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

state: generation 10653 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 15:12:36 +00:00
parent ccfc6e764d
commit 6a461369ce
5 changed files with 78 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files

174
.modelhub_state/recovery_intents.jsonl
View File

@@ -1683,65 +1683,65 @@
{"batchId": "c208b2f645614a14a05f569686eaa8f0", "completedAt": "2026-09-20T14:43:55.731149+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:37:40.025941+00:00", "framework": "vllm_tokenizer_patch", "intentId": "945ed355fc854c3796bff67a188dc1a4", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T15:00:55.812706+00:00", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation"}
{"batchId": "c208b2f645614a14a05f569686eaa8f0", "completedAt": "2026-09-20T14:43:55.731183+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:37:40.026474+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cc61d16ed90546aa8cdaefcc5b85acf3", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-20T15:00:55.812703+00:00", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4980576", "taskType": "text-generation"}
{"batchId": "feb78ef0c18e4e3985359b64b1296b80", "completedAt": "2026-09-20T14:48:06.593877+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:48:03.991748+00:00", "framework": "vllm-customized", "intentId": "71511ea3fb1c4043b4770c7db4bb7a60", "lastModified": "2026-09-14T13:40:21+00:00", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "reason": null, "reconciledAt": "2026-09-20T15:00:55.812429+00:00", "repoId": "IntervitensInc/kek_mk3", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4980632", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951708+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c4b19a906a774f309ff1ff16ca5b9c41", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951825+00:00", "framework": "vllm_tokenizer_patch", "intentId": "40cb8d6cac4845e4b49aa5c6cd800863", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951881+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0d7ff7ab8d9f4381af3a1be1995cacaa", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951932+00:00", "framework": "vllm_tokenizer_patch", "intentId": "10560b1d534d4396951654300e5f82f2", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951982+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a4abba36ce1f48f2b923eab116a13ba8", "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": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952040+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4511bef8b0a2471ea3e7bebba695b62b", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952091+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7b5eb8e18c444b10a4aa2a7a25358e4a", "lastModified": "2026-08-24T19:08:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4c3fe9e8ebe546fcabb184b93f132fd7", "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": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952192+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da2a3308c0464a339216574c69de10bd", "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": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952242+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dcaf958f00014cbeae7be125fc5407c2", "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": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952293+00:00", "framework": "vllm-mlu", "intentId": "5dca1f493a4f450b843a4c0dca386e5c", "lastModified": "2026-08-24T19:41:08+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-7B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952346+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8453111e6f95487a951acc9ab7eb1406", "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": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952397+00:00", "framework": "vllm_fix_tokenizer", "intentId": "50aa8565036e4d8db1c60291b6c24c9a", "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": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952441+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d2f793c49695489ca0d62834bf3d2569", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952482+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cd22e25ea99948f4a3f86a3abf88d1a2", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952520+00:00", "framework": "vllm_tokenizer_patch", "intentId": "db5ef01d080f4be1b7f48c121dd7844e", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952558+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ae386b83ff0f4b9aa2b54c741c4a7979", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952596+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1f39dc5cef934600a21d3a6b7db16562", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952634+00:00", "framework": "vllm_tokenizer_patch", "intentId": "285d6977567b4ec1956454e828123724", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952681+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ad23005b2b24d43b29c5d5b5b1d1ad8", "lastModified": "2026-08-24T18:26:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a16-per-channel", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952720+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9d7873e262aa453f8cafc6820eaeb24b", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952758+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dbce734bbe874bf999d1402247b00690", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952802+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b16dee7c56c046a6a1fd2d9d682da991", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952840+00:00", "framework": "vllm_tokenizer_patch", "intentId": "caaa68804a024d259da4b19e35b81f66", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952878+00:00", "framework": "vllm_tokenizer_patch", "intentId": "543bd5766eeb45a088ef421fdc10f831", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952917+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3b5a69ab68dc4169b5a508002ee1d389", "lastModified": "2026-08-24T19:38:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952954+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b5bcc23df75484eb2ddecd02328c1a6", "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": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952992+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1040d7d038c949d4ada8b86c5cc1dfc2", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953030+00:00", "framework": "vllm_tokenizer_patch", "intentId": "84d0340c697641ccbf522275e517eb59", "lastModified": "2026-08-24T19:06:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953068+00:00", "framework": "vllm-mlu", "intentId": "734e2e817a934c74ada62bb9a0c013a5", "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": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953133+00:00", "framework": "vllm-mlu", "intentId": "a2440e9d55d84cd2a7ea99d282034d94", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953196+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1de289508f8e422d891c1cae3c42a9e0", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953254+00:00", "framework": "vllm_tokenizer_patch", "intentId": "33663303a83b4133b366f73ab7f35f1d", "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": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953304+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6f95599364d447559daa41c7bb8bd056", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953354+00:00", "framework": "vllm_tokenizer_patch", "intentId": "42386fe3fd38475bbeab191d0ace37fe", "lastModified": "2026-08-24T19:40:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953403+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cd5ee274bcb0463b9348676128d956f4", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953453+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ac5b4b4ab21743249abad081636a13ab", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953502+00:00", "framework": "vllm_tokenizer_patch", "intentId": "472fdf72b1d748cfbc4a31ff4db2a205", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953550+00:00", "framework": "vllm_tokenizer_patch", "intentId": "afd24ec2b34342658a10ac1fd25b0e79", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953600+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7f0ac1d3ed134457bdcd282d6a45626c", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953655+00:00", "framework": "vllm_tokenizer_patch", "intentId": "be18720fa05a4f398244a41f20fa826e", "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": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953709+00:00", "framework": "vllm", "intentId": "e9634a782c8248bb9f50e3b78290f208", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953768+00:00", "framework": "vllm", "intentId": "4bce9ec7f1164ee89c7593f16b0f6c78", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953826+00:00", "framework": "vllm", "intentId": "1caf59014fd94f11ac48834037dd438e", "lastModified": "2026-09-09T14:59:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Hy3-preview-JANGTQ", "repoId": "JANGQ-AI/Hy3-preview-JANGTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953884+00:00", "framework": "vllm", "intentId": "d1f036f145c54c12b62535807537891a", "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": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953941+00:00", "framework": "vllm", "intentId": "3ea2b2b72d744f57a94cf8d649c27c95", "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": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953995+00:00", "framework": "vllm", "intentId": "90cfaa5b31594d55ae7f4adb0f49d34f", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954047+00:00", "framework": "vllm", "intentId": "2988dcb65ec1408b9993cbd021da94e8", "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": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954099+00:00", "framework": "vllm", "intentId": "4736a85b6ee24ab8b763d00bd87d11e9", "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": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954152+00:00", "framework": "vllm", "intentId": "1276b51a7424428f8cf66de35a98a312", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954211+00:00", "framework": "vllm", "intentId": "fae40da8fa9a4fddb0a56dd97c250883", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954263+00:00", "framework": "vllm", "intentId": "41cbd27946914621a8b62ff87e1e19d0", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954318+00:00", "framework": "vllm", "intentId": "bcd6da8046d54fb0b4161bbdcfc25cb7", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954373+00:00", "framework": "vllm", "intentId": "99f6c5a4b4034871b8b9b04bb9789c64", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954428+00:00", "framework": "vllm", "intentId": "06482311652642b18a7feef538dc30aa", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954483+00:00", "framework": "vllm", "intentId": "3a76657a26bc468e8e07ee8d1e0b3f31", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954537+00:00", "framework": "vllm", "intentId": "47ac440bce3f4a8d91eb60d53dcf552f", "lastModified": "2026-08-24T18:50:21+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954592+00:00", "framework": "vllm", "intentId": "db64fefec4a6420785fa10132af72b69", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954646+00:00", "framework": "vllm", "intentId": "3d2e4fe1c65640acb4d8fd270f91a77b", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727125+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951825+00:00", "framework": "vllm_tokenizer_patch", "intentId": "40cb8d6cac4845e4b49aa5c6cd800863", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4980848", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727129+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951881+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0d7ff7ab8d9f4381af3a1be1995cacaa", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "reason": null, "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4980847", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727169+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952482+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cd22e25ea99948f4a3f86a3abf88d1a2", "lastModified": "2026-08-24T19:36:40+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4980890", "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727304+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954646+00:00", "framework": "vllm", "intentId": "3d2e4fe1c65640acb4d8fd270f91a77b", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727301+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954592+00:00", "framework": "vllm", "intentId": "db64fefec4a6420785fa10132af72b69", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727298+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954537+00:00", "framework": "vllm", "intentId": "47ac440bce3f4a8d91eb60d53dcf552f", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727295+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954483+00:00", "framework": "vllm", "intentId": "3a76657a26bc468e8e07ee8d1e0b3f31", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727292+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954428+00:00", "framework": "vllm", "intentId": "06482311652642b18a7feef538dc30aa", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727289+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954373+00:00", "framework": "vllm", "intentId": "99f6c5a4b4034871b8b9b04bb9789c64", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727287+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954318+00:00", "framework": "vllm", "intentId": "bcd6da8046d54fb0b4161bbdcfc25cb7", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727284+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954263+00:00", "framework": "vllm", "intentId": "41cbd27946914621a8b62ff87e1e19d0", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727282+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954211+00:00", "framework": "vllm", "intentId": "fae40da8fa9a4fddb0a56dd97c250883", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727279+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954152+00:00", "framework": "vllm", "intentId": "1276b51a7424428f8cf66de35a98a312", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727276+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954099+00:00", "framework": "vllm", "intentId": "4736a85b6ee24ab8b763d00bd87d11e9", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727274+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.954047+00:00", "framework": "vllm", "intentId": "2988dcb65ec1408b9993cbd021da94e8", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727272+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953995+00:00", "framework": "vllm", "intentId": "90cfaa5b31594d55ae7f4adb0f49d34f", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727269+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953941+00:00", "framework": "vllm", "intentId": "3ea2b2b72d744f57a94cf8d649c27c95", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727266+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953884+00:00", "framework": "vllm", "intentId": "d1f036f145c54c12b62535807537891a", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727263+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953826+00:00", "framework": "vllm", "intentId": "1caf59014fd94f11ac48834037dd438e", "repoId": "JANGQ-AI/Hy3-preview-JANGTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727261+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953768+00:00", "framework": "vllm", "intentId": "4bce9ec7f1164ee89c7593f16b0f6c78", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727257+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953709+00:00", "framework": "vllm", "intentId": "e9634a782c8248bb9f50e3b78290f208", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727254+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953655+00:00", "framework": "vllm_tokenizer_patch", "intentId": "be18720fa05a4f398244a41f20fa826e", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727251+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953600+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7f0ac1d3ed134457bdcd282d6a45626c", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727249+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953550+00:00", "framework": "vllm_tokenizer_patch", "intentId": "afd24ec2b34342658a10ac1fd25b0e79", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727245+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953502+00:00", "framework": "vllm_tokenizer_patch", "intentId": "472fdf72b1d748cfbc4a31ff4db2a205", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727242+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953453+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ac5b4b4ab21743249abad081636a13ab", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727239+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953403+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cd5ee274bcb0463b9348676128d956f4", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727237+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953354+00:00", "framework": "vllm_tokenizer_patch", "intentId": "42386fe3fd38475bbeab191d0ace37fe", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727234+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953304+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6f95599364d447559daa41c7bb8bd056", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727231+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953254+00:00", "framework": "vllm_tokenizer_patch", "intentId": "33663303a83b4133b366f73ab7f35f1d", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727228+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953196+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1de289508f8e422d891c1cae3c42a9e0", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727225+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953133+00:00", "framework": "vllm-mlu", "intentId": "a2440e9d55d84cd2a7ea99d282034d94", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727223+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953068+00:00", "framework": "vllm-mlu", "intentId": "734e2e817a934c74ada62bb9a0c013a5", "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": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727219+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.953030+00:00", "framework": "vllm_tokenizer_patch", "intentId": "84d0340c697641ccbf522275e517eb59", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727216+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952992+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1040d7d038c949d4ada8b86c5cc1dfc2", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727213+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952954+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b5bcc23df75484eb2ddecd02328c1a6", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727210+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952917+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3b5a69ab68dc4169b5a508002ee1d389", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727207+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952878+00:00", "framework": "vllm_tokenizer_patch", "intentId": "543bd5766eeb45a088ef421fdc10f831", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727203+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952840+00:00", "framework": "vllm_tokenizer_patch", "intentId": "caaa68804a024d259da4b19e35b81f66", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727200+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952802+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b16dee7c56c046a6a1fd2d9d682da991", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727196+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952758+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dbce734bbe874bf999d1402247b00690", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727192+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952720+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9d7873e262aa453f8cafc6820eaeb24b", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727188+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952681+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ad23005b2b24d43b29c5d5b5b1d1ad8", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727184+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952634+00:00", "framework": "vllm_tokenizer_patch", "intentId": "285d6977567b4ec1956454e828123724", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727180+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952596+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1f39dc5cef934600a21d3a6b7db16562", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727176+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952558+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ae386b83ff0f4b9aa2b54c741c4a7979", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727172+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952520+00:00", "framework": "vllm_tokenizer_patch", "intentId": "db5ef01d080f4be1b7f48c121dd7844e", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727165+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952441+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d2f793c49695489ca0d62834bf3d2569", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727161+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952397+00:00", "framework": "vllm_fix_tokenizer", "intentId": "50aa8565036e4d8db1c60291b6c24c9a", "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": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727158+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952346+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8453111e6f95487a951acc9ab7eb1406", "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": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727155+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952293+00:00", "framework": "vllm-mlu", "intentId": "5dca1f493a4f450b843a4c0dca386e5c", "repoId": "RedHatAI/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727151+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952242+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dcaf958f00014cbeae7be125fc5407c2", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727148+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952192+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da2a3308c0464a339216574c69de10bd", "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": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727145+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4c3fe9e8ebe546fcabb184b93f132fd7", "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": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727142+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952091+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7b5eb8e18c444b10a4aa2a7a25358e4a", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727139+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.952040+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4511bef8b0a2471ea3e7bebba695b62b", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727135+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951982+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a4abba36ce1f48f2b923eab116a13ba8", "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": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727132+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951932+00:00", "framework": "vllm_tokenizer_patch", "intentId": "10560b1d534d4396951654300e5f82f2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "1adede56223f4636ab2af5f9200c5293", "completedAt": "2026-09-20T15:12:36.727108+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T15:06:00.951708+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c4b19a906a774f309ff1ff16ca5b9c41", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "25ba0a4da7e34622a6702513d8cdc4ce", "completedAt": "2026-09-20T14:46:26.841216+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:43:59.030327+00:00", "framework": "vllm", "intentId": "6552e2f86a624809a049273684b0db69", "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": "25ba0a4da7e34622a6702513d8cdc4ce", "completedAt": "2026-09-20T14:46:26.841213+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:43:59.030267+00:00", "framework": "vllm", "intentId": "d4a6ec4d041443a3aa7cbe85d6570cfb", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "25ba0a4da7e34622a6702513d8cdc4ce", "completedAt": "2026-09-20T14:46:26.841210+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:43:59.030208+00:00", "framework": "vllm", "intentId": "c4efb924449747e090a8b2f171754135", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
@@ -1986,59 +1986,3 @@
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554527+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775473+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7a7aab2c8ae94cfbb4a842e10b2ec8a4", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554524+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775423+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8c4ea7f7f91a491ab9857a0b6788e2d1", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554522+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775374+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7c2e7aca822c4244b67eff2765513404", "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": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554519+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775324+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1054018109124d16bd3d3a1803ed88a5", "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": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554516+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775275+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ec23cea0a56a4e50b4a87e8dc5b287dd", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554513+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775225+00:00", "framework": "vllm_tokenizer_patch", "intentId": "65b5313ef4644f4ab11d20978b53b47b", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554510+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775176+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dfa86f57f8a04d2c9b83d6112aabb2a6", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554506+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775126+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1ccb8efd97374af2b668737188b4f643", "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": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554504+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775076+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bb06d2bcec0b4bb8bc994ecde3d11964", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554500+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.775026+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8e3a2eb211cc48f593e5a4886a375e29", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554497+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.774976+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3d71487c827549d6b4cba6cbe659d65e", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554494+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.774925+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d6eb75e0c5af4b1da691b7ed6b6ae86e", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53e35231067c407ab2000d711d045081", "completedAt": "2026-09-20T14:07:56.554469+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:01:19.774763+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cc80ef7a8fac4167b6df3f27718fa70a", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051786+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.200221+00:00", "framework": "vllm", "intentId": "1e676ebe6ca94554b3d461895a08299e", "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": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051783+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.200163+00:00", "framework": "vllm", "intentId": "f2c52849a6a44ed8a2afb48e7df20131", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051780+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.200104+00:00", "framework": "vllm", "intentId": "f852155d13f142e59e0b3414a279eadf", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051777+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.200046+00:00", "framework": "vllm", "intentId": "c06cb422e35147f68ce406be03807d5e", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051775+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199987+00:00", "framework": "vllm", "intentId": "207d165f5e044d749b5a7506851148ad", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051772+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199928+00:00", "framework": "vllm", "intentId": "a187c22713c84e53b9b0c3582ec40756", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051768+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199868+00:00", "framework": "vllm-customized", "intentId": "8b1f333e7b5042cd88e2789f01d5f815", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051765+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199809+00:00", "framework": "vllm-customized", "intentId": "0bcd44f32953492bbf1a97e1c4899eb0", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051762+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199749+00:00", "framework": "vllm-customized", "intentId": "e191641a2b314f7792c00d0edd1eeee2", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051759+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199689+00:00", "framework": "vllm-customized", "intentId": "a008c8ec9f6b466e8b19560b25f3ed98", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051757+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199612+00:00", "framework": "vllm-customized", "intentId": "dfe5dc99de114cfeada6ce8e5a3c330f", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051753+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199553+00:00", "framework": "vllm-customized", "intentId": "794947fb1abf4117babd73b677fec8b3", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051751+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199494+00:00", "framework": "vllm-customized", "intentId": "367f2cbefe26401f9f1613ce3127c52d", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051748+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199434+00:00", "framework": "vllm-customized", "intentId": "e6450f2aff3e43e5b170b881d84387cf", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051745+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199373+00:00", "framework": "vllm-customized", "intentId": "1f867e59370f437a8312bb7364a548c6", "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": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051742+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199332+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5579a33bfc5442a48f359b2f6a0808ea", "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": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051739+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199291+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c584afcfb9bf43b28c355aa018f18d83", "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": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051735+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199250+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e9d7bf33a6914937b6198a9144f01539", "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": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051732+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199206+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9637d8edb3bb4272806226bb6ab9b164", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051729+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199163+00:00", "framework": "vllm-patch-tokenizer", "intentId": "294c18c65af64e52b0fb352ba9292975", "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": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051726+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199120+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c872cf153d3c4a9e98bf48b2aa898e2e", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051722+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199077+00:00", "framework": "vllm-patch-tokenizer", "intentId": "df58224e00b848f3a40b19c10d19fba7", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051719+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.199034+00:00", "framework": "vllm-patch-tokenizer", "intentId": "cf7b741756c74e8fa4db8af5c90cd9b1", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051716+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198991+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fbea68c58b3b411b9f6f852341a698ed", "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": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051713+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198947+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e1f1d512fe3e40ce94bb8a1e00208eab", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051710+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198902+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed897e04ecf74c39af9fddfc663613b9", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051707+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198857+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a6af15eaa30543488857fbb521cac820", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051704+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198812+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2b3ff356e55d42f7a860d49076171b83", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051700+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198755+00:00", "framework": "vllm", "intentId": "e942fc6bd6fd4a1884fa762759d9bfe4", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051696+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198698+00:00", "framework": "vllm", "intentId": "1bb21d153638453ab3efbab18493417b", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051689+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198627+00:00", "framework": "vllm", "intentId": "5eee68d2c77e4d579cb56cfc33ad76f9", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e6ee9f618f7244b8bef49d7238eb2bcd", "completedAt": "2026-09-20T13:46:34.051658+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:42:53.198494+00:00", "framework": "vllm", "intentId": "d3c0f274780c4e7c99483b32bec7c550", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397692+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.689392+00:00", "framework": "vllm", "intentId": "efec5a38f3154878ac3c636eaea39ebd", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397689+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.689337+00:00", "framework": "vllm", "intentId": "93dc1c2e3e5142a09a2487b1aa42ce6e", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397686+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.689266+00:00", "framework": "vllm", "intentId": "51739ebb865344e3930f97c5c0579934", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397684+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.689212+00:00", "framework": "vllm", "intentId": "78009906df1444d58ff0af197ed10338", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397681+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.689160+00:00", "framework": "vllm", "intentId": "4b903c99870040018da696f825f136cb", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397678+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.689109+00:00", "framework": "vllm", "intentId": "06a923f127864fa8a92ef7181b5cd95e", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397675+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.689056+00:00", "framework": "vllm", "intentId": "1cefdc0709f5446ca9104cd08f62bbf3", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397672+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.689003+00:00", "framework": "vllm", "intentId": "e3968b86946746a285a39cfe8b28725f", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397663+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.688950+00:00", "framework": "vllm", "intentId": "b804b436098c4dafbb306bedb7b05062", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397660+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.688879+00:00", "framework": "vllm", "intentId": "a6707779e2034bb1b23f390ccd691f0c", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397657+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.688825+00:00", "framework": "vllm", "intentId": "75bfcd90c56f413fb02f9074719003cb", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397654+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.688769+00:00", "framework": "vllm", "intentId": "02c12367623744849be84bc3ac18f7da", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397651+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.688711+00:00", "framework": "vllm", "intentId": "0fac48b8ffb042e5af386a7fd560405e", "repoId": "JANGQ-AI/Hy3-preview-JANGTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "e82d4a5fcd78405a8b5111c4ec09cd55", "completedAt": "2026-09-20T13:42:52.397648+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T13:35:58.688648+00:00", "framework": "vllm", "intentId": "cbac5fbb109f45b89adc700f59080633", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}

12
.modelhub_state/routing_intelligence.json
View File

@@ -1,14 +1,14 @@
{
"acceptedByCategory": {
"unified_success_first": 1823
"unified_success_first": 1826
},
"acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17,
"text-generation|Ascend_910-b3|vllm": 33,
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 133,
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 134,
"text-generation|Ascend_910-b4|llamacpp": 13,
"text-generation|Ascend_910-b4|vllm": 20,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 126,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 128,
"text-generation|Biren_166m|vllm": 77,
"text-generation|Biren_166m|vllm_fix_tokenizer": 13,
"text-generation|Cambricon_mlu-370-x4|vllm": 48,
@@ -37,8 +37,8 @@
"text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 109
},
"acceptedSinceRefresh": 1823,
"acceptedTotal": 1823,
"generatedAt": "2026-09-20T14:48:06.524036+00:00",
"acceptedSinceRefresh": 1826,
"acceptedTotal": 1826,
"generatedAt": "2026-09-20T15:12:36.665199+00:00",
"version": 1
}

3
ledger/submissions.jsonl
View File

@@ -1105,3 +1105,6 @@
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-20T11:44:01.235722+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4978143", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-20T12:41:32.800701+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979069", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "modelId": "aisingapore/SEA-LION-v1-7B", "submitTime": "2026-09-20T12:55:19.835166+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979183", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "modelId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "submitTime": "2026-09-20T15:06:10.397004+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980848", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "modelId": "nm-testing/tinyllama-marlin24-w4a16-group128", "submitTime": "2026-09-20T15:06:10.390571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T15:06:16.550878+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980890", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}

14
manifest.json
View File

@@ -9,16 +9,16 @@
".modelhub_state/queue_cleanup_latest.json": "eb01f106d0cd4018a0346c4a81182d6a9e67f5d4d14db22f5d0c685667977bc3",
".modelhub_state/recent_outcomes.jsonl": "c686c563ab48519884fd42d9952589ca0656ee5a5fab0f1556f4f5dc80e978ff",
".modelhub_state/recovery_active_tasks.jsonl": "96b91a97fe7611713f8c15cd9da701c3251866b901085189738eeb309814be8d",
".modelhub_state/recovery_intents.jsonl": "272a5dd5ff9d32a9df2e4acc5480a8a76dd1c5e499d5eeffee1a1a4cc4a554b4",
".modelhub_state/routing_intelligence.json": "76d5a555f3a78f8d4ff9b627b9dfe1bd2920e69f743d08781d7c84d2921b9fba",
".modelhub_state/recovery_intents.jsonl": "8663a1092c903fff2a27aee7ce093bf81e40b3857745569c5a49524250461420",
".modelhub_state/routing_intelligence.json": "e418d4958fc758b07f2dc817020c0e7841e2c4bbc38e0fb415434875cd962872",
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "db2082b3e3eb322c0b3e84ac029cea2322e011df5ce88e37a31224b29e715f62",
"outcomes/submissions.jsonl": "17c5f8213d7cabdd84e13e57e2ea022930453af02d538a796b4bf1168f38a3b9"
"ledger/submissions.jsonl": "c57248eec2d02134f39f74a1408a1e947b435008c9abe2196c7b46bc0dd19908",
"outcomes/submissions.jsonl": "4b1b929f99d48e61fbab473e27d2415a307c27476000d3c461f3e0e24e3a8853"
},
"generation": 10652,
"phase": "intent",
"generation": 10653,
"phase": "result",
"schemaVersion": 1,
"updatedAt": "2026-09-20T15:06:01.103558+00:00",
"updatedAt": "2026-09-20T15:12:36.860628+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996"
}

3
outcomes/submissions.jsonl
View File

@@ -1099,3 +1099,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457730}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:38:07.337494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020564058}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:39:32.708014+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980576", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:48:06.475114+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4980632", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233118759, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233118759}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T15:06:10.397004+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980848", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-marlin24-w4a16-group128", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 640856992, "estimatedRequiredGiB": 0.718, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 642705637, "modelscopeLicense": null, "modelscopeParams": 259844096, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 642705637}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T15:06:10.390571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980847", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T15:06:16.550878+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980890", "taskType": "text-generation", "verifyResult": null}