From f454ad46ab3d6ac9b3573fca81da76ce184a9182 Mon Sep 17 00:00:00 2001
From: CoolBoy <2269097679@qq.com>
Date: Mon, 21 Sep 2026 15:48:38 +0000
Subject: [PATCH] state: generation 11533 (result)

---
 .modelhub_state/recovery_intents.jsonl    | 177 ++++++++--------------
 .modelhub_state/routing_intelligence.json |  18 +--
 ledger/submissions.jsonl                  |   7 +-
 manifest.json                             |  14 +-
 outcomes/submissions.jsonl                |   6 +
 5 files changed, 89 insertions(+), 133 deletions(-)

diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index 4ee684b025..51bec0c395 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -2124,67 +2124,67 @@
 {"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786555+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162728+00:00", "framework": "vllm_fix_tokenizer", "intentId": "eb1b66ee51064deb862390688ac59e89", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "reason": null, "reconciledAt": "2026-09-21T15:33:58.190558+00:00", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5002498", "taskType": "text-generation"}
 {"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786557+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162773+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f1dbdb070df14d16917f1380db317b03", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "reason": null, "reconciledAt": "2026-09-21T15:33:58.187809+00:00", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5002503", "taskType": "text-generation"}
 {"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786560+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162816+00:00", "framework": "vllm_fix_tokenizer", "intentId": "98fb2208a84c47b6ad57ece75482b991", "lastModified": "2026-09-11T15:37:46+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "reason": null, "reconciledAt": "2026-09-21T15:33:58.187213+00:00", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5002497", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620034+00:00", "framework": "vllm_tokenizer_patch", "intentId": "80dac7b6f6cb49279fb29f8f6aa5175b", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620136+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2c9aa72d66194047bb8b750acc9149cb", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620177+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ec29c013ec984c0899f46860f3464d55", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620215+00:00", "framework": "vllm_tokenizer_patch", "intentId": "271938bfabb8471d961a4a08e5f8221a", "lastModified": "2026-08-24T19:06:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620269+00:00", "framework": "vllm", "intentId": "fdd867715aa842069ec7529029155e48", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620321+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fdf2eb2aa10540ae9a12c16cb68ac53b", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620364+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1f27373d603e4f91a3c1d4c8bf63b025", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620407+00:00", "framework": "vllm_fix_tokenizer", "intentId": "44943165eaca4387b18b8bf073f5ee6b", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620449+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f5cbd9985b794e77904fd1cb321859b6", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620492+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0ba165af4b794ddda3382fbb2dfcd603", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620534+00:00", "framework": "vllm_fix_tokenizer", "intentId": "167a9f31f1c3434b88ee9d6a2fb741be", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620576+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ce66ff013b784885a6d57f7a83a898ab", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620619+00:00", "framework": "vllm_fix_tokenizer", "intentId": "82c73b285a7d4dbcb074c4a658e4903d", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620661+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6bf33d93784240a2a1f049aadecf3340", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620721+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5753118d83274f9883043d8a85d69b99", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620763+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f4387aea625b4501b3e1b7345465b688", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620805+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d4bb21bf98c64e858748364e98c6a5ac", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620847+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0e21901591494784ae6952f23a32f0d5", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620890+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d966061690d41a6acc3ab12eb7b92e5", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620932+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4f46722d3a474592a75864eb0e8c4582", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620974+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9301f0e329a243cea0d071f432da52a4", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621016+00:00", "framework": "vllm_fix_tokenizer", "intentId": "441834c6c3e944359986d2d3fbf2d119", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621057+00:00", "framework": "vllm_fix_tokenizer", "intentId": "75fde94bc4fd474faf6cc2e7c64662fb", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621099+00:00", "framework": "vllm_fix_tokenizer", "intentId": "08e81d8b632448529211eab8c9bd9f99", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621153+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c53273d6b17e4fcfa3cddf38d5655fc2", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621195+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5b732bb1918d4ee7af3927f09a4c4646", "lastModified": "2026-09-09T06:50:48+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621236+00:00", "framework": "transformers", "intentId": "48fac18a8aad40ebbfe1ee68b52236b1", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621298+00:00", "framework": "transformers", "intentId": "807223c991824eb7adea5d12869836c5", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621359+00:00", "framework": "transformers", "intentId": "e9fa2ee13a4646a88763a844f4b382f3", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621420+00:00", "framework": "transformers", "intentId": "83efd8a8e57b4d7d96fce383d8244ef3", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621480+00:00", "framework": "transformers", "intentId": "2468c06ff25748b08dc6985d137964b4", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621540+00:00", "framework": "transformers", "intentId": "a22636f0e6674cd0a818553b99afcdce", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621601+00:00", "framework": "transformers", "intentId": "af14d99d1ec347249ad245e8c7a910cd", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621661+00:00", "framework": "transformers", "intentId": "dcb21651688e47758631feab62a60a3b", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621727+00:00", "framework": "transformers", "intentId": "ff39260d438a412f850cccea7da747b7", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621788+00:00", "framework": "transformers", "intentId": "52abb43a2af2448e9ef7d36b6829a7f4", "lastModified": "2026-08-24T19:08:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621848+00:00", "framework": "transformers", "intentId": "3aae176ebf6d4b72ae4790bac0cb9d78", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621908+00:00", "framework": "transformers", "intentId": "41d337ffcd304476ac433ae96b1cad84", "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, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621968+00:00", "framework": "transformers", "intentId": "fbb62e5459994b08bb11d28217a35474", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622028+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e89f78c62222493586781bf923c1211b", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622070+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f87c7e5aee084699baa8e7b74f729e97", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622112+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c595208a2913496489aa69817df77627", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622153+00:00", "framework": "vllm-patch-tokenizer", "intentId": "72654ae8412b471a8b0332b35ab9ef1b", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622194+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9a3870898cb148b1ac64e3881d8eebb9", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622235+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a9f2349ecc8d40d89934159bdf08b43e", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622277+00:00", "framework": "vllm-patch-tokenizer", "intentId": "921a89d747a94087b42ac54813b580a7", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622318+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4aa1e983598a4053beb6ff707822c4b8", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622359+00:00", "framework": "vllm-patch-tokenizer", "intentId": "89a4496d30cc4ae7a5002ee3042b3abf", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622400+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e572632720fb401eb78170067f2ca747", "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": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622441+00:00", "framework": "vllm-patch-tokenizer", "intentId": "af50985b6b2d4f1186f29413322a0bab", "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": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622483+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a81dbed676064007a165a7e2b37e6f99", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622525+00:00", "framework": "vllm-patch-tokenizer", "intentId": "dc54b6b793c341bd978cc7e4730052ec", "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": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622566+00:00", "framework": "vllm-patch-tokenizer", "intentId": "87cbc60a0ab64914aac6dc66612a3b7f", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622607+00:00", "framework": "vllm", "intentId": "4ddbe149a6ee4b21b73aed4dd7c1c935", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622656+00:00", "framework": "vllm", "intentId": "c65ea68579a5477688c85f03b600a578", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622707+00:00", "framework": "vllm", "intentId": "7dc43a4f5caf4d5aad9bdc11c00442cf", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622753+00:00", "framework": "vllm", "intentId": "70afa0149fd347a7b71275607e5d1aaf", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622799+00:00", "framework": "vllm", "intentId": "d38bdd7935b54cf192601455f05e1918", "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": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622846+00:00", "framework": "vllm", "intentId": "a5508ad2e66e442186d9134294f5983d", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622892+00:00", "framework": "vllm", "intentId": "8e9c55f82f9842d8a6ebc1526da993df", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622938+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6744cb33da7c4b53941d001c9f8f3ce5", "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": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969726+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620215+00:00", "framework": "vllm_tokenizer_patch", "intentId": "271938bfabb8471d961a4a08e5f8221a", "lastModified": "2026-08-24T19:06:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a8", "reason": null, "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5003018", "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969801+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621359+00:00", "framework": "transformers", "intentId": "e9fa2ee13a4646a88763a844f4b382f3", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5003113", "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969857+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622400+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e572632720fb401eb78170067f2ca747", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "reason": null, "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "5003178", "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969859+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622441+00:00", "framework": "vllm-patch-tokenizer", "intentId": "af50985b6b2d4f1186f29413322a0bab", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "5003181", "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969883+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622892+00:00", "framework": "vllm", "intentId": "8e9c55f82f9842d8a6ebc1526da993df", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003203", "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969886+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622938+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6744cb33da7c4b53941d001c9f8f3ce5", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "reason": null, "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5003204", "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969881+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622846+00:00", "framework": "vllm", "intentId": "a5508ad2e66e442186d9134294f5983d", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969878+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622799+00:00", "framework": "vllm", "intentId": "d38bdd7935b54cf192601455f05e1918", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969876+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622753+00:00", "framework": "vllm", "intentId": "70afa0149fd347a7b71275607e5d1aaf", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969874+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622707+00:00", "framework": "vllm", "intentId": "7dc43a4f5caf4d5aad9bdc11c00442cf", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969871+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622656+00:00", "framework": "vllm", "intentId": "c65ea68579a5477688c85f03b600a578", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969869+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622607+00:00", "framework": "vllm", "intentId": "4ddbe149a6ee4b21b73aed4dd7c1c935", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969866+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622566+00:00", "framework": "vllm-patch-tokenizer", "intentId": "87cbc60a0ab64914aac6dc66612a3b7f", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969864+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622525+00:00", "framework": "vllm-patch-tokenizer", "intentId": "dc54b6b793c341bd978cc7e4730052ec", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969861+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622483+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a81dbed676064007a165a7e2b37e6f99", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969854+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622359+00:00", "framework": "vllm-patch-tokenizer", "intentId": "89a4496d30cc4ae7a5002ee3042b3abf", "repoId": "RedHatAI/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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969851+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622318+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4aa1e983598a4053beb6ff707822c4b8", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969849+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622277+00:00", "framework": "vllm-patch-tokenizer", "intentId": "921a89d747a94087b42ac54813b580a7", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969847+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622235+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a9f2349ecc8d40d89934159bdf08b43e", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969844+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622194+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9a3870898cb148b1ac64e3881d8eebb9", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969841+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622153+00:00", "framework": "vllm-patch-tokenizer", "intentId": "72654ae8412b471a8b0332b35ab9ef1b", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969838+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622112+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c595208a2913496489aa69817df77627", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969835+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622070+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f87c7e5aee084699baa8e7b74f729e97", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969833+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622028+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e89f78c62222493586781bf923c1211b", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969830+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621968+00:00", "framework": "transformers", "intentId": "fbb62e5459994b08bb11d28217a35474", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969828+00:00", "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621908+00:00", "framework": "transformers", "intentId": "41d337ffcd304476ac433ae96b1cad84", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969825+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621848+00:00", "framework": "transformers", "intentId": "3aae176ebf6d4b72ae4790bac0cb9d78", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969823+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621788+00:00", "framework": "transformers", "intentId": "52abb43a2af2448e9ef7d36b6829a7f4", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969821+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621727+00:00", "framework": "transformers", "intentId": "ff39260d438a412f850cccea7da747b7", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969818+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621661+00:00", "framework": "transformers", "intentId": "dcb21651688e47758631feab62a60a3b", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969815+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621601+00:00", "framework": "transformers", "intentId": "af14d99d1ec347249ad245e8c7a910cd", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969811+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621540+00:00", "framework": "transformers", "intentId": "a22636f0e6674cd0a818553b99afcdce", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969808+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621480+00:00", "framework": "transformers", "intentId": "2468c06ff25748b08dc6985d137964b4", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969804+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621420+00:00", "framework": "transformers", "intentId": "83efd8a8e57b4d7d96fce383d8244ef3", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969798+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621298+00:00", "framework": "transformers", "intentId": "807223c991824eb7adea5d12869836c5", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969794+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621236+00:00", "framework": "transformers", "intentId": "48fac18a8aad40ebbfe1ee68b52236b1", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969790+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621195+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5b732bb1918d4ee7af3927f09a4c4646", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969787+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621153+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c53273d6b17e4fcfa3cddf38d5655fc2", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969783+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621099+00:00", "framework": "vllm_fix_tokenizer", "intentId": "08e81d8b632448529211eab8c9bd9f99", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969780+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621057+00:00", "framework": "vllm_fix_tokenizer", "intentId": "75fde94bc4fd474faf6cc2e7c64662fb", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969777+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621016+00:00", "framework": "vllm_fix_tokenizer", "intentId": "441834c6c3e944359986d2d3fbf2d119", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969773+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620974+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9301f0e329a243cea0d071f432da52a4", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969770+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620932+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4f46722d3a474592a75864eb0e8c4582", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969766+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620890+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d966061690d41a6acc3ab12eb7b92e5", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969763+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620847+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0e21901591494784ae6952f23a32f0d5", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969760+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620805+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d4bb21bf98c64e858748364e98c6a5ac", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969757+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620763+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f4387aea625b4501b3e1b7345465b688", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969755+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620721+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5753118d83274f9883043d8a85d69b99", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969752+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620661+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6bf33d93784240a2a1f049aadecf3340", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969749+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620619+00:00", "framework": "vllm_fix_tokenizer", "intentId": "82c73b285a7d4dbcb074c4a658e4903d", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969747+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620576+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ce66ff013b784885a6d57f7a83a898ab", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969744+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620534+00:00", "framework": "vllm_fix_tokenizer", "intentId": "167a9f31f1c3434b88ee9d6a2fb741be", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969742+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620492+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0ba165af4b794ddda3382fbb2dfcd603", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969740+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620449+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f5cbd9985b794e77904fd1cb321859b6", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969737+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620407+00:00", "framework": "vllm_fix_tokenizer", "intentId": "44943165eaca4387b18b8bf073f5ee6b", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969735+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620364+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1f27373d603e4f91a3c1d4c8bf63b025", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969732+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620321+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fdf2eb2aa10540ae9a12c16cb68ac53b", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969729+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620269+00:00", "framework": "vllm", "intentId": "fdd867715aa842069ec7529029155e48", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969723+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620177+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ec29c013ec984c0899f46860f3464d55", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969719+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620136+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2c9aa72d66194047bb8b750acc9149cb", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
+{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969705+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620034+00:00", "framework": "vllm_tokenizer_patch", "intentId": "80dac7b6f6cb49279fb29f8f6aa5175b", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
 {"batchId": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560500+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651513+00:00", "framework": "vllm", "intentId": "6de6e0ac88b545bf9483d93dbed8b284", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560497+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651456+00:00", "framework": "vllm", "intentId": "805ac1abf9784788b971d3510068a82c", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
 {"batchId": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560494+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651398+00:00", "framework": "vllm", "intentId": "fdaf04ba752c4067b0e318b0f05a99aa", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
@@ -2430,58 +2430,3 @@
 {"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199922+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158495+00:00", "framework": "vllm_fix_tokenizer", "intentId": "03658bf19deb4a31b699d5b9541192cc", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
 {"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199919+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158452+00:00", "framework": "vllm_fix_tokenizer", "intentId": "16adba7d2c6e4c269d9198b21f90105a", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
 {"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199916+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158410+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e564d14c7a2943a8a9e625609076cb5c", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199914+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158367+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b97281c63aee44f98804c9542140a308", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199911+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158323+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6025fa59bd804673906a98eb16dbe27e", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199908+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158281+00:00", "framework": "vllm_fix_tokenizer", "intentId": "732fd6a602204cd58b3bceaa01039cda", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199905+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158238+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7da49ec7c9b34cb8a5d1686be1a471fd", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199902+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158195+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5658554409e74cad809e1a1f21dc5620", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199899+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158153+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0a92f6f7544a490ca0f183908b6d8991", "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": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199896+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158109+00:00", "framework": "vllm_fix_tokenizer", "intentId": "15611b9822cc488985800b95e73d39ed", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199893+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158065+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5c065cf7488f457ca81ed174048c232c", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199889+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.158021+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2d17e2bc3a924e7a9d2114e1bd176f50", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199886+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.157976+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a224b24bd915483b94048326ff1f6c9f", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
-{"batchId": "649b0fdc0f8f466abe2e903dc3f4c10c", "completedAt": "2026-09-21T13:51:38.199868+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:43:21.157810+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d921da2c7ef140b78a9902bd38739a5a", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177559+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.727015+00:00", "framework": "vllm", "intentId": "6f21e83b92bf4d7e9e7143c7f7a2aac7", "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": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177555+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726957+00:00", "framework": "vllm", "intentId": "fe76a54c207f49919516cd4578315996", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177551+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726898+00:00", "framework": "vllm", "intentId": "01c450d8c4114309a29b0366ac38790b", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177547+00:00", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726846+00:00", "framework": "vllm-customized", "intentId": "9f955bfd6884427f97b480c02d518d8e", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177543+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726794+00:00", "framework": "vllm-customized", "intentId": "cc3830d504d941f4998756781f4003e8", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177538+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726741+00:00", "framework": "vllm-customized", "intentId": "182d56896b244001b663ff31b74a5a54", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177534+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726687+00:00", "framework": "vllm-customized", "intentId": "ab0bc978dfa4421390bf5c01f60303de", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177531+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726629+00:00", "framework": "vllm-customized", "intentId": "800177b6528e4634b674aae6debae830", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177527+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726575+00:00", "framework": "vllm-customized", "intentId": "5f7497c9a1ff49d295536861d7c28753", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177524+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726515+00:00", "framework": "vllm-customized", "intentId": "293f6df5e3e94f2e869adad476231aad", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177520+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726458+00:00", "framework": "vllm-customized", "intentId": "3ac36fc7dd104ada8643cc0910183227", "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": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177516+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726400+00:00", "framework": "vllm-customized", "intentId": "63fb0dba9e2643c4a40f7d861e98eb5a", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177512+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726342+00:00", "framework": "vllm-customized", "intentId": "500ab1c6947146df8e7ede1de913ce81", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177508+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726284+00:00", "framework": "vllm-customized", "intentId": "afe6673aa7a24c0297cf40a5d4c1bbbc", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177505+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726226+00:00", "framework": "vllm-customized", "intentId": "368b7fe2cce04a79acdb14bd17baf20a", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177501+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726168+00:00", "framework": "vllm-customized", "intentId": "51154ebdec2a43c99ac582c4900e1acd", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177498+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726110+00:00", "framework": "vllm-customized", "intentId": "ef239590c7194aa4af180f6afec09d06", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177495+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.726052+00:00", "framework": "vllm-customized", "intentId": "c1e038e6c2e54dbc9dce7c449363d183", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177491+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725993+00:00", "framework": "vllm-customized", "intentId": "24ca4345558045bcb6d727ced5d989e0", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177487+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725932+00:00", "framework": "vllm-customized", "intentId": "42c036d3b70046789994e15a2ce7692c", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177482+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725869+00:00", "framework": "vllm-customized", "intentId": "348bf24ea77e4a52a81d7961d4cd82c4", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177478+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725829+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0605b79649a743358fe1b45e80071f03", "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": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177475+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725788+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c6cbdc68d2584e93b4e4ba2f4666badb", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177472+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725748+00:00", "framework": "vllm_tokenizer_patch", "intentId": "41a4c69856784926a75837909793ed3b", "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": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177468+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725707+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8f708ba078c74b7bba63cd4adbf6574a", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177464+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725648+00:00", "framework": "vllm_tokenizer_patch", "intentId": "60dbe4db0dc54b9d8dbf76584d66ad20", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177460+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725605+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ad01585e18f483da5fa96e560f16e90", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177456+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725557+00:00", "framework": "vllm", "intentId": "3db6af9908af4578b3010976e31a909b", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177452+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725509+00:00", "framework": "vllm", "intentId": "54641ec54cbd4b1694505da22d611274", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177448+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725459+00:00", "framework": "vllm", "intentId": "e320918a254f47c8a3e4d09289756380", "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": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177442+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725406+00:00", "framework": "vllm", "intentId": "3badfbd00f5c4d608d926beba44d84e4", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "f00b6b01777c4e4d8fa15a8de07f4c45", "completedAt": "2026-09-21T13:28:48.177420+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:24:27.725274+00:00", "framework": "vllm", "intentId": "a3bbd6ce08294d2aaf97b92d4867b191", "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": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683937+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710404+00:00", "framework": "vllm", "intentId": "4069d3dd01054f50a9f12d60f4aa12ed", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
-{"batchId": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683935+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710362+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4eb8010160b54561b7bce7b51c780c37", "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": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683932+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710321+00:00", "framework": "vllm-patch-tokenizer", "intentId": "6d869be1dff542f9915c4203a6152995", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
-{"batchId": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683930+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710279+00:00", "framework": "vllm-patch-tokenizer", "intentId": "af092f1f317c4ea4ae30ba532b0af933", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
-{"batchId": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683927+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710237+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c0b51462d0e743bcaa7aac66007f5938", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
-{"batchId": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683925+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710194+00:00", "framework": "vllm-patch-tokenizer", "intentId": "8670933ddf934a358f2c3573f9d15e6a", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
-{"batchId": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683922+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710153+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b2774dc169e540a4bcc66c8974113403", "repoId": "RedHatAI/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": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683919+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710111+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e662eb7139894bacb1ccec0e60599c6c", "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": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683917+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710069+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ad1617df90d94c209659026745ec5a57", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
-{"batchId": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683914+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.710027+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c1402ce0748741f29c02321a55ff6747", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
-{"batchId": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683911+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.709985+00:00", "framework": "vllm-patch-tokenizer", "intentId": "11c5eed8819640edb6ee4352b2aa790f", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
-{"batchId": "b2142cbcc51a45d6b9ec9a082a1909fa", "completedAt": "2026-09-21T13:24:26.683908+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:17:26.709943+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c3fb070808d84c848850bc13a221c0c0", "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"}
diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json
index bda87f0ef6..641a22a1f5 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,6 +1,6 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 2263
+    "unified_success_first": 2269
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 17,
@@ -11,7 +11,7 @@
     "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 141,
     "text-generation|Biren_166m|vllm": 81,
     "text-generation|Biren_166m|vllm_fix_tokenizer": 128,
-    "text-generation|Cambricon_mlu-370-x4|vllm": 70,
+    "text-generation|Cambricon_mlu-370-x4|vllm": 71,
     "text-generation|Cambricon_mlu-370-x4|vllm-customized": 5,
     "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 87,
     "text-generation|Cambricon_mlu-370-x8|vllm": 55,
@@ -19,15 +19,15 @@
     "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 97,
     "text-generation|Iluvatar_bi-100|transformers": 20,
     "text-generation|Iluvatar_bi-150|llamacpp": 16,
-    "text-generation|Iluvatar_bi-150|transformers": 35,
+    "text-generation|Iluvatar_bi-150|transformers": 36,
     "text-generation|Iluvatar_bi-150|vllm": 9,
     "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 102,
     "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 44,
-    "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 9,
+    "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 10,
     "text-generation|Iluvatar_mrv-100|vllm": 62,
     "text-generation|Kunlunxin_p-800|vllm": 59,
     "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 183,
-    "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 86,
+    "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 87,
     "text-generation|MetaX_c-500|vllm": 104,
     "text-generation|Mthreads_s4000|llamacpp": 17,
     "text-generation|Mthreads_s4000|vllm": 103,
@@ -36,10 +36,10 @@
     "text-generation|Vastai_va16|vllm_fix_tokenizer": 75,
     "text-generation|hygon_k100-ai|llamacpp": 18,
     "text-generation|hygon_k100-ai|vllm": 26,
-    "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 129
+    "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 131
   },
-  "acceptedSinceRefresh": 2263,
-  "acceptedTotal": 2263,
-  "generatedAt": "2026-09-21T14:59:12.494460+00:00",
+  "acceptedSinceRefresh": 2269,
+  "acceptedTotal": 2269,
+  "generatedAt": "2026-09-21T15:48:37.864362+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index d653da03f2..4ce25da3fe 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -1012,7 +1012,6 @@
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "submitTime": "2026-09-21T14:48:11.800344+00:00", "targetGpu": "Biren_166m", "taskId": "5002498", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-21T14:48:11.805114+00:00", "targetGpu": "Biren_166m", "taskId": "5002503", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-21T14:48:11.795290+00:00", "targetGpu": "Biren_166m", "taskId": "5002497", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
-{"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_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_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T19:48:14.574218+00:00", "targetGpu": "Biren_166m", "taskId": "4986610", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.639695+00:00", "targetGpu": "Biren_166m", "taskId": "4986615", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
@@ -1214,3 +1213,9 @@
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "submitTime": "2026-09-21T14:17:59.387901+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002151", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
 {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-21T14:20:21.627234+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002168", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "submitTime": "2026-09-21T14:22:53.836064+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002202", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a8", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "submitTime": "2026-09-21T15:37:01.383959+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5003018", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-21T15:40:17.175718+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003113", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "modelId": "RedHatAI/starcoder2-7b-FP8", "submitTime": "2026-09-21T15:43:55.761793+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003178", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "submitTime": "2026-09-21T15:44:10.499526+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003181", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "modelId": "aisingapore/SEA-LION-v1-7B", "submitTime": "2026-09-21T15:46:08.955762+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003203", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-21T15:46:22.786539+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003204", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"}
diff --git a/manifest.json b/manifest.json
index 44c2644d18..748577cedf 100644
--- a/manifest.json
+++ b/manifest.json
@@ -10,16 +10,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "0ad8bae3fa1afa7ca210869b402afc058a903fdc4e2d86ace5dcbd51a06fabd1",
     ".modelhub_state/recent_outcomes.jsonl": "2a173ac6b4f5af299e47a033c354044636957b901c2fb942e1eb8e6f825a7003",
     ".modelhub_state/recovery_active_tasks.jsonl": "176667ceefd8bd84b11705f4d6246e59ecded9d6c3bce4aaeef6aaccfa9e44ae",
-    ".modelhub_state/recovery_intents.jsonl": "5e73a218ad3081e81df179e52e3029cba914dcc8a042b859228425007b2fb175",
-    ".modelhub_state/routing_intelligence.json": "401420e4c946e0b966737f95e5e50eebfcf2cedd81edbf210c3ff687244d372b",
+    ".modelhub_state/recovery_intents.jsonl": "4c1c0a9cb122ec6fb68ec93d959972fb2df93432799818b06b37721beae6c908",
+    ".modelhub_state/routing_intelligence.json": "91cb0720fae195f55872b65dbb1aafaa10b68aa3d3d77a158a8d8ff11f8b28bd",
     ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
     ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
-    "ledger/submissions.jsonl": "6c74b656702bbb1842ad0c41fb62716c4b043392e9d8f8516ed6cd706093d07e",
-    "outcomes/submissions.jsonl": "1b4934503e7c1c3826870af1bfbc7614740c6beb773c731edb2ab5c0b1e88d39"
+    "ledger/submissions.jsonl": "41b954697772199040f23538b8886342b99c6f2702699ff95c2c7386dda0cdf2",
+    "outcomes/submissions.jsonl": "cd807f5d3f8d94f98f8200f7405650bbcc83550c2dd3745142a73157dee06800"
   },
-  "generation": 11532,
-  "phase": "intent",
+  "generation": 11533,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-21T15:36:50.816382+00:00",
+  "updatedAt": "2026-09-21T15:48:38.111645+00:00",
   "writerId": "8b35139af6674067a339a670222d4b67"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index ab0c9cac67..920f692ebf 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -1141,3 +1141,9 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663548868}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:48:11.800344+00:00", "targetGpu": "Biren_166m", "taskId": "5002498", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:48:11.805114+00:00", "targetGpu": "Biren_166m", "taskId": "5002503", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:48:11.795290+00:00", "targetGpu": "Biren_166m", "taskId": "5002497", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385522016, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407346443, "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": 4407346443}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T15:37:01.383959+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5003018", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "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": 6768615496}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T15:40:17.175718+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003113", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": 7858540940, "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": 7858540940}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T15:43:55.761793+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003178", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T15:44:10.499526+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003181", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T15:46:08.955762+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003203", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T15:46:22.786539+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003204", "taskType": "text-generation", "verifyResult": null}