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

state: generation 11336 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 08:36:59 +00:00
parent 5b676b28bd
commit a88492d5a8
5 changed files with 86 additions and 122 deletions
Download Patch File Download Diff File Expand all files Collapse all files

164
.modelhub_state/recovery_intents.jsonl
View File

@@ -2003,63 +2003,63 @@
{"batchId": "94fa65280ebc4ffe87b819cfb4433489", "completedAt": "2026-09-21T08:17:20.360601+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:17:10.101584+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ae64386f6ca48c38accae5cd676d52c", "lastModified": "2026-09-17T15:15:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-21T08:22:13.016425+00:00", "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4996859", "taskType": "text-generation"}
{"batchId": "94fa65280ebc4ffe87b819cfb4433489", "completedAt": "2026-09-21T08:17:20.360620+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:17:10.101734+00:00", "framework": "vllm", "intentId": "14a017ca764f4d31a47c1b218150d2fb", "lastModified": "2026-09-17T13:06:10+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "reason": null, "reconciledAt": "2026-09-21T08:22:13.016153+00:00", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4996858", "taskType": "text-generation"}
{"batchId": "94fa65280ebc4ffe87b819cfb4433489", "completedAt": "2026-09-21T08:17:20.360624+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:17:10.101799+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1819d015d79041a98b8592001f18c384", "lastModified": "2026-09-21T01:31:41+00:00", "modelAddress": "https://modelscope.cn/models/blue2star/Qwen-Image-2.1-PE-T2I-ComfyUI", "reason": null, "reconciledAt": "2026-09-21T08:22:13.019512+00:00", "repoId": "blue2star/Qwen-Image-2.1-PE-T2I-ComfyUI", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4996857", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341582+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4ecceef8c3e34e69b5633c14fd76e0d6", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341718+00:00", "framework": "vllm_tokenizer_patch", "intentId": "35a96e7094bc4b2ab305fa4795c8326e", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341772+00:00", "framework": "vllm", "intentId": "285e69eaf8da4d1fa03807805fd02a33", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341822+00:00", "framework": "vllm", "intentId": "d68a85d02d64402f97de86717c422232", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341871+00:00", "framework": "vllm", "intentId": "aef435d05a004cc495a1e661cc56a4f9", "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": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341919+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d7fe2a4d519a43b7a87e57f06ed6c672", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341960+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cee162f9da1e4e5c95e343a65fc35a18", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341999+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cd499973f8c14a04bb930a55709b7b05", "lastModified": "2026-08-24T18:15:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342037+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ec983485c729450196906ea0bd55c7b9", "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": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342074+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b5c8312512a44121b2bab7b1eb657a99", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342112+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d6f012237fc44b4ca50964d7564ce9c2", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342151+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c325c22a7b5243718e5b4802060b4a78", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342188+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a865966dac654e718af93b88021a317d", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342226+00:00", "framework": "vllm_tokenizer_patch", "intentId": "119fadf5a18f49219be7591c4ab05efe", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342264+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1e2f4ae26340433ba848c828a32c8037", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8a9d6c4b42ec4fbabc1451982b668aa0", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342339+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd21d9669f0344bf92bfba43f2718fea", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342376+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e4bd52679b1548b983ed291e9a6bd3d7", "lastModified": "2026-08-24T19:08:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342414+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9a25b374aa534e66b5814c8cbc3d9944", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342451+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c19c291c800b4cab8cd93cae146073cd", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342489+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b63bc3a1f1d24842bb163e1ffdbf2780", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342527+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1155224ce24c4c9588168a7dadcdd978", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342565+00:00", "framework": "vllm", "intentId": "bde149fbc27343698ea399f18b1d5292", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342625+00:00", "framework": "vllm", "intentId": "28f5efe1a3824e05ba64c037f54e78df", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342688+00:00", "framework": "vllm", "intentId": "9a32c56e1ccd427f9b5449323760dcd5", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342745+00:00", "framework": "vllm", "intentId": "8a389d95d3294278ad2fc527e21619ec", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342802+00:00", "framework": "vllm", "intentId": "acd79326fcd44084bc5b9a5f04fa9602", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342859+00:00", "framework": "vllm", "intentId": "2872bffdedf5407e8ca379ee586510d2", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342916+00:00", "framework": "vllm", "intentId": "76ed48a71a5c42849406786189b71738", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342972+00:00", "framework": "vllm", "intentId": "ba014286cc784b99b5a7a8eaaf4c1a58", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343029+00:00", "framework": "vllm", "intentId": "be4c50873a504559badea171353a2aff", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343086+00:00", "framework": "vllm", "intentId": "733b3874eef84ec891d1efc803f20359", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343142+00:00", "framework": "vllm", "intentId": "a19a92ee848e408e9a96946470b5428c", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343200+00:00", "framework": "vllm", "intentId": "a438a711d43f492e81dd6b2f21448e6b", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343256+00:00", "framework": "vllm", "intentId": "c56ab15797944ffc876085d5c001e0ec", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343314+00:00", "framework": "vllm", "intentId": "009b98968a364eb89d04269af6378068", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343371+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4163cad4e0fa40d5898ae5199def7ac3", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "20cdbe73f7054e7699a7e97c2ef51820", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343459+00:00", "framework": "vllm", "intentId": "1a933c3a0ee047c193356e652c151e56", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343508+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7f90348806264016a67ae33ddc5346de", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343551+00:00", "framework": "vllm-patch-tokenizer", "intentId": "59aea16fe95a404287465515a9cde451", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343595+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e257e711259c4b21ab73fb9634c853ba", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343637+00:00", "framework": "vllm-patch-tokenizer", "intentId": "681273e1ad22435fa576d4c6dcc9e3e0", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343689+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5a56d2657e0d40db934210336d750a4a", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343731+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9037e7ff7e9b4e05abf4ad7401dfbaaa", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343774+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b932617a80f9453a888ce97be73f89c4", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343815+00:00", "framework": "vllm-patch-tokenizer", "intentId": "23d4dc98d3f34c06bcab5a1d43c7e0cc", "lastModified": "2026-08-24T19:20:59+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343858+00:00", "framework": "vllm-patch-tokenizer", "intentId": "36a7c5f66b9e42e1bee3d5d4ebb8aac5", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343900+00:00", "framework": "vllm", "intentId": "a55b2474f6e24cc99d53517cfc430255", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343949+00:00", "framework": "vllm", "intentId": "0a3522ffa8c04cbb9e4ac978a1138911", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343996+00:00", "framework": "vllm", "intentId": "9cbf4d8fb2df4c1eb256ac2cc6535a25", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344043+00:00", "framework": "vllm-customized", "intentId": "04f06cc5707a4f009b8f8a0e1550e4b7", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344103+00:00", "framework": "vllm-customized", "intentId": "17777273175d453fb4b3763ecc109c4f", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344161+00:00", "framework": "vllm-customized", "intentId": "aa7b8f907336466a87d56ebcb5548e69", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344219+00:00", "framework": "vllm-customized", "intentId": "3c985f6f5d6a41dba83c9b4291b30e6f", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344276+00:00", "framework": "vllm-customized", "intentId": "5a5dbc3f15524ec5a1078de10692df88", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344333+00:00", "framework": "vllm-customized", "intentId": "6361228927444e939da28960c5f8f929", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913930+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341871+00:00", "framework": "vllm", "intentId": "aef435d05a004cc495a1e661cc56a4f9", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4997055", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913937+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341960+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cee162f9da1e4e5c95e343a65fc35a18", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4997054", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913940+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341999+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cd499973f8c14a04bb930a55709b7b05", "lastModified": "2026-08-24T18:15:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "reason": null, "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4997053", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913972+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342376+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e4bd52679b1548b983ed291e9a6bd3d7", "lastModified": "2026-08-24T19:08:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4997092", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914009+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342972+00:00", "framework": "vllm", "intentId": "ba014286cc784b99b5a7a8eaaf4c1a58", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "reason": null, "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4997093", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914064+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343815+00:00", "framework": "vllm-patch-tokenizer", "intentId": "23d4dc98d3f34c06bcab5a1d43c7e0cc", "lastModified": "2026-08-24T19:20:59+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a8", "reason": null, "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4997188", "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914067+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343858+00:00", "framework": "vllm-patch-tokenizer", "intentId": "36a7c5f66b9e42e1bee3d5d4ebb8aac5", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "reason": null, "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4997190", "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"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914078+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.344043+00:00", "framework": "vllm-customized", "intentId": "04f06cc5707a4f009b8f8a0e1550e4b7", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914075+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343996+00:00", "framework": "vllm", "intentId": "9cbf4d8fb2df4c1eb256ac2cc6535a25", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914072+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343949+00:00", "framework": "vllm", "intentId": "0a3522ffa8c04cbb9e4ac978a1138911", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914069+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343900+00:00", "framework": "vllm", "intentId": "a55b2474f6e24cc99d53517cfc430255", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914061+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343774+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b932617a80f9453a888ce97be73f89c4", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914058+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343731+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9037e7ff7e9b4e05abf4ad7401dfbaaa", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914055+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343689+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5a56d2657e0d40db934210336d750a4a", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914052+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343637+00:00", "framework": "vllm-patch-tokenizer", "intentId": "681273e1ad22435fa576d4c6dcc9e3e0", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914049+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343595+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e257e711259c4b21ab73fb9634c853ba", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914045+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343551+00:00", "framework": "vllm-patch-tokenizer", "intentId": "59aea16fe95a404287465515a9cde451", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914043+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343508+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7f90348806264016a67ae33ddc5346de", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914040+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343459+00:00", "framework": "vllm", "intentId": "1a933c3a0ee047c193356e652c151e56", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914036+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "20cdbe73f7054e7699a7e97c2ef51820", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914033+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343371+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4163cad4e0fa40d5898ae5199def7ac3", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914030+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343314+00:00", "framework": "vllm", "intentId": "009b98968a364eb89d04269af6378068", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914026+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343256+00:00", "framework": "vllm", "intentId": "c56ab15797944ffc876085d5c001e0ec", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914023+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343200+00:00", "framework": "vllm", "intentId": "a438a711d43f492e81dd6b2f21448e6b", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914020+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343142+00:00", "framework": "vllm", "intentId": "a19a92ee848e408e9a96946470b5428c", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914016+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343086+00:00", "framework": "vllm", "intentId": "733b3874eef84ec891d1efc803f20359", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914013+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.343029+00:00", "framework": "vllm", "intentId": "be4c50873a504559badea171353a2aff", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914006+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342916+00:00", "framework": "vllm", "intentId": "76ed48a71a5c42849406786189b71738", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914003+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342859+00:00", "framework": "vllm", "intentId": "2872bffdedf5407e8ca379ee586510d2", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.914000+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342802+00:00", "framework": "vllm", "intentId": "acd79326fcd44084bc5b9a5f04fa9602", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913997+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342745+00:00", "framework": "vllm", "intentId": "8a389d95d3294278ad2fc527e21619ec", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913994+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342688+00:00", "framework": "vllm", "intentId": "9a32c56e1ccd427f9b5449323760dcd5", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913991+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342625+00:00", "framework": "vllm", "intentId": "28f5efe1a3824e05ba64c037f54e78df", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913987+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342565+00:00", "framework": "vllm", "intentId": "bde149fbc27343698ea399f18b1d5292", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913984+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342527+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1155224ce24c4c9588168a7dadcdd978", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913981+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342489+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b63bc3a1f1d24842bb163e1ffdbf2780", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913978+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342451+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c19c291c800b4cab8cd93cae146073cd", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913975+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342414+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9a25b374aa534e66b5814c8cbc3d9944", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913970+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342339+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd21d9669f0344bf92bfba43f2718fea", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913966+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8a9d6c4b42ec4fbabc1451982b668aa0", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913963+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342264+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1e2f4ae26340433ba848c828a32c8037", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913960+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342226+00:00", "framework": "vllm_tokenizer_patch", "intentId": "119fadf5a18f49219be7591c4ab05efe", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913957+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342188+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a865966dac654e718af93b88021a317d", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913953+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342151+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c325c22a7b5243718e5b4802060b4a78", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913950+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342112+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d6f012237fc44b4ca50964d7564ce9c2", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913946+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342074+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b5c8312512a44121b2bab7b1eb657a99", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913943+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.342037+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ec983485c729450196906ea0bd55c7b9", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913933+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341919+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d7fe2a4d519a43b7a87e57f06ed6c672", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913926+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341822+00:00", "framework": "vllm", "intentId": "d68a85d02d64402f97de86717c422232", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913922+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341772+00:00", "framework": "vllm", "intentId": "285e69eaf8da4d1fa03807805fd02a33", "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": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913917+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341718+00:00", "framework": "vllm_tokenizer_patch", "intentId": "35a96e7094bc4b2ab305fa4795c8326e", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "53c59e9635fa4b4abb2faa302ec48e2b", "completedAt": "2026-09-21T08:36:58.913894+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:29:14.341582+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4ecceef8c3e34e69b5633c14fd76e0d6", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466082+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127288+00:00", "framework": "vllm", "intentId": "65cef4d446084037bb13153d52b7c872", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466079+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127231+00:00", "framework": "vllm", "intentId": "a7743eff51694235ba4577c5edb0a5c8", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466076+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127174+00:00", "framework": "vllm", "intentId": "d8aff6a5552345c6aabfa8a2186a5135", "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"}
@@ -2310,53 +2310,3 @@
{"batchId": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383360+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304737+00:00", "framework": "vllm-customized", "intentId": "32e536eeafb840a9a4af556fbe43ae44", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383357+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304647+00:00", "framework": "vllm-customized", "intentId": "da4a1fbb84284bf7b3c10516d1565ff2", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383354+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304589+00:00", "framework": "vllm-customized", "intentId": "5125f3e23a6c4506b552e415df7bd41d", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383351+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304531+00:00", "framework": "vllm-customized", "intentId": "a26b64a9f8e74b358a4c131d2c275049", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383348+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304464+00:00", "framework": "vllm-customized", "intentId": "50a83ae8b98b41e5984d50d5586f229c", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383345+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304399+00:00", "framework": "vllm-customized", "intentId": "f5108138f6d840978565a5ffa9476857", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383342+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304340+00:00", "framework": "vllm-customized", "intentId": "ee319504f1374c5b88c8a53b6ceece5b", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383339+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304260+00:00", "framework": "vllm-customized", "intentId": "6af12f102d28497da7db80b708b079f4", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383337+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304201+00:00", "framework": "vllm-customized", "intentId": "d8165cee646c4338b85c4070f977922c", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383334+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304154+00:00", "framework": "vllm", "intentId": "9d070f7f0d3e4d35a5935f852d7515a6", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383331+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304106+00:00", "framework": "vllm", "intentId": "9fd392cbb7f54590a2045ef2f2e26dd3", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383329+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304059+00:00", "framework": "vllm", "intentId": "78c8db397a844ece82e1750095cfa675", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383326+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.304009+00:00", "framework": "vllm", "intentId": "34f2a7f444a9445481b72fe733d22c6f", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383323+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303966+00:00", "framework": "vllm_fix_tokenizer", "intentId": "57ba7a1beda6453bb98a700ae3d3711e", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383320+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303923+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c32f784212d14d9aae697fa7844548b1", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383317+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303866+00:00", "framework": "vllm", "intentId": "307ba76b426c4ef6b3937b6721908790", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383314+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303808+00:00", "framework": "vllm", "intentId": "fc379c78e37b446095b129f5c72c206c", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383308+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303690+00:00", "framework": "vllm", "intentId": "337d15dacfde4bd8989172b0e62c0411", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383306+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303632+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7cd622d588aa4dcb93bba296d40c1274", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383303+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303579+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c677854ebf924525acd805ac7b8863a1", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383300+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303519+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c7d9e532157546889a05410c6cca7a8d", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383297+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303482+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3e4af9a09a5b42e5b959823d91c1eb99", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383294+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303445+00:00", "framework": "vllm_tokenizer_patch", "intentId": "51ef32c1becb4a2c9dcd1155f44fd524", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383291+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303407+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1f6b41509834410c88f02a5c210ffc94", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383288+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303369+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2ce879288a974a6a9eb81752e73b4dda", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383285+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303331+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7d555c1cb199493fac2af45f713ce96e", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383282+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303293+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da8b78a397cc489198e4ec10b0a8fa5f", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383279+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303255+00:00", "framework": "vllm_tokenizer_patch", "intentId": "21cb47a019884faf892d6f1d9f473e9e", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383275+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303202+00:00", "framework": "vllm_tokenizer_patch", "intentId": "751102b7f6034acfa0e9f3c8276742c8", "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": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383268+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.303099+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6ab267401a2e4fa3b4bccea1fd06f542", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "58be078557ce418fa185f1fb58e21e3e", "completedAt": "2026-09-21T06:57:34.383252+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:49:04.302985+00:00", "framework": "vllm", "intentId": "f106a935e3844338854dd1b6b2c8818c", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "da43ceee19dc4776988b8624394fec0f", "completedAt": "2026-09-21T06:38:59.010213+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:38:49.970340+00:00", "framework": "vllm-customized", "intentId": "c20d857e32e2470e88ae4ea63c1bf3ae", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115452+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.480250+00:00", "framework": "vllm", "intentId": "9ffab013056041aa9b5eef668a30fee7", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115449+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.480201+00:00", "framework": "vllm", "intentId": "4c68de9a884243749fc37788ab72611a", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115447+00:00", "configFingerprint": "5227b42f4cdd7539bb62412569c7d9c8b3cc2e321cdbac3654c73c95c5bc8a7b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.480151+00:00", "framework": "vllm", "intentId": "683ea516ed5b4314857a145882067423", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115443+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.480101+00:00", "framework": "vllm", "intentId": "c7e7db46bc3c447ab34e24f3e6a807f4", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115440+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.480051+00:00", "framework": "vllm", "intentId": "5de2a033e0714e16842e0ffc865d1556", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115438+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.480001+00:00", "framework": "vllm", "intentId": "bc0739a0b043426e9be11ed08e74a249", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115435+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479950+00:00", "framework": "vllm", "intentId": "2af1410d89bb430baf2121ddbbf1db8a", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115432+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479891+00:00", "framework": "vllm", "intentId": "81c2c3ed2d3e41318f2d6d441edf2440", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115429+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479832+00:00", "framework": "vllm-customized", "intentId": "fe6b00b2714d493bb5fb118b93fa4c9e", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115426+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479774+00:00", "framework": "vllm-customized", "intentId": "dba6342a4aea4f8c8a57ca630e83bcf4", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115423+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479716+00:00", "framework": "vllm-customized", "intentId": "27563cf0ca7e4d63ad817927794fbea8", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115420+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479638+00:00", "framework": "vllm-customized", "intentId": "1852a1b6223644209680b17d5543c0f7", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115417+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479580+00:00", "framework": "vllm-customized", "intentId": "a65e50b7ff8e4dc28228de197256b0a7", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115414+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479522+00:00", "framework": "vllm-customized", "intentId": "b7d2fe6ebd0f43ad9f3acc58d0bdffa0", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115411+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479465+00:00", "framework": "vllm-customized", "intentId": "20aaf1d3d5f64f7ab621980cc3d95f2d", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115408+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479407+00:00", "framework": "vllm-customized", "intentId": "caf23f4ce69941fcb2ded6f50feb1955", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115404+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479349+00:00", "framework": "vllm-customized", "intentId": "95707883043d469badcd22a0d02386cb", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115402+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479291+00:00", "framework": "vllm-customized", "intentId": "ba51927f421444379a52f8ead565c163", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115399+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479234+00:00", "framework": "vllm-customized", "intentId": "d7a41a1589bb4febbf62ddc47f3359f1", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115395+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479176+00:00", "framework": "vllm-customized", "intentId": "fce3333016464023b3c142c2d8c39271", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115393+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479118+00:00", "framework": "vllm-customized", "intentId": "422d6121868946509a5debc4e6078f90", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}

16
.modelhub_state/routing_intelligence.json
View File

@@ -1,11 +1,11 @@
{
"acceptedByCategory": {
"unified_success_first": 2142
"unified_success_first": 2149
},
"acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17,
"text-generation|Ascend_910-b3|vllm": 36,
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 143,
"text-generation|Ascend_910-b3|vllm": 37,
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 146,
"text-generation|Ascend_910-b4|llamacpp": 13,
"text-generation|Ascend_910-b4|vllm": 23,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 137,
@@ -25,7 +25,7 @@
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 40,
"text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 3,
"text-generation|Iluvatar_mrv-100|vllm": 62,
"text-generation|Kunlunxin_p-800|vllm": 47,
"text-generation|Kunlunxin_p-800|vllm": 48,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 181,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 76,
"text-generation|MetaX_c-500|vllm": 104,
@@ -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": 120
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 122
},
"acceptedSinceRefresh": 2142,
"acceptedTotal": 2142,
"generatedAt": "2026-09-21T08:17:20.299391+00:00",
"acceptedSinceRefresh": 2149,
"acceptedTotal": 2149,
"generatedAt": "2026-09-21T08:36:58.848646+00:00",
"version": 1
}

7
ledger/submissions.jsonl
View File

@@ -1165,3 +1165,10 @@
{"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", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "submitTime": "2026-09-21T08:29:25.977872+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997055", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "submitTime": "2026-09-21T08:29:25.981023+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997054", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "submitTime": "2026-09-21T08:29:25.979829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997053", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "submitTime": "2026-09-21T08:29:48.235778+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997092", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-21T08:31:34.413070+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997093", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a8", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "submitTime": "2026-09-21T08:33:50.394331+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997188", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "submitTime": "2026-09-21T08:33:57.835795+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997190", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}

14
manifest.json
View File

@@ -10,16 +10,16 @@
".modelhub_state/queue_cleanup_latest.json": "f4afc5dbbf57b883780778e798518d72ad1770b7d52c2f9efa7ac7bca07813f7",
".modelhub_state/recent_outcomes.jsonl": "192c324383a5677c649ff5959d4c94833cadd97e64612ac0cbb69a2d1c720104",
".modelhub_state/recovery_active_tasks.jsonl": "63aaf1dab275a6a6144cec167deac14d5324368c393d71dd9d4c1b840dc52802",
".modelhub_state/recovery_intents.jsonl": "dbd4eb203fa77c94ac47e7a1b458ba00d8073b9d87815989fdcddd7b9373bf57",
".modelhub_state/routing_intelligence.json": "9cd6cab068960be9aa13a5d32b2c8fbec6d281eaae88659f6893211c5b0f0a7d",
".modelhub_state/recovery_intents.jsonl": "a018bd4cef2918f9fb3c7dd04189819d84c8fb7ecc2ab165334bc77bac86faa2",
".modelhub_state/routing_intelligence.json": "ff99ddcba7a0ca5fcf718fa7cd285eb27a5e1f2911edc2727c1b41e8e9359922",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "91484b32049219522f891ed5b4a3e5d3d956a2a1c56261fc229f28c270f267be",
"outcomes/submissions.jsonl": "0151e4ee48024c1bb2b9540671c4d1976cc67bd4e093452dbf93ddba5a8b9c71"
"ledger/submissions.jsonl": "d625e6514b40ddaa76781c2d04c85e7357d5944950405b0971e6b398a662e9c0",
"outcomes/submissions.jsonl": "89075fa6013244144d8ba3da1a51508977139cc654fd0b490675fa494884c418"
},
"generation": 11335,
"phase": "intent",
"generation": 11336,
"phase": "result",
"schemaVersion": 1,
"updatedAt": "2026-09-21T08:29:14.490172+00:00",
"updatedAt": "2026-09-21T08:36:59.054353+00:00",
"writerId": "8b35139af6674067a339a670222d4b67"
}

7
outcomes/submissions.jsonl
View File

@@ -1118,3 +1118,10 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:17:20.243727+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4996859", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952488643, "estimatedRequiredGiB": 33.497, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29972714678, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29972714678}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:17:20.220538+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4996858", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "blue2star/Qwen-Image-2.1-PE-T2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29326950127, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:text-to-image"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326950127}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:17:20.209866+00:00", "targetGpu": "Biren_166m", "taskId": "4996857", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:29:25.977872+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997055", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "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": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:29:25.981023+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997054", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "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": 9093197700, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197700}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:29:25.979829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997053", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13594088584, "estimatedRequiredGiB": 15.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 13603621925, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12247782400, "modelscopeTags": ["license:apache-2.0", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 13603621925}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:29:48.235778+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997092", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:31:34.413070+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997093", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499021, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020499021}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:33:50.394331+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997188", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:33:57.835795+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997190", "taskType": "text-generation", "verifyResult": null}