CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 11130 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 03:15:12 +00:00
parent b0c0deb0cb
commit adb54fd8a2
5 changed files with 55 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

105
.modelhub_state/recovery_intents.jsonl
View File

@@ -1961,42 +1961,42 @@
{"batchId": "243f4088a4994c3cbc472ef19e52886e", "completedAt": "2026-09-21T02:21:28.412435+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:21:26.798256+00:00", "framework": "vllm", "intentId": "444f704301f944879fae4a3fce3a65ea", "lastModified": "2026-09-20T14:39:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "reconciledAt": "2026-09-21T03:05:57.242885+00:00", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4992047", "taskType": "text-generation"}
{"batchId": "243f4088a4994c3cbc472ef19e52886e", "completedAt": "2026-09-21T02:21:28.412447+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:21:26.798380+00:00", "framework": "vllm", "intentId": "eea322d8e8624c00812a6ff7ecd1b244", "lastModified": "2026-09-17T13:36:05+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "reason": null, "reconciledAt": "2026-09-21T03:05:57.242585+00:00", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4992046", "taskType": "text-generation"}
{"batchId": "4ebeabe10e824f7ab597594406b6205f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:51:56.239072+00:00", "framework": "vllm-customized", "intentId": "67b30ce588ad4c6f9412e291c75fcecc", "lastModified": "2026-09-20T14:50:03+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "reconciledAt": "2026-09-21T03:05:57.245438+00:00", "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4992371", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.555968+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b21c2e9db2fc42c3899ad1b494c0bf78", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.556971+00:00", "framework": "vllm_fix_tokenizer", "intentId": "173ec5f2cbbc4148b47133e20aeaa56d", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557035+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8013c9089d2940268c91b114d9e94d80", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557080+00:00", "framework": "vllm-mlu", "intentId": "cc9dcafb85344e738976036273ab6593", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557149+00:00", "framework": "vllm", "intentId": "c2fd8f6e6f8447f08128dc9542eeef2d", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557210+00:00", "framework": "vllm", "intentId": "a9f13fb1dbcd4a5e9a765d11833ae2af", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557269+00:00", "framework": "vllm", "intentId": "b17c22a2aa37424fbe11665cb2950c32", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557328+00:00", "framework": "vllm", "intentId": "8fb2a00847a6422f83ecf92fd67fed9d", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557417+00:00", "framework": "vllm", "intentId": "021fa45a85de42d18cfee559fdf547cb", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557482+00:00", "framework": "vllm", "intentId": "b2a167588e084209b02d611dfbeb4c4e", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557539+00:00", "framework": "vllm", "intentId": "84f59afdbef04797be7aaea42bb5eb48", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557596+00:00", "framework": "vllm", "intentId": "cc5c2e2b1a6a4aa49426be59fbb25f9d", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557653+00:00", "framework": "vllm", "intentId": "dedc7edf43ed4165be6036717cf3a883", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557729+00:00", "framework": "vllm", "intentId": "69d289f7399046dc9c71586dca9a3643", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557787+00:00", "framework": "vllm", "intentId": "505bf5f419ce4d968f7a2345cb17e447", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557844+00:00", "framework": "vllm", "intentId": "0964b2e4a372466394d03d9111957982", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557901+00:00", "framework": "vllm", "intentId": "8bc100ff46b642a6ab8e3bbee5a98d13", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557958+00:00", "framework": "vllm", "intentId": "6938b5953adc4b329152d78feb39399b", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558014+00:00", "framework": "vllm", "intentId": "d8bbf02d284041b396c8b89f6cca50de", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558070+00:00", "framework": "vllm", "intentId": "836b19cc3f5042738981ac6f021eaf55", "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": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558127+00:00", "framework": "vllm", "intentId": "e6e7a276612c46f1a51d6a703587cb5a", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558184+00:00", "framework": "vllm", "intentId": "012b33523947498897c6ad2f2ca83a37", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558240+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c109aecbd52404683c3fa072cf95a70", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558284+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a471d47e1acb4d368eec329e9f33e966", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558327+00:00", "framework": "vllm-patch-tokenizer", "intentId": "61b04169ae9049d8ab5c29366b9516d3", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558369+00:00", "framework": "vllm-patch-tokenizer", "intentId": "46f87227ec65464685bb60bf1f02a2cd", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558412+00:00", "framework": "vllm-patch-tokenizer", "intentId": "6d99d70168954b6098d1fce1805d088c", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558455+00:00", "framework": "vllm-patch-tokenizer", "intentId": "674e8b31d1b141e6a518ad774cb216da", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558497+00:00", "framework": "vllm-patch-tokenizer", "intentId": "25997315b2d949189f7b7836f5a6f09c", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558538+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ade5f3328390402fa3cb080ed30644f8", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558580+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3e96bd2d86b74ea0b8fac8840c68fd6f", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558622+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2e85fb1258b44b858d843e2774a38e23", "lastModified": "2026-08-24T19:20:59+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558673+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e8208942b81a41c4b1ac543edc23077d", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558719+00:00", "framework": "vllm-patch-tokenizer", "intentId": "621ca79f277541b3947fc7f43c3453f7", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558762+00:00", "framework": "vllm", "intentId": "8cd6962ffe23458d95ed285f9732a1dd", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558810+00:00", "framework": "vllm", "intentId": "765e405dd2454d4a8a84eaf0bb67d118", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788713+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.555968+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b21c2e9db2fc42c3899ad1b494c0bf78", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4992751", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788728+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.556971+00:00", "framework": "vllm_fix_tokenizer", "intentId": "173ec5f2cbbc4148b47133e20aeaa56d", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4992749", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788748+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557149+00:00", "framework": "vllm", "intentId": "c2fd8f6e6f8447f08128dc9542eeef2d", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "reason": null, "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4992750", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788845+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558810+00:00", "framework": "vllm", "intentId": "765e405dd2454d4a8a84eaf0bb67d118", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788843+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558762+00:00", "framework": "vllm", "intentId": "8cd6962ffe23458d95ed285f9732a1dd", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788840+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558719+00:00", "framework": "vllm-patch-tokenizer", "intentId": "621ca79f277541b3947fc7f43c3453f7", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788837+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558673+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e8208942b81a41c4b1ac543edc23077d", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788834+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558622+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2e85fb1258b44b858d843e2774a38e23", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788831+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558580+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3e96bd2d86b74ea0b8fac8840c68fd6f", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788829+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558538+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ade5f3328390402fa3cb080ed30644f8", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788826+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558497+00:00", "framework": "vllm-patch-tokenizer", "intentId": "25997315b2d949189f7b7836f5a6f09c", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788823+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558455+00:00", "framework": "vllm-patch-tokenizer", "intentId": "674e8b31d1b141e6a518ad774cb216da", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788820+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558412+00:00", "framework": "vllm-patch-tokenizer", "intentId": "6d99d70168954b6098d1fce1805d088c", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788818+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558369+00:00", "framework": "vllm-patch-tokenizer", "intentId": "46f87227ec65464685bb60bf1f02a2cd", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788815+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558327+00:00", "framework": "vllm-patch-tokenizer", "intentId": "61b04169ae9049d8ab5c29366b9516d3", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788812+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558284+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a471d47e1acb4d368eec329e9f33e966", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788809+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558240+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c109aecbd52404683c3fa072cf95a70", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788806+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558184+00:00", "framework": "vllm", "intentId": "012b33523947498897c6ad2f2ca83a37", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788803+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558127+00:00", "framework": "vllm", "intentId": "e6e7a276612c46f1a51d6a703587cb5a", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788800+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558070+00:00", "framework": "vllm", "intentId": "836b19cc3f5042738981ac6f021eaf55", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788797+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558014+00:00", "framework": "vllm", "intentId": "d8bbf02d284041b396c8b89f6cca50de", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788794+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557958+00:00", "framework": "vllm", "intentId": "6938b5953adc4b329152d78feb39399b", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788792+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557901+00:00", "framework": "vllm", "intentId": "8bc100ff46b642a6ab8e3bbee5a98d13", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788789+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557844+00:00", "framework": "vllm", "intentId": "0964b2e4a372466394d03d9111957982", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788785+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557787+00:00", "framework": "vllm", "intentId": "505bf5f419ce4d968f7a2345cb17e447", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788782+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557729+00:00", "framework": "vllm", "intentId": "69d289f7399046dc9c71586dca9a3643", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557653+00:00", "framework": "vllm", "intentId": "dedc7edf43ed4165be6036717cf3a883", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788776+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557596+00:00", "framework": "vllm", "intentId": "cc5c2e2b1a6a4aa49426be59fbb25f9d", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788773+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557539+00:00", "framework": "vllm", "intentId": "84f59afdbef04797be7aaea42bb5eb48", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788770+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557482+00:00", "framework": "vllm", "intentId": "b2a167588e084209b02d611dfbeb4c4e", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788766+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557417+00:00", "framework": "vllm", "intentId": "021fa45a85de42d18cfee559fdf547cb", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788762+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557328+00:00", "framework": "vllm", "intentId": "8fb2a00847a6422f83ecf92fd67fed9d", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788756+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557269+00:00", "framework": "vllm", "intentId": "b17c22a2aa37424fbe11665cb2950c32", "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": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788752+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557210+00:00", "framework": "vllm", "intentId": "a9f13fb1dbcd4a5e9a765d11833ae2af", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788743+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557080+00:00", "framework": "vllm-mlu", "intentId": "cc9dcafb85344e738976036273ab6593", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "completedAt": "2026-09-21T03:15:12.788732+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557035+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8013c9089d2940268c91b114d9e94d80", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388181+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1948200c63fd4072ac075656ec8053ee", "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": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388178+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135881+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bf3aed8733f24050b6c911eb5a98d891", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388175+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135828+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d6d64229eafe4036a52529aaa805b830", "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"}
@@ -2264,36 +2264,3 @@
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880122+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.234388+00:00", "framework": "vllm_fix_tokenizer", "intentId": "93af7338aa9742c8995e5bc317b9d0dc", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880116+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.234240+00:00", "framework": "vllm_fix_tokenizer", "intentId": "93fc109858bf436f997aa7eae9d44746", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880113+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.234165+00:00", "framework": "vllm_fix_tokenizer", "intentId": "478e45de71394a12be61f790cc45892c", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880110+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.234091+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8545d4d787c24c91a881b6b07b906728", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880107+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.234017+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a7ca45f317024e9cb5c0a7447a2bf829", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880104+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233937+00:00", "framework": "vllm_fix_tokenizer", "intentId": "15daefd8f37e4f0a94c1da130a42fa6d", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880101+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233863+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a612b1966b94483dbf45292f05c9abc0", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880098+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233790+00:00", "framework": "vllm_fix_tokenizer", "intentId": "567a72bc00694caf97266236843d1268", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880095+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233716+00:00", "framework": "vllm_fix_tokenizer", "intentId": "633a2d0e1a194040a22757252f439d85", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880093+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233633+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dd85e027fbe4447395779ff4affc2161", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880090+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233558+00:00", "framework": "vllm_fix_tokenizer", "intentId": "467d75dd4b384b4a98c79dea58fe1351", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880087+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233484+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1f82f41a8faf4f9897f2ebffe9af3042", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880084+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233409+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6ce53ca49a9f4a9f806b144ad7f24c09", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880081+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233333+00:00", "framework": "vllm_fix_tokenizer", "intentId": "795ab5ee92094881a172f9119006df4a", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880079+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233258+00:00", "framework": "vllm_fix_tokenizer", "intentId": "613f5c1391d542ce868425d0b1950efe", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880076+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233184+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8ac854aedc26442faf50be6108c7ade9", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880073+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233108+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec4659376b0646049b0bafa40c2c4801", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880070+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.233034+00:00", "framework": "vllm_fix_tokenizer", "intentId": "29d573f9024548f28d919220914991be", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880066+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232960+00:00", "framework": "vllm_fix_tokenizer", "intentId": "873a3cfb5ff2440ab9f083b134d61d46", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880063+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232884+00:00", "framework": "vllm_fix_tokenizer", "intentId": "85bf36f89394452eb65be8003ecb565d", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880060+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232810+00:00", "framework": "vllm_fix_tokenizer", "intentId": "08c5aebdd29d4d93991a7348a2dd80a2", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880056+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232734+00:00", "framework": "vllm_fix_tokenizer", "intentId": "58d45101151d47f1bc97dc2e67b250a4", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880054+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232653+00:00", "framework": "vllm_fix_tokenizer", "intentId": "620b38a5436d4ba7ab8158177bc294d4", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880051+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232579+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f1b4ac92847249aab16cd79217c607c6", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880044+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232431+00:00", "framework": "vllm_fix_tokenizer", "intentId": "26f8e1d2abe041f09686e285ebcde760", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880041+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232357+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3e7edb1bf8864e9a9bed143cd1054dc7", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880038+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232284+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8afcef18f5574dc486f4145f8feb8c29", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880035+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232209+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9eae16fff4c8420390a0fd7cdcf9f8de", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880032+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.232135+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fbf010afd8fe4814a1785284717072ca", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880025+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.231985+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9ff0220ace094e5caf160913ccafd738", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880021+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.231911+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b53ef226d9974dc38d011419f94d0eca", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880018+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.231833+00:00", "framework": "vllm_fix_tokenizer", "intentId": "47f51e42322b45c0a8e2e7208a6aee95", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.880013+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.231725+00:00", "framework": "vllm", "intentId": "78e9583f0c8e44c3b1244cc3fc9b8222", "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": "7baa8a6d2e634624be0d39fcee9aed65", "completedAt": "2026-09-21T01:32:21.879996+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:23:56.231527+00:00", "framework": "vllm", "intentId": "93f2a7bce9d94ccaad8f70be58d8f071", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111089+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938810+00:00", "framework": "vllm_fix_tokenizer", "intentId": "79f1949e9b554e83a620c1d6a5411da3", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111087+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938753+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c0241439eb454c13a187d21167c5a622", "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"}

12
.modelhub_state/routing_intelligence.json
View File

@@ -1,6 +1,6 @@
{
"acceptedByCategory": {
"unified_success_first": 2100
"unified_success_first": 2103
},
"acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17,
@@ -25,8 +25,8 @@
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 40,
"text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 3,
"text-generation|Iluvatar_mrv-100|vllm": 62,
"text-generation|Kunlunxin_p-800|vllm": 38,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 176,
"text-generation|Kunlunxin_p-800|vllm": 39,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 178,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 70,
"text-generation|MetaX_c-500|vllm": 104,
"text-generation|Mthreads_s4000|llamacpp": 17,
@@ -38,8 +38,8 @@
"text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 120
},
"acceptedSinceRefresh": 2100,
"acceptedTotal": 2100,
"generatedAt": "2026-09-21T02:21:28.346456+00:00",
"acceptedSinceRefresh": 2103,
"acceptedTotal": 2103,
"generatedAt": "2026-09-21T03:15:12.680717+00:00",
"version": 1
}

3
ledger/submissions.jsonl
View File

@@ -1178,3 +1178,6 @@
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T20:09:24.405809+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986872", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T20:09:24.421834+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "submitTime": "2026-09-21T03:11:17.186758+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4992751", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "submitTime": "2026-09-21T03:11:17.184850+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4992749", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "modelId": "neuralmagic/starcoder2-3b-FP8", "submitTime": "2026-09-21T03:11:17.181043+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4992750", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"}

14
manifest.json
View File

@@ -10,16 +10,16 @@
".modelhub_state/queue_cleanup_latest.json": "294596e0492bf1839a4c2e817f44101a0d6d6c4779bf685b402ef658b7bffabd",
".modelhub_state/recent_outcomes.jsonl": "254ebb9091d505dfca62fa053b0d43c6b5fe34a92e9c453216b3faaf0a55f63b",
".modelhub_state/recovery_active_tasks.jsonl": "9b6030185dfd7968c28eb4ce8d77f9fa739a58e4f26a32c6aa6d31b632645f98",
".modelhub_state/recovery_intents.jsonl": "fd5ce535ad2070500673696526179a249815f9ea6fb9e97651077c25752415b6",
".modelhub_state/routing_intelligence.json": "a27c2ca5d63103031c8ffb9b5d9d41a0d0d174f4c58e138f98c42bdb550def90",
".modelhub_state/recovery_intents.jsonl": "703b5d0f0dafb1645288b0265e03cd9395bbdc5b8164746b5b629d08e1c2e468",
".modelhub_state/routing_intelligence.json": "e7c644b6e7e5b738cb152d9c9a36507b92714dc85672675779db82b0a0db16a1",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "ca3fbf25b8f261c314737aa5e015e297bc78155dd2ab15df002d6987510ce2e1",
"outcomes/submissions.jsonl": "0db2d2577767bac55989e1bf2dd694de8ee1252de5d5750755162193bfded03f"
"ledger/submissions.jsonl": "ec8541f2003870ed91eac724cf39bd3fb9660f3cd5c613aedd1a584722dc02a3",
"outcomes/submissions.jsonl": "63a249896f6c5ee2aa667ec87054256c0961ee2541801cff625eab6dcf8155ed"
},
"generation": 11129,
"phase": "intent",
"generation": 11130,
"phase": "result",
"schemaVersion": 1,
"updatedAt": "2026-09-21T03:11:09.690147+00:00",
"updatedAt": "2026-09-21T03:15:12.931744+00:00",
"writerId": "8b35139af6674067a339a670222d4b67"
}

3
outcomes/submissions.jsonl
View File

@@ -1169,3 +1169,6 @@
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "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": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:10:00.812814+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991872", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "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 - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-20T22:43:47.754849+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:21:28.295232+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4992047", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973200235, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973200235}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:21:28.285988+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4992046", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261800, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261800}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T03:11:17.186758+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4992751", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "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": 2018195467}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T03:11:17.184850+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4992749", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786187, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786187}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T03:11:17.181043+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4992750", "taskType": "text-generation", "verifyResult": null}