intentId": "02a2712e8f434a599ad9678a0ac11341", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687317+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859151+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9fa3eaf0b01e4cb5a0956436e2454607", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687314+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859108+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9f536c6f58c2483b89a6fe7fe14ca8b1", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687311+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859065+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6adae3cd1f7a4eaea2074d5090a7cd5a", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687308+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.859020+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9abb49a3dfe441ef842aefd2ff1f6f2c", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687298+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.858849+00:00", "framework": "vllm", "intentId": "07a506b179f0482aa23708aba0bfd14c", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687285+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.858614+00:00", "framework": "vllm-mlu", "intentId": "d3eaf6e4f5db4c6787530112b0eab516", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687281+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.858558+00:00", "framework": "vllm-mlu", "intentId": "4ab318caec164511a5ba20d5440ec3a0", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "cf1a636e34204cb5aac76b0f3ab28e70", "completedAt": "2026-09-20T18:02:47.687258+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:55:41.858453+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c4be38efc20f4c588ed5a9997e7744f3", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971458+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093477+00:00", "framework": "vllm_fix_tokenizer", "intentId": "65946c0f4a7040009864f784d43f933e", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971455+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093422+00:00", "framework": "vllm_fix_tokenizer", "intentId": "43923da2c7d44dd3a1c21a80ed6affcc", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971453+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093367+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e74232cd25d34efbb51b84ea6c088f6d", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971450+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093313+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0911cb883c1b437392b77f4d420243cf", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971447+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093258+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1085c9f95b18485d992ce41e49dfbf50", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971444+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093204+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4e4bab49da2c40538c052a4ed1e06619", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971441+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093148+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5141f7f36e2f4ec19129c492892835c7", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971438+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093094+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c29f7b3adf504c9986b13c6d18be3ed6", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971436+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.093039+00:00", "framework": "vllm_fix_tokenizer", "intentId": "61ce2d2e53084bb4897b8a5766d0ec0d", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971433+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092984+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9b542d0788484892a3e6b73ec6d654b2", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971430+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092923+00:00", "framework": "vllm_fix_tokenizer", "intentId": "06b1947d1a4e42dda46914f6bc6f9785", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971428+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092868+00:00", "framework": "vllm_fix_tokenizer", "intentId": "470d4db8c384484c97068a00e10f6386", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971425+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092813+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2032311d0b27447095292370f14c43ae", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971422+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092758+00:00", "framework": "vllm_fix_tokenizer", "intentId": "60605a5a783a4954b100ca98f686b426", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971420+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092703+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ae30ce4d1f8a471897096e3b9220fb2a", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971417+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092636+00:00", "framework": "vllm_fix_tokenizer", "intentId": "622f8cdebfb641aeaf22f3234d5c0c83", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971414+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092581+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c1d6b3795ee342b2b4f3dc35c2d88878", "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971411+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092526+00:00", "framework": "vllm_fix_tokenizer", "intentId": "42816817d2df40608ef7da3571fd45f3", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971409+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092472+00:00", "framework": "vllm_fix_tokenizer", "intentId": "eb990281e9024744ad17d148de9d255b", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971406+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "56249d1efda5400fa1831bef833bc279", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971402+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092361+00:00", "framework": "vllm_fix_tokenizer", "intentId": "61362c06dd644d639ecce061b58af4f7", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971399+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092305+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9fad8ee38409449c95dc80d92f30e787", "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971397+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092242+00:00", "framework": "vllm_fix_tokenizer", "intentId": "333b65b90e3a4d56ae9f573ea239741e", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971394+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092184+00:00", "framework": "vllm_fix_tokenizer", "intentId": "69c18e5a049f423e9bf184d01ee36f91", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971391+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092124+00:00", "framework": "vllm", "intentId": "25ba4a42da684d48adf33e9a871f7f16", "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": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971388+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092060+00:00", "framework": "vllm", "intentId": "5fbc35815b7e479db4a96052d3292df8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971385+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.092017+00:00", "framework": "vllm", "intentId": "a5e7052df5214e99af8b20274f06df9e", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971382+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091975+00:00", "framework": "vllm", "intentId": "e3101515c8694a6e85b160d86c5a677f", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971379+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091932+00:00", "framework": "vllm", "intentId": "bee0ba24b263497e80b05637294f413e", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971376+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091884+00:00", "framework": "vllm", "intentId": "f006fffb18004263a3bc67898f81892a", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971374+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091842+00:00", "framework": "vllm", "intentId": "ebb67cbbc90a4053ba840bfa307d2f68", "repoId": "aisingapore/Gemma-SEA-LION-v3-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971371+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091800+00:00", "framework": "vllm", "intentId": "fda67c6d329142ba8c984ba9838e8940", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971369+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091758+00:00", "framework": "vllm", "intentId": "98d3bc23ef1c47aa81347d2984a31701", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971366+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091714+00:00", "framework": "vllm", "intentId": "a71620f1ad924623960115da8ee342e1", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971363+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091656+00:00", "framework": "vllm", "intentId": "e0804f30ecd544e08220cdf863b09d63", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971360+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091613+00:00", "framework": "vllm", "intentId": "feab22ccabad47798262684eb8c26d50", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
-{"batchId": "5fe296d13fbd4fbb9daa2fb3741fd055", "completedAt": "2026-09-20T17:54:08.971357+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-20T17:49:20.091570+00:00", "framework": "vllm", "intentId": "0eddf7d058bf4984a6752f590a244791", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json
index 15e9ac876..f4d36044b 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,19 +1,19 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 1878
+    "unified_success_first": 1888
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 17,
     "text-generation|Ascend_910-b3|vllm": 33,
-    "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 135,
+    "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 140,
     "text-generation|Ascend_910-b4|llamacpp": 13,
     "text-generation|Ascend_910-b4|vllm": 20,
-    "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 129,
+    "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 130,
     "text-generation|Biren_166m|vllm": 79,
     "text-generation|Biren_166m|vllm_fix_tokenizer": 13,
     "text-generation|Cambricon_mlu-370-x4|vllm": 50,
     "text-generation|Cambricon_mlu-370-x4|vllm-customized": 2,
-    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 80,
+    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82,
     "text-generation|Cambricon_mlu-370-x8|vllm": 55,
     "text-generation|Cambricon_mlu-370-x8|vllm-customized": 35,
     "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 92,
@@ -35,10 +35,10 @@
     "text-generation|Vastai_va16|vllm_fix_tokenizer": 74,
     "text-generation|hygon_k100-ai|llamacpp": 18,
     "text-generation|hygon_k100-ai|vllm": 26,
-    "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 110
+    "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 112
   },
-  "acceptedSinceRefresh": 1878,
-  "acceptedTotal": 1878,
-  "generatedAt": "2026-09-20T18:51:31.894004+00:00",
+  "acceptedSinceRefresh": 1888,
+  "acceptedTotal": 1888,
+  "generatedAt": "2026-09-20T19:01:16.273248+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index 6f98cc725..819658784 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -995,7 +995,6 @@
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T18:39:41.567990+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985663", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
 {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "modelId": "inceptionai/Jais-2-8B-Chat", "submitTime": "2026-09-20T18:39:53.164098+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985692", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
 {"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "modelId": "sapientinc/HRM-Text-1B", "submitTime": "2026-09-20T18:47:15.075816+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985774", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
-{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T03:25:33.082653+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969693", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-20T03:30:31.100436+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969813", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"}
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T03:41:49.051083+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970006", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "submitTime": "2026-09-20T03:41:49.009007+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970003", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
@@ -1122,3 +1121,13 @@
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "modelId": "aisingapore/SEA-LION-v1-7B", "submitTime": "2026-09-20T12:55:19.835166+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979183", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "submitTime": "2026-09-20T13:22:06.962643+00:00", "targetGpu": "Biren_166m", "taskId": "4979624", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "modelId": "LiquidAI/LFM2.5-2.6B", "submitTime": "2026-09-20T14:26:18.189644+00:00", "targetGpu": "Biren_166m", "taskId": "4980427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "modelId": "neuralmagic/starcoder2-3b-FP8", "submitTime": "2026-09-20T18:54:50.769551+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4985843", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-20T18:54:50.753303+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4985841", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "submitTime": "2026-09-20T18:54:50.779862+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4985846", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "modelId": "neuralmagic/starcoder2-7b-FP8", "submitTime": "2026-09-20T18:54:50.771337+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985844", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "submitTime": "2026-09-20T18:54:50.781158+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "submitTime": "2026-09-20T18:54:50.778321+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985848", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "submitTime": "2026-09-20T18:54:50.767556+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985845", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "submitTime": "2026-09-20T18:54:50.763750+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985842", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-20T18:56:13.145823+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4985871", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "modelId": "RedHatAI/starcoder2-15b-FP8", "submitTime": "2026-09-20T18:57:33.406739+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4985872", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
diff --git a/manifest.json b/manifest.json
index 3dffce396..471ca935c 100644
--- a/manifest.json
+++ b/manifest.json
@@ -9,16 +9,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "51060760318808c95c5f937aac9389cef4379d95a33f6213764b0f798b1c6bb9",
     ".modelhub_state/recent_outcomes.jsonl": "15e6bd7829e8e77d7c46a9e2035cd3a77ca652112c645fe83c727c723083bd64",
     ".modelhub_state/recovery_active_tasks.jsonl": "4c461c92d603ecbd77094fd4fa2b870a759f7eb06a9c7151b2f230c9dc442216",
-    ".modelhub_state/recovery_intents.jsonl": "ec54399b29c319c8ea4727fd6409300e23fcb3f235dc71be461e28d41995a8a6",
-    ".modelhub_state/routing_intelligence.json": "a124ea5f4e4a166a71780eb04d0b25316cb234982b1e4094a310afd0533d79af",
+    ".modelhub_state/recovery_intents.jsonl": "b4db1e903d1669b642a346fc1f9c45fe97e66dd58a9ac24484fc885b80570636",
+    ".modelhub_state/routing_intelligence.json": "f059393f6b8c71f7ae023b913ba5c2e6c1f6d57a918cd2c41510de709119a526",
     ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
     ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
-    "ledger/submissions.jsonl": "33d632e4287a24b09eff3aac40157874c8547810b1203853ebc9c5d9e112c3aa",
-    "outcomes/submissions.jsonl": "4111dea6a0564f5ff0ed20fbfd4372c166de13ff036fc6fea184ed87d2c92f9c"
+    "ledger/submissions.jsonl": "0cba88a53dded12d730d5cab0e051b070df3f608dcdafd9b74983def6673d6a8",
+    "outcomes/submissions.jsonl": "c9f8d76f997ed97424b7384b41cefe4e1e0561b842c220f4c25ed72b76945284"
   },
-  "generation": 10810,
-  "phase": "intent",
+  "generation": 10811,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-20T18:54:42.831310+00:00",
+  "updatedAt": "2026-09-20T19:01:16.539302+00:00",
   "writerId": "fc715c06e24c4db2ae3e425e435db996"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index ed966c1fe..ffd5876dc 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -1070,3 +1070,13 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "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_tokenizer_patch", "lastTerminalAt": "2026-09-20T16:44:23.353846+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:39:41.567990+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985663", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:39:53.164098+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985692", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:47:15.075816+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985774", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786187, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786187}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:54:50.769551+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4985843", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:54:50.753303+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4985841", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261800, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261800}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:54:50.779862+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4985846", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858541078}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:54:50.771337+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985844", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385522016, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407346497, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407346497}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:54:50.781158+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985847", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093203965, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "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_tokenizer_patch", "lastTerminalAt": "2026-09-20T16:44:23.353846+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093203965}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:54:50.778321+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985848", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479058, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479058}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:54:50.767556+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985845", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449433, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449433}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:54:50.763750+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985842", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367987, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367987}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:56:13.145823+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4985871", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142065}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T18:57:33.406739+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4985872", "taskType": "text-generation", "verifyResult": null}