From 2180b8621ad53a465672b3861ba4aab41b5ce51c Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 09:49:02 +0000 Subject: [PATCH] state: generation 11372 (result) --- .modelhub_state/recovery_intents.jsonl | 172 ++++++++-------------- .modelhub_state/routing_intelligence.json | 14 +- ledger/submissions.jsonl | 5 + manifest.json | 14 +- outcomes/submissions.jsonl | 5 + 5 files changed, 83 insertions(+), 127 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 013e3fae88..106c582107 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2031,65 +2031,65 @@ {"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695948+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179908+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c8b86cbd048b41e39e71e32ac6023276", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "reason": null, "reconciledAt": "2026-09-21T09:35:48.297574+00:00", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4997864", "taskType": "text-generation"} {"batchId": "b1abf696e5f843c9b4eec1cb47df86aa", "completedAt": "2026-09-21T09:27:59.695954+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:19:21.179997+00:00", "framework": "vllm", "intentId": "0130519d24ea4c1d86c609de7b0ca5b9", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "reason": null, "reconciledAt": "2026-09-21T09:35:48.297571+00:00", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4997865", "taskType": "text-generation"} {"batchId": "052a3ef1ca704507a84b644771628f89", "completedAt": "2026-09-21T09:33:26.772007+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:33:17.377406+00:00", "framework": "vllm-customized", "intentId": "28f2d282e656423ca2f597ba5f02d675", "lastModified": "2026-09-20T14:39:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "reconciledAt": "2026-09-21T09:35:48.297808+00:00", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4998167", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.404846+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dc1bbc7324e24744bf52e1adb7a2b944", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.404968+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2bf1e4842577432db303ba91c2e705ae", "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": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405023+00:00", "framework": "vllm_fix_tokenizer", "intentId": "614f77bf98b748889af7b244a754a662", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405068+00:00", "framework": "vllm", "intentId": "af1e89d4d49d49ab91aec36c57ca06c7", "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, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405116+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9925633a3f5a40dd9ac32e9e63e08df4", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "24a4f25199eb4f4191b2744b7b6ae51a", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405195+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e3c138b231984ad2bf759891de63091d", "lastModified": "2026-08-24T17:55:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405233+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ff81358ca734b47a106e836a1f71148", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405271+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8cd49b3c9db04ab28d00ee5f21b17df4", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405310+00:00", "framework": "vllm_tokenizer_patch", "intentId": "12ee9796822a41559fc3c1cc750e1234", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405348+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d196ab3bd96e4844b8cb13932690f57a", "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": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405385+00:00", "framework": "vllm_tokenizer_patch", "intentId": "563464de09344181bee8d51442eff825", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405424+00:00", "framework": "vllm_tokenizer_patch", "intentId": "22f497e788354b23bb8752facbfdf367", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405461+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6fcca3c3e2d84c4095741a8740bb7708", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405499+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7f46c7c42a754ffb9ccd691492ecd09e", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405536+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b96adae0f42842b3a34a0f37da5404da", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405573+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c9a16d207004451fb055563caadb84b5", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405611+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a2bae934ce9a4e19bab858725e593415", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405648+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d5e4b7e6f5a341ad9c9dba1f613b82c6", "lastModified": "2026-09-08T15:40:32+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405693+00:00", "framework": "vllm-mlu", "intentId": "51dcf583c46347c6b2295f452831376c", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405761+00:00", "framework": "vllm_tokenizer_patch", "intentId": "93e0534d8c434f6790a09895d6e7a917", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405812+00:00", "framework": "vllm_tokenizer_patch", "intentId": "34d3c311b17d48cc8912f2f01d78adb5", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405862+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6bcdbe8bbe2144e0b2bb4a7f1a193c94", "lastModified": "2026-08-24T18:12:10+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405912+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ff896332209949a3ac302a16043982b6", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405962+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0eb9f93fecb9480fa3f8caf5358a1efd", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406011+00:00", "framework": "vllm_tokenizer_patch", "intentId": "eefd3a5f51be4e8385770954926fa8da", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406060+00:00", "framework": "vllm_tokenizer_patch", "intentId": "40d9cc0cf50641d2a9654c20aa664d88", "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": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406108+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd84a896be6b45898ddba8100c5ea33b", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "df129b71d9e14cd98eea089522c93b2a", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406206+00:00", "framework": "vllm", "intentId": "422577bbcd4743b794cf9bbffe126847", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406264+00:00", "framework": "vllm", "intentId": "b5ce0ba9a5864d9ba0b29cb98cc09a77", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406323+00:00", "framework": "vllm", "intentId": "a69fb60c277943b38e8050c0eb51d03d", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406380+00:00", "framework": "vllm", "intentId": "1b78d944f725418daf5bcec8551ecc90", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406437+00:00", "framework": "vllm", "intentId": "07de76243403465b87bacb2086432b7f", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406495+00:00", "framework": "vllm", "intentId": "e3adaf3396dd44ad88831db3e2424323", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406551+00:00", "framework": "vllm", "intentId": "c59ac11567584269be638039b5058b53", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406608+00:00", "framework": "vllm", "intentId": "4905d8036e5e43ceae61d11a6387c2ed", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406674+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "88a10ca20bb244538cd98710e2babc33", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406721+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a59450ac591e451fabc318830a65bc2d", "lastModified": "2026-08-24T18:06:52+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406764+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6f06c252b38848fb9b02d9c196059cdc", "lastModified": "2026-08-31T03:35:12+00:00", "modelAddress": "https://modelscope.cn/models/logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406807+00:00", "framework": "vllm_fix_tokenizer", "intentId": "38805b8185354f238dfb8e42aca1d847", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406850+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4a1d3ca5039c4c1b97d0d2cebbc423fc", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406894+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fab2331ce6cf4af1b6a0b52f800ad773", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406936+00:00", "framework": "vllm-patch-tokenizer", "intentId": "16f7273188c74556a49518991cd81c35", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406978+00:00", "framework": "vllm-patch-tokenizer", "intentId": "88645fb9177840808e8fbf0c30ddfb80", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407020+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5b86584587974e90bc745fa71c1c60b8", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407062+00:00", "framework": "vllm-patch-tokenizer", "intentId": "98812bc6c0c349138760bfeb80e1783c", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407104+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a38c823cfc654e9c89b598d9664f41ff", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407147+00:00", "framework": "vllm-patch-tokenizer", "intentId": "67ff8c192094428ea8d85baf23bb974d", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407189+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4a309ebea7c34437a21b1ade58ef6fa8", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407231+00:00", "framework": "vllm-patch-tokenizer", "intentId": "325e3879b8be4c11a235ed9d647fa30b", "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, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407273+00:00", "framework": "vllm-patch-tokenizer", "intentId": "cc569b11da8b4fcc8d15d33839eff1de", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407315+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7dbfe2dd1cec4b6b909059e0676e6d18", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407358+00:00", "framework": "vllm", "intentId": "379ba67464b5425eb02b37a25725317f", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407406+00:00", "framework": "vllm", "intentId": "fb62c6b988484ff1a70b82bdfb472b16", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407453+00:00", "framework": "vllm", "intentId": "06930ba0fd194ef99bb38af5b1bef11d", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407500+00:00", "framework": "vllm", "intentId": "bb687fa6bb434bd1b7bcae89c035f946", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407547+00:00", "framework": "vllm-customized", "intentId": "2f41b4f405d14d5eb38f55a32264a6d7", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407606+00:00", "framework": "vllm-customized", "intentId": "203d6fcfb6ef4138a6aaf4df8bbb0d07", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457633+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.404846+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dc1bbc7324e24744bf52e1adb7a2b944", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "reason": null, "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4998299", "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457673+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405195+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e3c138b231984ad2bf759891de63091d", "lastModified": "2026-08-24T17:55:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "reason": null, "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4998300", "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457703+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405611+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a2bae934ce9a4e19bab858725e593415", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "reason": null, "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4998344", "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457783+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407104+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a38c823cfc654e9c89b598d9664f41ff", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "reason": null, "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4998407", "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457785+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407147+00:00", "framework": "vllm-patch-tokenizer", "intentId": "67ff8c192094428ea8d85baf23bb974d", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4998415", "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457810+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407606+00:00", "framework": "vllm-customized", "intentId": "203d6fcfb6ef4138a6aaf4df8bbb0d07", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457808+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407547+00:00", "framework": "vllm-customized", "intentId": "2f41b4f405d14d5eb38f55a32264a6d7", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457805+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407500+00:00", "framework": "vllm", "intentId": "bb687fa6bb434bd1b7bcae89c035f946", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457803+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407453+00:00", "framework": "vllm", "intentId": "06930ba0fd194ef99bb38af5b1bef11d", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457800+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407406+00:00", "framework": "vllm", "intentId": "fb62c6b988484ff1a70b82bdfb472b16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457798+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407358+00:00", "framework": "vllm", "intentId": "379ba67464b5425eb02b37a25725317f", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457795+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407315+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7dbfe2dd1cec4b6b909059e0676e6d18", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457792+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407273+00:00", "framework": "vllm-patch-tokenizer", "intentId": "cc569b11da8b4fcc8d15d33839eff1de", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457790+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407231+00:00", "framework": "vllm-patch-tokenizer", "intentId": "325e3879b8be4c11a235ed9d647fa30b", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457787+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407189+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4a309ebea7c34437a21b1ade58ef6fa8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457780+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407062+00:00", "framework": "vllm-patch-tokenizer", "intentId": "98812bc6c0c349138760bfeb80e1783c", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457778+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.407020+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5b86584587974e90bc745fa71c1c60b8", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457775+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406978+00:00", "framework": "vllm-patch-tokenizer", "intentId": "88645fb9177840808e8fbf0c30ddfb80", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457773+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406936+00:00", "framework": "vllm-patch-tokenizer", "intentId": "16f7273188c74556a49518991cd81c35", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457770+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406894+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fab2331ce6cf4af1b6a0b52f800ad773", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457768+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406850+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4a1d3ca5039c4c1b97d0d2cebbc423fc", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457765+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406807+00:00", "framework": "vllm_fix_tokenizer", "intentId": "38805b8185354f238dfb8e42aca1d847", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457763+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406764+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6f06c252b38848fb9b02d9c196059cdc", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457760+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406721+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a59450ac591e451fabc318830a65bc2d", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457757+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406674+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "88a10ca20bb244538cd98710e2babc33", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457754+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406608+00:00", "framework": "vllm", "intentId": "4905d8036e5e43ceae61d11a6387c2ed", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457751+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406551+00:00", "framework": "vllm", "intentId": "c59ac11567584269be638039b5058b53", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457748+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406495+00:00", "framework": "vllm", "intentId": "e3adaf3396dd44ad88831db3e2424323", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457746+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406437+00:00", "framework": "vllm", "intentId": "07de76243403465b87bacb2086432b7f", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457743+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406380+00:00", "framework": "vllm", "intentId": "1b78d944f725418daf5bcec8551ecc90", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457740+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406323+00:00", "framework": "vllm", "intentId": "a69fb60c277943b38e8050c0eb51d03d", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457737+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406264+00:00", "framework": "vllm", "intentId": "b5ce0ba9a5864d9ba0b29cb98cc09a77", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457734+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406206+00:00", "framework": "vllm", "intentId": "422577bbcd4743b794cf9bbffe126847", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457732+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "df129b71d9e14cd98eea089522c93b2a", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457729+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406108+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd84a896be6b45898ddba8100c5ea33b", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457726+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406060+00:00", "framework": "vllm_tokenizer_patch", "intentId": "40d9cc0cf50641d2a9654c20aa664d88", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457724+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406011+00:00", "framework": "vllm_tokenizer_patch", "intentId": "eefd3a5f51be4e8385770954926fa8da", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457721+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405962+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0eb9f93fecb9480fa3f8caf5358a1efd", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457719+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405912+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ff896332209949a3ac302a16043982b6", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457716+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405862+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6bcdbe8bbe2144e0b2bb4a7f1a193c94", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457713+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405812+00:00", "framework": "vllm_tokenizer_patch", "intentId": "34d3c311b17d48cc8912f2f01d78adb5", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457710+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405761+00:00", "framework": "vllm_tokenizer_patch", "intentId": "93e0534d8c434f6790a09895d6e7a917", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457708+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405693+00:00", "framework": "vllm-mlu", "intentId": "51dcf583c46347c6b2295f452831376c", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457705+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405648+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d5e4b7e6f5a341ad9c9dba1f613b82c6", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457700+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405573+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c9a16d207004451fb055563caadb84b5", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457697+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405536+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b96adae0f42842b3a34a0f37da5404da", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457695+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405499+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7f46c7c42a754ffb9ccd691492ecd09e", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457692+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405461+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6fcca3c3e2d84c4095741a8740bb7708", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457689+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405424+00:00", "framework": "vllm_tokenizer_patch", "intentId": "22f497e788354b23bb8752facbfdf367", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457686+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405385+00:00", "framework": "vllm_tokenizer_patch", "intentId": "563464de09344181bee8d51442eff825", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457683+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405348+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d196ab3bd96e4844b8cb13932690f57a", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457680+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405310+00:00", "framework": "vllm_tokenizer_patch", "intentId": "12ee9796822a41559fc3c1cc750e1234", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457678+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405271+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8cd49b3c9db04ab28d00ee5f21b17df4", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457675+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405233+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ff81358ca734b47a106e836a1f71148", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457663+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "24a4f25199eb4f4191b2744b7b6ae51a", "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": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457660+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405116+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9925633a3f5a40dd9ac32e9e63e08df4", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457656+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405068+00:00", "framework": "vllm", "intentId": "af1e89d4d49d49ab91aec36c57ca06c7", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457653+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405023+00:00", "framework": "vllm_fix_tokenizer", "intentId": "614f77bf98b748889af7b244a754a662", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457645+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.404968+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2bf1e4842577432db303ba91c2e705ae", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979823+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524650+00:00", "framework": "vllm", "intentId": "70181d484e034c4c99bce93d2c9afa9a", "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": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979820+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524590+00:00", "framework": "vllm", "intentId": "745a98c92bf14f7884ff416219393fa7", "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": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979817+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524530+00:00", "framework": "vllm", "intentId": "c97311b9308d4a6d98baffab6c5c7ea5", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} @@ -2336,57 +2336,3 @@ {"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337090+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902481+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fcac75ee90754e4aabb047c188a5c2bd", "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": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337088+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902428+00:00", "framework": "vllm_tokenizer_patch", "intentId": "efb15b49dc1140cd9fb7b6465d2ae795", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337085+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902374+00:00", "framework": "vllm_tokenizer_patch", "intentId": "08c7691d32bb4d90b7298dfd819e7bad", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337082+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902328+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fc336904becf41228759f62f0212c90b", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337079+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902279+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f761d106cbaf423bb4308d4afa1b7f0d", "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": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337077+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902238+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f630ae4f9cb548e28cb01339b58ab8d4", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337074+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902198+00:00", "framework": "vllm_tokenizer_patch", "intentId": "08fa4e65b3e24277bd4e6ece634f1010", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337071+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902158+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2c0bdf7fa3334d2e81647f4ab3e330be", "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": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337068+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902118+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ac6d960d199e45cea54d95d5ff36252a", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337065+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902078+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8016709760834f878714e8b1261ea15c", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337062+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.902038+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d9ef0005a582465fb29d4185c0f3b382", "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": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337059+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901996+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d9720955cefa4be99631b865e19632a7", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337056+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901953+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3e68e483ed784ea797668c6f87c0dbdb", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337053+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901903+00:00", "framework": "vllm", "intentId": "cab26704dbaf4f13bb40dfb19e660cec", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337050+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901851+00:00", "framework": "vllm", "intentId": "d7da673ed48442919b786bedc9ad1afc", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337047+00:00", "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901799+00:00", "framework": "vllm-mlu", "intentId": "e353966edf5e439c9a17e9e79eb68b96", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337044+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901746+00:00", "framework": "vllm-mlu", "intentId": "70f8a6348edd410ca8491ebb341261b6", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337041+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901693+00:00", "framework": "vllm-mlu", "intentId": "320214167d5e48f2ba79162fa9996915", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337038+00:00", "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901629+00:00", "framework": "vllm-mlu", "intentId": "44ba954dd43e47dc88a129b8397413ed", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337035+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901571+00:00", "framework": "vllm-mlu", "intentId": "01a049abe8b241b091eab320182370c6", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337026+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901513+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c47ea83734b5464ebb691c8af83e5ce7", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948173+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735716+00:00", "framework": "vllm", "intentId": "c2e64998f23a40b4b5d5bdfc07284f0d", "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": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948170+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735654+00:00", "framework": "vllm", "intentId": "bfb716a2925645b59cdac51aed06c793", "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": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948167+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735597+00:00", "framework": "vllm", "intentId": "b433c64d8fc840f1b2f808089748adc5", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948165+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735539+00:00", "framework": "vllm", "intentId": "a5c2c69c606d49469516d523855ba332", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948162+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735480+00:00", "framework": "vllm", "intentId": "89024e2935eb49f28db157fc87733e39", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948157+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735371+00:00", "framework": "vllm", "intentId": "c4c6c7e95ccc4dc987b14b37d335f62e", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948151+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735271+00:00", "framework": "vllm", "intentId": "d3464dc72d7d40d691d557a2c572fd46", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948148+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735221+00:00", "framework": "vllm", "intentId": "34db647ca5b947c297a394de90990190", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948145+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735169+00:00", "framework": "vllm", "intentId": "4a1003abe0b140a3a40cd51bda486a61", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948142+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735118+00:00", "framework": "vllm", "intentId": "a0d8475aacd04c36b41d76c9c78344f3", "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": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948139+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735061+00:00", "framework": "vllm", "intentId": "65d03d32af1441f7bdd1e8892503137d", "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": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948136+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.735003+00:00", "framework": "vllm", "intentId": "5bc7d38c97ff48d1896819dbea1c17a4", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948133+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734944+00:00", "framework": "vllm", "intentId": "a6ffe502193f4b468eb3caa01df820b4", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948130+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734885+00:00", "framework": "vllm-customized", "intentId": "8ffe301ef3c449c88a211f2b1359a145", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948127+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734828+00:00", "framework": "vllm-customized", "intentId": "1483d4b84367440d857f6451eb2cc37b", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948124+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734771+00:00", "framework": "vllm-customized", "intentId": "966949fcd36d437da950612dfe5bcb24", "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": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948122+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734713+00:00", "framework": "vllm-customized", "intentId": "44062a9c914649d69166d12f817bd507", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948111+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734474+00:00", "framework": "vllm-customized", "intentId": "1b1f38f2397142869fa23f15381c3c40", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948108+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734416+00:00", "framework": "vllm-customized", "intentId": "32ccfea699d3494fa642239bdb77ecc4", "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": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948106+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734358+00:00", "framework": "vllm-customized", "intentId": "6902f212ee344ff4936749a994f07241", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948100+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734242+00:00", "framework": "vllm-customized", "intentId": "8c2eb68162ae43d784cbbf01fa0405cb", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948097+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734184+00:00", "framework": "vllm-customized", "intentId": "a1338711ed8446f3a89eb48740a2c77e", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948094+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734125+00:00", "framework": "vllm-customized", "intentId": "66d9a6d03afe4f78876c4c9bfa5e72ac", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948091+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734067+00:00", "framework": "vllm-customized", "intentId": "154047c6f071444bbe1cb8fbcd7c4f72", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948088+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.734009+00:00", "framework": "vllm-customized", "intentId": "4f8dcb61e2ee41c2a1e8d107530fb9d0", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948085+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.733944+00:00", "framework": "vllm-customized", "intentId": "6b4288e0f4d74733a21f9ea046395309", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948082+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.733884+00:00", "framework": "vllm-customized", "intentId": "b12809f195bc4e828bfb60e3132c4565", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948079+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.733825+00:00", "framework": "vllm-customized", "intentId": "e441506f8aa94f3884582d512efc8b36", "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": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948075+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.733764+00:00", "framework": "vllm-customized", "intentId": "ffe144f8cfc34779802008a7f79c32db", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948071+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.733700+00:00", "framework": "vllm-customized", "intentId": "fead8c430d3e482d93152339e197a099", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f1d22b7d76084321a5e6a45d08bf0104", "completedAt": "2026-09-21T08:42:21.948045+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:36:59.733544+00:00", "framework": "vllm-customized", "intentId": "e0ce4f0b7fa44270b5b0a5c482102caa", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914093+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344333+00:00", "framework": "vllm-customized", "intentId": "6361228927444e939da28960c5f8f929", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914090+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344276+00:00", "framework": "vllm-customized", "intentId": "5a5dbc3f15524ec5a1078de10692df88", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914086+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344219+00:00", "framework": "vllm-customized", "intentId": "3c985f6f5d6a41dba83c9b4291b30e6f", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914084+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344161+00:00", "framework": "vllm-customized", "intentId": "aa7b8f907336466a87d56ebcb5548e69", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914081+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344103+00:00", "framework": "vllm-customized", "intentId": "17777273175d453fb4b3763ecc109c4f", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 024112d9a5..5fac70dd39 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,14 +1,14 @@ { "acceptedByCategory": { - "unified_success_first": 2170 + "unified_success_first": 2175 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|vllm": 38, - "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 147, + "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 149, "text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|vllm": 26, - "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 139, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 140, "text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm_fix_tokenizer": 121, "text-generation|Cambricon_mlu-370-x4|vllm": 69, @@ -36,10 +36,10 @@ "text-generation|Vastai_va16|vllm_fix_tokenizer": 74, "text-generation|hygon_k100-ai|llamacpp": 18, "text-generation|hygon_k100-ai|vllm": 26, - "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 123 + "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 125 }, - "acceptedSinceRefresh": 2170, - "acceptedTotal": 2170, - "generatedAt": "2026-09-21T09:33:26.709127+00:00", + "acceptedSinceRefresh": 2175, + "acceptedTotal": 2175, + "generatedAt": "2026-09-21T09:49:02.394241+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 52eadabbfd..3cb4a25732 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1175,3 +1175,8 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T20:09:24.405809+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986872", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T20:09:24.421834+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "submitTime": "2026-09-21T09:40:34.489077+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4998299", "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/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "submitTime": "2026-09-21T09:40:34.490655+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998300", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-21T09:41:35.705044+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998344", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "modelId": "neuralmagic/starcoder2-7b-FP8", "submitTime": "2026-09-21T09:45:53.481324+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998407", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} +{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-21T09:46:02.415434+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998415", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} diff --git a/manifest.json b/manifest.json index 783ee25f5e..518e6007be 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "f4afc5dbbf57b883780778e798518d72ad1770b7d52c2f9efa7ac7bca07813f7", ".modelhub_state/recent_outcomes.jsonl": "efd6e3cd49c106ba9dc65fb589a1629fb65ac06f4e5341884266acb60ac03834", ".modelhub_state/recovery_active_tasks.jsonl": "437aed2c8dbd4884a6c7f940f398a37ca81aa5030bd6bf6791e4f76b3fc9f145", - ".modelhub_state/recovery_intents.jsonl": "e1c82e9934604c2ee63f4faa63c8447b74df569443dd197de0c6fc59bf660361", - ".modelhub_state/routing_intelligence.json": "bec656a99e764925ebff726424dad3b193d19a1c10495049e2ab53aba1fec024", + ".modelhub_state/recovery_intents.jsonl": "7b91ee5d44d57d3a040f1f2c41cef440434802c3311bff132d43d5dc4f1c6ce4", + ".modelhub_state/routing_intelligence.json": "e8c0ab8a0870e0236e92f5f80d1711ea41212d1f9e13e28672c2eee322454bab", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "b3c091e51ac1d46d6316f33c8cb1052a8279abf93cc9d1ba669740ad8103d43a", - "outcomes/submissions.jsonl": "c2e4f8f766e09a287669a3183bffc2b21f90605209e3d4877aab1974e91fd59f" + "ledger/submissions.jsonl": "f672783e2a67fea6834dfa6a2d6f6891126f8ad6768e927ebc6f3358015d79fc", + "outcomes/submissions.jsonl": "5bdcd16a2121282e5f530aef409a1cc2cfa66fcb2e467449aac4e6c6da85f727" }, - "generation": 11371, - "phase": "intent", + "generation": 11372, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T09:40:25.555330+00:00", + "updatedAt": "2026-09-21T09:49:02.612876+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 1524a34536..dd64c17afc 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1129,3 +1129,8 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231252716, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233101396, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T08:44:09.587569+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233101396}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:19:32.876555+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997864", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-21T09:19:32.868721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997865", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:33:26.659264+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4998167", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1048871402, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1048871402}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:40:34.489077+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4998299", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013064, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197403, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197403}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:40:34.490655+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998300", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615358}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:41:35.705044+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998344", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858541078}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:45:53.481324+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998407", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "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": 7860673858}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:46:02.415434+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998415", "taskType": "text-generation", "verifyResult": null}