From 12911595ba4b1a3a817901c456d4df76c7dd5252 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 01:01:39 +0000 Subject: [PATCH] state: generation 11047 (result) --- .modelhub_state/recovery_intents.jsonl | 176 ++++++++-------------- .modelhub_state/routing_intelligence.json | 10 +- ledger/submissions.jsonl | 1 + manifest.json | 14 +- outcomes/submissions.jsonl | 1 + 5 files changed, 73 insertions(+), 129 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index f6612c2fc3..714d3e7997 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1881,65 +1881,65 @@ {"batchId": "b8238a2b8f5743219f8e203945e8940c", "completedAt": "2026-09-21T00:36:41.972169+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:28:56.157937+00:00", "framework": "vllm_fix_tokenizer", "intentId": "497f736703aa429c90bc7ba192de67f0", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "reason": null, "reconciledAt": "2026-09-21T00:49:09.235473+00:00", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4990404", "taskType": "text-generation"} {"batchId": "801c58a410704e9f9dd21ff480faeae0", "completedAt": "2026-09-21T00:40:32.435004+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:36:42.801279+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fd92d1143c9c435cb04e1bd29d07c1cb", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T00:49:09.235777+00:00", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4990464", "taskType": "text-generation"} {"batchId": "bfa8ed2fa7ec4618ab6db0c51699fd3e", "completedAt": "2026-09-21T00:41:04.872858+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:40:56.683923+00:00", "framework": "vllm-customized", "intentId": "eaae0dbf87bd408297fdfa4ceb9d0b6a", "lastModified": "2026-09-20T14:38:08+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "reason": null, "reconciledAt": "2026-09-21T00:49:09.234030+00:00", "repoId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990527", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609391+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d30000d53ec74cb19da4c8d8750bcaff", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609510+00:00", "framework": "vllm_tokenizer_patch", "intentId": "927449254c224cc1b7f6b19c1bac3304", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609565+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8fcfc7642fd64be590baf588588caa65", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609615+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c3b3b81c8d5448d3acef1fd6288b6db9", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609677+00:00", "framework": "vllm-mlu", "intentId": "96fe23ff5b9b4c178da32cd301166147", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609736+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc3e95a3696c41ce97fe74ce8121f599", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609781+00:00", "framework": "vllm-mlu", "intentId": "e61b5eb79d79449b94b1c7e6b6df13ee", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609845+00:00", "framework": "vllm-mlu", "intentId": "24534aed8bbc4b3c91e183d20f34065a", "lastModified": "2026-08-24T19:36:40+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609909+00:00", "framework": "vllm-mlu", "intentId": "66ff4fcc6a114bab9c2fdd60d15a0fcf", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609972+00:00", "framework": "vllm", "intentId": "32aa28686e0d4eb3872cc917809d9565", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610031+00:00", "framework": "vllm", "intentId": "d0960baac006415699a77dc8359f8f06", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610090+00:00", "framework": "vllm", "intentId": "65d204d75aff43a09b30dd9c354cbc63", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610148+00:00", "framework": "vllm", "intentId": "06c7a55c037e42fb9f8391b0466735fc", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610206+00:00", "framework": "vllm", "intentId": "0e492acf37314da6930321e8beb7348c", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610264+00:00", "framework": "vllm", "intentId": "3ecffef6e50040d5a4b54d2d69e98b95", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610321+00:00", "framework": "vllm", "intentId": "d61bf9944a40478a967b78ec1f6ee545", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610378+00:00", "framework": "vllm", "intentId": "24316c82af784d50b8b69a639cc88290", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610436+00:00", "framework": "vllm", "intentId": "2d43c1d1608a496593a00177fe7bf3f9", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610493+00:00", "framework": "vllm", "intentId": "c3ce3b5873264e0ea125b05f1a396b91", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610549+00:00", "framework": "vllm", "intentId": "d86ae26aed124f53b3027e16e6d4d91b", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610606+00:00", "framework": "vllm", "intentId": "a65dbfab5a34480abd3ee77b04945b82", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610663+00:00", "framework": "vllm", "intentId": "213bb8e750224d4baa7a21b9a4237c75", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610725+00:00", "framework": "vllm", "intentId": "acc7ef6f54584bb2aa40b0204b0b7b23", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610782+00:00", "framework": "vllm_fix_tokenizer", "intentId": "57f864280af7498f9e305ff4a97f5c7d", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610825+00:00", "framework": "vllm_fix_tokenizer", "intentId": "941f031ead7440678f69d87e0245e391", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610869+00:00", "framework": "vllm_fix_tokenizer", "intentId": "371881195b824b3a885203e67bc76e5c", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610912+00:00", "framework": "vllm_fix_tokenizer", "intentId": "452ea70c90e64e6390c52e4db1320648", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610955+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d998a9cb39b74bca9064e9bcb4a4c800", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610998+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bd87d9cd00a24b31b9871247c0c7f51b", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611040+00:00", "framework": "vllm_fix_tokenizer", "intentId": "54898f10475b4a4a9cfc9ba82e900036", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611083+00:00", "framework": "vllm_fix_tokenizer", "intentId": "43cd02ab0b924091ba375d1ebfa578d4", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611125+00:00", "framework": "vllm_fix_tokenizer", "intentId": "96521a9b32384ee68945a2c588ef9630", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611167+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e727af0129214c5bb483f305f03e686f", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611210+00:00", "framework": "vllm_fix_tokenizer", "intentId": "47ef99be1f174e65a68434f30721bcc8", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611253+00:00", "framework": "vllm_fix_tokenizer", "intentId": "57ef95822bc8470b96c5ce750e90096f", "lastModified": "2026-08-31T14:36:00+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611295+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e56f454ee1044853846ae7124ea8d968", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611337+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d82eddc50ee4c60ba7d938822d285f7", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611379+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ba643f561cf14972bbaf78934d613977", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611422+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d87643d22dad4126beb1a2deea8dcf85", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611465+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5a3932d228524568a88533fb5a05b374", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611507+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8e80100b911445ce89123d88fc2d353a", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611550+00:00", "framework": "vllm_fix_tokenizer", "intentId": "63ba816667a045c199c6ed72de7e680a", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611593+00:00", "framework": "vllm_fix_tokenizer", "intentId": "212dc6c47b0f42b28f6f2cc8801a329f", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611635+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d9d509a10ec04566941e477c13311130", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611683+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8cc64dec505348fabe2824f7bfd8ce1f", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611725+00:00", "framework": "vllm_fix_tokenizer", "intentId": "52a42ec99c524631a32102ba02d87401", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611767+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d5c808a0267c489f97a47523a0915c5f", "lastModified": "2026-08-26T13:13:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611810+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4a61bc88b0ff4829ab5c14014296a0a3", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611852+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e19296ea36d345369f2416eebdd331cf", "lastModified": "2026-09-03T06:52:45+00:00", "modelAddress": "https://modelscope.cn/models/bharatgenai/Param2-17B-A2.4B-Thinking", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611894+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3cb38d0f6cbe4807a3855218f4affe9e", "lastModified": "2026-08-28T09:38:42+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611937+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e0992d40028746d185caa00cff4607c4", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611979+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e46f41ce52f4eb7b3a9859c4f1cfa20", "lastModified": "2026-09-08T15:40:32+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612021+00:00", "framework": "vllm_fix_tokenizer", "intentId": "62d01964bf8940d8b08565226ff13f27", "lastModified": "2026-08-26T20:08:51+00:00", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612064+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7cdbf192ded34e4e85f217e16a1daecf", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612106+00:00", "framework": "vllm_fix_tokenizer", "intentId": "af60bd53ca0f4b41bbe7d8aa784cd481", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612149+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bcc10ffc64644a38806a005e3a853430", "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": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612191+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d106f8b74e564f9fbffd00c9a3ecd184", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612233+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2677341cf6f47ce84a2a35b4347277c", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612276+00:00", "framework": "vllm_fix_tokenizer", "intentId": "def5db3202ef4372a86887c491aa4ebe", "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": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006186+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609781+00:00", "framework": "vllm-mlu", "intentId": "e61b5eb79d79449b94b1c7e6b6df13ee", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006332+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612276+00:00", "framework": "vllm_fix_tokenizer", "intentId": "def5db3202ef4372a86887c491aa4ebe", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006329+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612233+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2677341cf6f47ce84a2a35b4347277c", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006326+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612191+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d106f8b74e564f9fbffd00c9a3ecd184", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006323+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612149+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bcc10ffc64644a38806a005e3a853430", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006321+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612106+00:00", "framework": "vllm_fix_tokenizer", "intentId": "af60bd53ca0f4b41bbe7d8aa784cd481", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006318+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612064+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7cdbf192ded34e4e85f217e16a1daecf", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006315+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.612021+00:00", "framework": "vllm_fix_tokenizer", "intentId": "62d01964bf8940d8b08565226ff13f27", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006312+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611979+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e46f41ce52f4eb7b3a9859c4f1cfa20", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006309+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611937+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e0992d40028746d185caa00cff4607c4", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006307+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611894+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3cb38d0f6cbe4807a3855218f4affe9e", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006304+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611852+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e19296ea36d345369f2416eebdd331cf", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006301+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611810+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4a61bc88b0ff4829ab5c14014296a0a3", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006298+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611767+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d5c808a0267c489f97a47523a0915c5f", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006295+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611725+00:00", "framework": "vllm_fix_tokenizer", "intentId": "52a42ec99c524631a32102ba02d87401", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006293+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611683+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8cc64dec505348fabe2824f7bfd8ce1f", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006290+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611635+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d9d509a10ec04566941e477c13311130", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006287+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611593+00:00", "framework": "vllm_fix_tokenizer", "intentId": "212dc6c47b0f42b28f6f2cc8801a329f", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006284+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611550+00:00", "framework": "vllm_fix_tokenizer", "intentId": "63ba816667a045c199c6ed72de7e680a", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006281+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611507+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8e80100b911445ce89123d88fc2d353a", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006279+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611465+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5a3932d228524568a88533fb5a05b374", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006276+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611422+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d87643d22dad4126beb1a2deea8dcf85", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006273+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611379+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ba643f561cf14972bbaf78934d613977", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006270+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611337+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d82eddc50ee4c60ba7d938822d285f7", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006268+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611295+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e56f454ee1044853846ae7124ea8d968", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006265+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611253+00:00", "framework": "vllm_fix_tokenizer", "intentId": "57ef95822bc8470b96c5ce750e90096f", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006262+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611210+00:00", "framework": "vllm_fix_tokenizer", "intentId": "47ef99be1f174e65a68434f30721bcc8", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006259+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611167+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e727af0129214c5bb483f305f03e686f", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006256+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611125+00:00", "framework": "vllm_fix_tokenizer", "intentId": "96521a9b32384ee68945a2c588ef9630", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006253+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611083+00:00", "framework": "vllm_fix_tokenizer", "intentId": "43cd02ab0b924091ba375d1ebfa578d4", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006251+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.611040+00:00", "framework": "vllm_fix_tokenizer", "intentId": "54898f10475b4a4a9cfc9ba82e900036", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006248+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610998+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bd87d9cd00a24b31b9871247c0c7f51b", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006245+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610955+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d998a9cb39b74bca9064e9bcb4a4c800", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006242+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610912+00:00", "framework": "vllm_fix_tokenizer", "intentId": "452ea70c90e64e6390c52e4db1320648", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006239+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610869+00:00", "framework": "vllm_fix_tokenizer", "intentId": "371881195b824b3a885203e67bc76e5c", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006237+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610825+00:00", "framework": "vllm_fix_tokenizer", "intentId": "941f031ead7440678f69d87e0245e391", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006234+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610782+00:00", "framework": "vllm_fix_tokenizer", "intentId": "57f864280af7498f9e305ff4a97f5c7d", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006231+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610725+00:00", "framework": "vllm", "intentId": "acc7ef6f54584bb2aa40b0204b0b7b23", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006228+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610663+00:00", "framework": "vllm", "intentId": "213bb8e750224d4baa7a21b9a4237c75", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006225+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610606+00:00", "framework": "vllm", "intentId": "a65dbfab5a34480abd3ee77b04945b82", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006223+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610549+00:00", "framework": "vllm", "intentId": "d86ae26aed124f53b3027e16e6d4d91b", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006220+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610493+00:00", "framework": "vllm", "intentId": "c3ce3b5873264e0ea125b05f1a396b91", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006217+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610436+00:00", "framework": "vllm", "intentId": "2d43c1d1608a496593a00177fe7bf3f9", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006214+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610378+00:00", "framework": "vllm", "intentId": "24316c82af784d50b8b69a639cc88290", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006212+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610321+00:00", "framework": "vllm", "intentId": "d61bf9944a40478a967b78ec1f6ee545", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006209+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610264+00:00", "framework": "vllm", "intentId": "3ecffef6e50040d5a4b54d2d69e98b95", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006207+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610206+00:00", "framework": "vllm", "intentId": "0e492acf37314da6930321e8beb7348c", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006204+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610148+00:00", "framework": "vllm", "intentId": "06c7a55c037e42fb9f8391b0466735fc", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006200+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610090+00:00", "framework": "vllm", "intentId": "65d204d75aff43a09b30dd9c354cbc63", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006198+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.610031+00:00", "framework": "vllm", "intentId": "d0960baac006415699a77dc8359f8f06", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006195+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609972+00:00", "framework": "vllm", "intentId": "32aa28686e0d4eb3872cc917809d9565", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006192+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609909+00:00", "framework": "vllm-mlu", "intentId": "66ff4fcc6a114bab9c2fdd60d15a0fcf", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006189+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609845+00:00", "framework": "vllm-mlu", "intentId": "24534aed8bbc4b3c91e183d20f34065a", "repoId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006183+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609736+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc3e95a3696c41ce97fe74ce8121f599", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006180+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609677+00:00", "framework": "vllm-mlu", "intentId": "96fe23ff5b9b4c178da32cd301166147", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006177+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609615+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c3b3b81c8d5448d3acef1fd6288b6db9", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006173+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609565+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8fcfc7642fd64be590baf588588caa65", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006169+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609510+00:00", "framework": "vllm_tokenizer_patch", "intentId": "927449254c224cc1b7f6b19c1bac3304", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006149+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609391+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d30000d53ec74cb19da4c8d8750bcaff", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "801c58a410704e9f9dd21ff480faeae0", "completedAt": "2026-09-21T00:40:32.435081+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:36:42.802503+00:00", "framework": "vllm_fix_tokenizer", "intentId": "634b5203572b489fa0bcf351f75f776b", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "801c58a410704e9f9dd21ff480faeae0", "completedAt": "2026-09-21T00:40:32.435078+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:36:42.802447+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cdfa76f48eff42948fb51bb28c336acf", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "801c58a410704e9f9dd21ff480faeae0", "completedAt": "2026-09-21T00:40:32.435075+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:36:42.802393+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b9f8c69eab0f405da9a06cbd7368bc37", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} @@ -2182,61 +2182,3 @@ {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409639+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294963+00:00", "framework": "vllm_fix_tokenizer", "intentId": "98674de3a84e4875bbcee75cb814f924", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409636+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294920+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d91e6a316a84fa39de96952d299222a", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409633+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294856+00:00", "framework": "vllm", "intentId": "34bfcce23a9a434e89b878e07ef02c8b", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409630+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294799+00:00", "framework": "vllm", "intentId": "832cd72d07624c4a951b2bf96a702d77", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409627+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294742+00:00", "framework": "vllm", "intentId": "d03c5ebcc6ba4faba602b61e2389698c", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409620+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294621+00:00", "framework": "vllm", "intentId": "9640d0ea4b28474fba9a46c1c4ead978", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409617+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294556+00:00", "framework": "vllm", "intentId": "be89658e3e3a469f8e08ef8dd7dbf2a1", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409614+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294499+00:00", "framework": "vllm", "intentId": "73fe840d5aed420f8f367913b98be1e4", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409611+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294441+00:00", "framework": "vllm", "intentId": "673b972157504ac8a2b8d3912392e41b", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409608+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294384+00:00", "framework": "vllm", "intentId": "d82ba6abfa1d4d46becebfc0d4c64ee8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409605+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294325+00:00", "framework": "vllm", "intentId": "1a8b50128aac4685879530f3c1b7f87a", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409601+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294266+00:00", "framework": "vllm", "intentId": "c585753ca22d4de0aa7506f5b8368380", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409592+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294155+00:00", "framework": "vllm_fix_tokenizer", "intentId": "383d6398a9c241b89a5fc07dbce3275b", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409564+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294034+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cccd1c22862d4c338cdc7697b93410bf", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778811+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625471+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b8196779bbc54c5bbb81b09c273ee2d8", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778808+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c7c0d6c8881547889f550e1bdcd822a1", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778806+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625361+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ef8a7a87f66242bb985c1b1f6ed9a9d2", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778803+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625305+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2797c85e91ff4b13bb7dc726563a5115", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778800+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625250+00:00", "framework": "vllm_fix_tokenizer", "intentId": "30d8d4982aa24960ab337864e425d824", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778797+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625194+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0809f2b5a8074fa5876027a33910b8b3", "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778794+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625136+00:00", "framework": "vllm", "intentId": "85e9c42f23e14dfa93d68c6356b627bb", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778791+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625076+00:00", "framework": "vllm", "intentId": "56fbcbc03687488fbb32babb0ba1f5ec", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778789+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625034+00:00", "framework": "vllm", "intentId": "edd936c2c84648d8b4586ecfb8a900a7", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778786+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624990+00:00", "framework": "vllm", "intentId": "8e45816d10c44fe38fcdfeea3d259c9c", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778784+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624920+00:00", "framework": "vllm", "intentId": "2d7caed9b4eb4c8c8d7f4455c478b50d", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778781+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624866+00:00", "framework": "vllm", "intentId": "2ef41281b8a24c8d8ff2c774a564578a", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778778+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624824+00:00", "framework": "vllm", "intentId": "2ac59f55783a4627a61183fdbea0e35b", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778775+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624782+00:00", "framework": "vllm", "intentId": "88baef27f6ed4ea5836bc57594b5e6a6", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778773+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624738+00:00", "framework": "vllm", "intentId": "07e06feecd2c414bab2c35e63ea74a55", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778770+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624650+00:00", "framework": "vllm", "intentId": "0ab3348b7e354017a2cf4ed869225134", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778768+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624605+00:00", "framework": "vllm", "intentId": "593eecd217e7474b8054720adeba0b14", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778766+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624545+00:00", "framework": "vllm-customized", "intentId": "be65d544780a4bf8a9d0ed2ffcfcd5a4", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778763+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624472+00:00", "framework": "vllm-customized", "intentId": "533148a2489d43cea04c020be7bd026d", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778760+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624413+00:00", "framework": "vllm-customized", "intentId": "7abadaab11334f6aa7b36d2c81b4d262", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778758+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624353+00:00", "framework": "vllm-customized", "intentId": "771519de908a440f80e279a83a868d3d", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778755+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624292+00:00", "framework": "vllm-customized", "intentId": "a0fe49579e364b28926cae2eb4b45d97", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778752+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624198+00:00", "framework": "vllm-customized", "intentId": "7168a023fe7d45b49ca8a742a7eb8c95", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778749+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "972de5bac2974baca2f730e452e81a57", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778746+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624116+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8a8c8437f33f4e0787bbe8ea293197e7", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778743+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624074+00:00", "framework": "vllm_tokenizer_patch", "intentId": "feb76e25fc8c4385935a6c9d711257aa", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778740+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.624026+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2a7c486c898b40db91313dcb46d2beb2", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778737+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623947+00:00", "framework": "vllm", "intentId": "e99f1756b5ae46d6a4c2354de63cffd7", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778734+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623865+00:00", "framework": "vllm", "intentId": "2690a665c5a443b49fe0bdaa5d83ec1c", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778732+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623780+00:00", "framework": "vllm", "intentId": "3d828d44c761463e9f370301edd213d1", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778729+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623696+00:00", "framework": "vllm", "intentId": "35c80514b7fa457fa91fbf9e0d5ba049", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778726+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623596+00:00", "framework": "vllm", "intentId": "d8e16a386c5e4f1291efde6b454e5afb", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778723+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623510+00:00", "framework": "vllm", "intentId": "fa3119585b644519b76896e0e703029b", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778719+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623424+00:00", "framework": "vllm", "intentId": "f29ca31caa7f44b8a2f3a523b9a33f40", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778716+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623336+00:00", "framework": "vllm", "intentId": "21aaa0625e354802892392add853d57b", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778711+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623253+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f90c588f970b449c825be3b04f0ab688", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778690+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.623111+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2e2beedc5cfd49718b36bf9199dc0bb7", "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": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764726+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157483+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e913e98636f540b08896fffd55a94bc4", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764723+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157441+00:00", "framework": "vllm-patch-tokenizer", "intentId": "0453eebf35f844a4a66cbbaeacfb9e36", "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": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764720+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157398+00:00", "framework": "vllm-patch-tokenizer", "intentId": "08495d40498e4f6f8b79df3c3456e2fe", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764717+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157356+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c8954329246a4bde9f56edd89b6ed96d", "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": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764714+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157314+00:00", "framework": "vllm-patch-tokenizer", "intentId": "903d0fdd4fb4488cb6848734be17f23c", "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": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764711+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157271+00:00", "framework": "vllm-patch-tokenizer", "intentId": "0db6569351bb455c8ad4bce3de0d646d", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764703+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157143+00:00", "framework": "vllm-patch-tokenizer", "intentId": "402b318e4b6942cfbe0cac82730d14b1", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764700+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157101+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c8c6869119b14d00a8fc35e1f78a6066", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764698+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157058+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2b8b5d0e0056493b85ddd9bc1b7c3556", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "df59c310a652422eb4792044b7b60b91", "completedAt": "2026-09-20T23:18:39.764695+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:11:07.157016+00:00", "framework": "vllm-patch-tokenizer", "intentId": "def9fc978b414266a7327c91980e298f", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index e4eb1d28a0..1686fb283d 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2021 + "unified_success_first": 2022 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -16,7 +16,7 @@ "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82, "text-generation|Cambricon_mlu-370-x8|vllm": 55, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 40, - "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 92, + "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 93, "text-generation|Iluvatar_bi-100|transformers": 20, "text-generation|Iluvatar_bi-150|llamacpp": 16, "text-generation|Iluvatar_bi-150|transformers": 30, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 118 }, - "acceptedSinceRefresh": 2021, - "acceptedTotal": 2021, - "generatedAt": "2026-09-21T00:41:04.812999+00:00", + "acceptedSinceRefresh": 2022, + "acceptedTotal": 2022, + "generatedAt": "2026-09-21T01:01:38.943928+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index f2003851d6..b5c3ab4b50 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1159,3 +1159,4 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T20:09:24.405809+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986872", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T20:09:24.421834+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-21T00:51:43.688289+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 7bebbbc303..ca7b9f23ba 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "87ea93bf42a8a1e24e156ef53e31bb1f4495dd95733206eb0979243c703bdc7f", ".modelhub_state/recent_outcomes.jsonl": "7f4abc664bcf1e6f5f29fd9daaf4b42b82bc638059c252e52870ccc20b3b941c", ".modelhub_state/recovery_active_tasks.jsonl": "97d851f31bc293b1c6d78102824689508fb60f00bc2f0b426f44f13df4c5a319", - ".modelhub_state/recovery_intents.jsonl": "ec861b5a2ffff2dde4379781372317f5b49b03876d73687ff32bb6f1beb296ed", - ".modelhub_state/routing_intelligence.json": "ed5c5140e24aabc43151a286b69340887209db72849b02a56d9913dc99001ac6", + ".modelhub_state/recovery_intents.jsonl": "2e2d30366fc5e1fdea65129280d21b8f6ee6cf7fb09df9e8662918fc8d175210", + ".modelhub_state/routing_intelligence.json": "5918b45e7f3bcb83b0603c317612101afc4cc8b48989343cbbec73c09792fbcf", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "07b5f18add0c0bd7032ddac42dcf7d8222a6b4562f30172bb3cdd84cd9119f11", - "outcomes/submissions.jsonl": "60c7e9051904788cf1f44bfbbd8d73b284f71af179e63a4981c794c4763c1a46" + "ledger/submissions.jsonl": "31a00874f04c9ca2304191ccc401cbcc15dfcef49fe8243000d8e77dddfc8e11", + "outcomes/submissions.jsonl": "a313ae4532b64b548b9ae24505d1048d9f5cef8e9f144fb854dfca3c4fbed12e" }, - "generation": 11046, - "phase": "intent", + "generation": 11047, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T00:51:37.756474+00:00", + "updatedAt": "2026-09-21T01:01:39.154108+00:00", "writerId": "fc715c06e24c4db2ae3e425e435db996" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 9415ee79b4..3b3fee19a0 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1116,3 +1116,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:29:58.598630+00:00", "targetGpu": "Biren_166m", "taskId": "4990404", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:36:43.644698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4990464", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:41:04.760036+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990527", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:51:43.688289+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation", "verifyResult": null}