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

state: generation 11578 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 17:36:56 +00:00
parent 181c23a16b
commit c1b54b71d5
5 changed files with 109 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

185
.modelhub_state/recovery_intents.jsonl
View File

@@ -2162,72 +2162,72 @@
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427653+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706511+00:00", "framework": "vllm", "intentId": "a946c4d8d67145c2a4bf8e3112cb4e8e", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "reason": null, "reconciledAt": "2026-09-21T17:22:43.866884+00:00", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427653+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706511+00:00", "framework": "vllm", "intentId": "a946c4d8d67145c2a4bf8e3112cb4e8e", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "reason": null, "reconciledAt": "2026-09-21T17:22:43.866884+00:00", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation"}
{"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427655+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706557+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1408ca1d3cfa42449273b93f7c7042c8", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T17:22:43.867317+00:00", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427655+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706557+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1408ca1d3cfa42449273b93f7c7042c8", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T17:22:43.867317+00:00", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281128+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498117+00:00", "framework": "vllm-customized", "intentId": "0ecdca2c3c0a4e598c587f4861545643", "lastModified": "2026-08-24T18:50:21+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T17:22:43.868219+00:00", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation"} {"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281128+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498117+00:00", "framework": "vllm-customized", "intentId": "0ecdca2c3c0a4e598c587f4861545643", "lastModified": "2026-08-24T18:50:21+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T17:22:43.868219+00:00", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.059897+00:00", "framework": "vllm_tokenizer_patch", "intentId": "feeb5ccb64374d9dbe4987f4113c222c", "lastModified": "2026-08-24T16:17:12+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959774+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.059897+00:00", "framework": "vllm_tokenizer_patch", "intentId": "feeb5ccb64374d9dbe4987f4113c222c", "lastModified": "2026-08-24T16:17:12+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5004733", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060026+00:00", "framework": "vllm_tokenizer_patch", "intentId": "83386a7918154a97ac31c2c1664c16af", "lastModified": "2026-08-24T16:38:03+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959797+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060080+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8d4e1bb85f094cc9b309213cc72f89ce", "lastModified": "2026-08-24T17:41:35+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "reason": null, "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5004731", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060080+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8d4e1bb85f094cc9b309213cc72f89ce", "lastModified": "2026-08-24T17:41:35+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959801+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060130+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1a49349fd4694eff8be7bf367717f0f2", "lastModified": "2026-08-24T17:18:07+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "reason": null, "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5004732", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060130+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1a49349fd4694eff8be7bf367717f0f2", "lastModified": "2026-08-24T17:18:07+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959805+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060179+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fca72785bcbf45a0b47ba070dfe38cfb", "lastModified": "2026-08-24T16:01:21+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-group128-v2", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5004736", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060179+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fca72785bcbf45a0b47ba070dfe38cfb", "lastModified": "2026-08-24T16:01:21+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-group128-v2", "repoId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959813+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060278+00:00", "framework": "vllm_tokenizer_patch", "intentId": "032e266c7f884028b17c18124737a493", "lastModified": "2026-08-24T17:49:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "reason": null, "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5004737", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060229+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1ab0dcb3e7d246459f328c8a605cb38f", "lastModified": "2026-08-24T16:10:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-channel-v2", "repoId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959825+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060431+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9f86e3cb2abd49c9b72e878a10943b25", "lastModified": "2026-08-24T17:53:32+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "reason": null, "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5004738", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060278+00:00", "framework": "vllm_tokenizer_patch", "intentId": "032e266c7f884028b17c18124737a493", "lastModified": "2026-08-24T17:49:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959829+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060479+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc2e5cb3b78947e988ea847b3fea2068", "lastModified": "2026-09-21T17:22:45+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Agents-A1", "reason": null, "repoId": "InternScience/Agents-A1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5004735", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060327+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c3b7b7527eca4c8bb96e2933f6572e77", "lastModified": "2026-08-24T17:35:14+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959833+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060523+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2b406390f3564fc29a1875cb082c7778", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "reason": null, "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "5004734", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060376+00:00", "framework": "vllm_tokenizer_patch", "intentId": "878589d3b3104a05930bd55fd661a05f", "lastModified": "2026-08-24T17:33:00+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959897+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061549+00:00", "framework": "vllm_fix_tokenizer", "intentId": "54d1cb7c2da14680821011e3d903a63f", "lastModified": "2026-09-21T15:48:16+00:00", "modelAddress": "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "reason": null, "repoId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "5004770", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060431+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9f86e3cb2abd49c9b72e878a10943b25", "lastModified": "2026-08-24T17:53:32+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959922+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061947+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31f699eb49254cd1a88c1015bf37a33c", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5004794", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060479+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc2e5cb3b78947e988ea847b3fea2068", "lastModified": "2026-09-21T17:22:45+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Agents-A1", "repoId": "InternScience/Agents-A1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959952+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062440+00:00", "framework": "transformers", "intentId": "390f17520fa04e948c38fab9b9cc8706", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "reason": null, "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5004804", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060523+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2b406390f3564fc29a1875cb082c7778", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959979+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063067+00:00", "framework": "transformers", "intentId": "b837f348c6c5472bb06ed470becc03d6", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5004817", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060563+00:00", "framework": "vllm_tokenizer_patch", "intentId": "691d1320a33b462ab882ba95dd0050fa", "lastModified": "2026-08-24T16:03:28+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "repoId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959982+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063127+00:00", "framework": "transformers", "intentId": "4200d03eb0bb4a2e84deaea7db024a05", "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": "Iluvatar_bi-150", "taskId": "5004818", "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060601+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2a6c31e568454e299a41cdc2133b38a6", "lastModified": "2026-08-24T17:02:50+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959987+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063249+00:00", "framework": "transformers", "intentId": "ef972c0363d84722a9b05476dbb0c5e7", "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": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a3e789ba339d4179aed4ae3206b1c264", "lastModified": "2026-08-24T16:35:49+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959984+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063188+00:00", "framework": "transformers", "intentId": "bca8f1e092bb4f3a8b6ad5be466065e4", "repoId": "RedHatAI/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": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060689+00:00", "framework": "vllm_tokenizer_patch", "intentId": "221499919944485291424a67a0c2255a", "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": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959976+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063007+00:00", "framework": "transformers", "intentId": "460b12da111a4b548ff03253d006bf64", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060727+00:00", "framework": "vllm_tokenizer_patch", "intentId": "30d27c6c77954b949d921414741a5ce3", "lastModified": "2026-08-24T16:40:22+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959973+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062946+00:00", "framework": "transformers", "intentId": "413d89991a214e138d2a403d7a6449bd", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060771+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ef1d4ec2d9d94d8794b3d022b9effca1", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959970+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062879+00:00", "framework": "transformers", "intentId": "767b894112024a2d8a24be8684bfc0eb", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060808+00:00", "framework": "vllm-mlu", "intentId": "d0519698a3cd495da5e06aa53eee8d78", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959968+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062818+00:00", "framework": "transformers", "intentId": "7c57603b1fef4f9288ec10c10f251222", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060875+00:00", "framework": "vllm-mlu", "intentId": "fbdb0d00c610455e8e2c7272a44e7749", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959965+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062757+00:00", "framework": "transformers", "intentId": "cf216303ad2d4b64bdf549031b1cdccd", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060937+00:00", "framework": "vllm-mlu", "intentId": "35df697bdc974a28a301921cd8b92879", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959962+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062696+00:00", "framework": "transformers", "intentId": "1a8af68d3c254c9987b1aecdbdc9fb09", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061000+00:00", "framework": "vllm-mlu", "intentId": "52bafd3ecd574c37b44710b533f54567", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959959+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062630+00:00", "framework": "transformers", "intentId": "61f427269b024f8aa9e6c83842d665c2", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061062+00:00", "framework": "vllm-mlu", "intentId": "581d0ce9a65f4a4982a5bc3805160fc8", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959956+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062562+00:00", "framework": "transformers", "intentId": "17440a9ecfb546feb86d2af2fc89ce8d", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061124+00:00", "framework": "vllm_tokenizer_patch", "intentId": "df108764bb6b48ee97d38958abda1e1c", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959954+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062501+00:00", "framework": "transformers", "intentId": "4bd54d2a7232473abf5a05ad83fc7042", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061173+00:00", "framework": "vllm_tokenizer_patch", "intentId": "11679ea11ac2462a9457e77fbb00fe3e", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959949+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062378+00:00", "framework": "transformers", "intentId": "ae51c1829a734b27878f288468a5355f", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061223+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d29fd19b4ebb42b28e5c41365bfa5303", "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": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959946+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062335+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04ac952ce4754aa9ae410eae73417d16", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061277+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6d95e03819d549c492daeb552f651d02", "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": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959943+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062286+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2b2b9809b0f4ac09b5cb16f264dd31c", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061326+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b02e3dafd1fa4cacad5a8a58b2aad56e", "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": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959941+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062243+00:00", "framework": "vllm_fix_tokenizer", "intentId": "43a69f8331b741328b2f7e918472c40f", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061374+00:00", "framework": "vllm_fix_tokenizer", "intentId": "69e1da04388848df909c8ac07297dcfd", "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": "Biren_166m", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959938+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062202+00:00", "framework": "vllm_fix_tokenizer", "intentId": "54e3a669496947578033df3a8019ebdb", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "78756e9e47584ae1992d0dfa075c9e93", "lastModified": "2026-08-24T18:06:52+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959935+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062159+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b48202aa3ca44e9e98f9b04bf31da48a", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061458+00:00", "framework": "vllm_fix_tokenizer", "intentId": "deb5f418aad74f3595e8056faba5afeb", "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": "Biren_166m", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959933+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062117+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a1ef3ffc801041a29229b0563036c63b", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061501+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a42f6a42fe7449c8bd5d7b7645635074", "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": "Biren_166m", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959930+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062075+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f063fcc323cf4f7abe54ea1c6ad52a2c", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061549+00:00", "framework": "vllm_fix_tokenizer", "intentId": "54d1cb7c2da14680821011e3d903a63f", "lastModified": "2026-09-21T15:48:16+00:00", "modelAddress": "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "repoId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959927+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062032+00:00", "framework": "vllm_fix_tokenizer", "intentId": "543da9d65cdf4547a4eb1b308717b060", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061591+00:00", "framework": "vllm_fix_tokenizer", "intentId": "83b34a04ca4d425caa6df272831a0908", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959924+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061990+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1a45e0a3d04940dc85ccd40299598b13", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061634+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1d5814a187bd452ba6ffa509c4cd3baf", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959919+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061899+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a0ac874fb23f40b5a752d15be870ea8f", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061689+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d8bf4a06568243bd9cc9ed636d9733aa", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959916+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061858+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b8b952f8a67e46aba56809e63424ab08", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061732+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e9efc42fd49431f9325b6b3e99b3b98", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959914+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061816+00:00", "framework": "vllm_fix_tokenizer", "intentId": "316ad0fa35f94502810025b3be17122c", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061774+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e27a8e38b8e7401a9309dd80a486fda7", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959911+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061774+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e27a8e38b8e7401a9309dd80a486fda7", "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": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061816+00:00", "framework": "vllm_fix_tokenizer", "intentId": "316ad0fa35f94502810025b3be17122c", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959908+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061732+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e9efc42fd49431f9325b6b3e99b3b98", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061858+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b8b952f8a67e46aba56809e63424ab08", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959906+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061689+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d8bf4a06568243bd9cc9ed636d9733aa", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061899+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a0ac874fb23f40b5a752d15be870ea8f", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959903+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061634+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1d5814a187bd452ba6ffa509c4cd3baf", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061947+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31f699eb49254cd1a88c1015bf37a33c", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959900+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061591+00:00", "framework": "vllm_fix_tokenizer", "intentId": "83b34a04ca4d425caa6df272831a0908", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061990+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1a45e0a3d04940dc85ccd40299598b13", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959894+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061501+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a42f6a42fe7449c8bd5d7b7645635074", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062032+00:00", "framework": "vllm_fix_tokenizer", "intentId": "543da9d65cdf4547a4eb1b308717b060", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959892+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061458+00:00", "framework": "vllm_fix_tokenizer", "intentId": "deb5f418aad74f3595e8056faba5afeb", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062075+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f063fcc323cf4f7abe54ea1c6ad52a2c", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959889+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "78756e9e47584ae1992d0dfa075c9e93", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062117+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a1ef3ffc801041a29229b0563036c63b", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959886+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061374+00:00", "framework": "vllm_fix_tokenizer", "intentId": "69e1da04388848df909c8ac07297dcfd", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062159+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b48202aa3ca44e9e98f9b04bf31da48a", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959884+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061326+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b02e3dafd1fa4cacad5a8a58b2aad56e", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062202+00:00", "framework": "vllm_fix_tokenizer", "intentId": "54e3a669496947578033df3a8019ebdb", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959880+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061277+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6d95e03819d549c492daeb552f651d02", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062243+00:00", "framework": "vllm_fix_tokenizer", "intentId": "43a69f8331b741328b2f7e918472c40f", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959878+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061223+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d29fd19b4ebb42b28e5c41365bfa5303", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062286+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2b2b9809b0f4ac09b5cb16f264dd31c", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959875+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061173+00:00", "framework": "vllm_tokenizer_patch", "intentId": "11679ea11ac2462a9457e77fbb00fe3e", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062335+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04ac952ce4754aa9ae410eae73417d16", "lastModified": "2026-09-09T06:50:48+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959872+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061124+00:00", "framework": "vllm_tokenizer_patch", "intentId": "df108764bb6b48ee97d38958abda1e1c", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062378+00:00", "framework": "transformers", "intentId": "ae51c1829a734b27878f288468a5355f", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959869+00:00", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061062+00:00", "framework": "vllm-mlu", "intentId": "581d0ce9a65f4a4982a5bc3805160fc8", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062440+00:00", "framework": "transformers", "intentId": "390f17520fa04e948c38fab9b9cc8706", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959866+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.061000+00:00", "framework": "vllm-mlu", "intentId": "52bafd3ecd574c37b44710b533f54567", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062501+00:00", "framework": "transformers", "intentId": "4bd54d2a7232473abf5a05ad83fc7042", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959863+00:00", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060937+00:00", "framework": "vllm-mlu", "intentId": "35df697bdc974a28a301921cd8b92879", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062562+00:00", "framework": "transformers", "intentId": "17440a9ecfb546feb86d2af2fc89ce8d", "lastModified": "2026-08-24T19:54:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959860+00:00", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060875+00:00", "framework": "vllm-mlu", "intentId": "fbdb0d00c610455e8e2c7272a44e7749", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062630+00:00", "framework": "transformers", "intentId": "61f427269b024f8aa9e6c83842d665c2", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959857+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060808+00:00", "framework": "vllm-mlu", "intentId": "d0519698a3cd495da5e06aa53eee8d78", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062696+00:00", "framework": "transformers", "intentId": "1a8af68d3c254c9987b1aecdbdc9fb09", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959853+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060771+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ef1d4ec2d9d94d8794b3d022b9effca1", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062757+00:00", "framework": "transformers", "intentId": "cf216303ad2d4b64bdf549031b1cdccd", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959850+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060727+00:00", "framework": "vllm_tokenizer_patch", "intentId": "30d27c6c77954b949d921414741a5ce3", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062818+00:00", "framework": "transformers", "intentId": "7c57603b1fef4f9288ec10c10f251222", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959847+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060689+00:00", "framework": "vllm_tokenizer_patch", "intentId": "221499919944485291424a67a0c2255a", "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": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062879+00:00", "framework": "transformers", "intentId": "767b894112024a2d8a24be8684bfc0eb", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959843+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a3e789ba339d4179aed4ae3206b1c264", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.062946+00:00", "framework": "transformers", "intentId": "413d89991a214e138d2a403d7a6449bd", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959840+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060601+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2a6c31e568454e299a41cdc2133b38a6", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063007+00:00", "framework": "transformers", "intentId": "460b12da111a4b548ff03253d006bf64", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959836+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060563+00:00", "framework": "vllm_tokenizer_patch", "intentId": "691d1320a33b462ab882ba95dd0050fa", "repoId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063067+00:00", "framework": "transformers", "intentId": "b837f348c6c5472bb06ed470becc03d6", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959820+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060376+00:00", "framework": "vllm_tokenizer_patch", "intentId": "878589d3b3104a05930bd55fd661a05f", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063127+00:00", "framework": "transformers", "intentId": "4200d03eb0bb4a2e84deaea7db024a05", "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": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959816+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060327+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c3b7b7527eca4c8bb96e2933f6572e77", "repoId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063188+00:00", "framework": "transformers", "intentId": "bca8f1e092bb4f3a8b6ad5be466065e4", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959809+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060229+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1ab0dcb3e7d246459f328c8a605cb38f", "repoId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b2403ad41b344619b44998d83ee40d90", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.063249+00:00", "framework": "transformers", "intentId": "ef972c0363d84722a9b05476dbb0c5e7", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "b2403ad41b344619b44998d83ee40d90", "completedAt": "2026-09-21T17:36:55.959788+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:25:49.060026+00:00", "framework": "vllm_tokenizer_patch", "intentId": "83386a7918154a97ac31c2c1664c16af", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281170+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498817+00:00", "framework": "vllm", "intentId": "3cf1f8a68f1540cf8c061c7882e351ed", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281170+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498817+00:00", "framework": "vllm", "intentId": "3cf1f8a68f1540cf8c061c7882e351ed", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281166+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498759+00:00", "framework": "vllm", "intentId": "a2609c244ae04dd3ade72ca48f1880b4", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281166+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498759+00:00", "framework": "vllm", "intentId": "a2609c244ae04dd3ade72ca48f1880b4", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281162+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498700+00:00", "framework": "vllm", "intentId": "a5df71d38d964ab69f7f50d7fd0e94e1", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281162+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498700+00:00", "framework": "vllm", "intentId": "a5df71d38d964ab69f7f50d7fd0e94e1", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
@@ -2475,56 +2475,3 @@
{"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029998+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829512+00:00", "framework": "vllm-customized", "intentId": "0b4c1fb43148405c8d304e7084c53dfc", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} {"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029998+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829512+00:00", "framework": "vllm-customized", "intentId": "0b4c1fb43148405c8d304e7084c53dfc", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029995+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829454+00:00", "framework": "vllm-customized", "intentId": "f0c2eb8945e54883b9be0a6af5387919", "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": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029995+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829454+00:00", "framework": "vllm-customized", "intentId": "f0c2eb8945e54883b9be0a6af5387919", "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": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029992+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829396+00:00", "framework": "vllm-customized", "intentId": "62a92b6a2caa42a5a4545f1f8515e44e", "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": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029992+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829396+00:00", "framework": "vllm-customized", "intentId": "62a92b6a2caa42a5a4545f1f8515e44e", "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": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029989+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829339+00:00", "framework": "vllm-customized", "intentId": "f17d8547f2ad4ecc902019be5f551a9e", "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": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029987+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829280+00:00", "framework": "vllm-customized", "intentId": "b8fff96a5c9542b4b29836472a04d680", "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": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029984+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829221+00:00", "framework": "vllm-customized", "intentId": "5d3e8ef36f3949478a19bf4d7631fc99", "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": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029981+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829140+00:00", "framework": "vllm-customized", "intentId": "e4e9ae909dbd43b2941434f71822584b", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029978+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829075+00:00", "framework": "vllm-customized", "intentId": "a9eddf290ba84f189aaa5a3284059925", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029975+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.829034+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4e27e4cb882145358026d71c5d01733c", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029972+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.828995+00:00", "framework": "vllm_tokenizer_patch", "intentId": "15183a97f5bc4f498b30fb9c85a968fa", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029968+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.828953+00:00", "framework": "vllm_tokenizer_patch", "intentId": "afa05d46ea8247e59b286d52d3f67353", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029965+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.828907+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f219fe94493e4819b90521371040fc20", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "b79a640b5060464c9b45fd46695fddbc", "completedAt": "2026-09-21T15:53:48.029950+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:48:38.828803+00:00", "framework": "vllm_tokenizer_patch", "intentId": "596b9ecedfcd46b6ab0d73c3b353a654", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969881+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622846+00:00", "framework": "vllm", "intentId": "a5508ad2e66e442186d9134294f5983d", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969878+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622799+00:00", "framework": "vllm", "intentId": "d38bdd7935b54cf192601455f05e1918", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969876+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622753+00:00", "framework": "vllm", "intentId": "70afa0149fd347a7b71275607e5d1aaf", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969874+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622707+00:00", "framework": "vllm", "intentId": "7dc43a4f5caf4d5aad9bdc11c00442cf", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969871+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622656+00:00", "framework": "vllm", "intentId": "c65ea68579a5477688c85f03b600a578", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969869+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622607+00:00", "framework": "vllm", "intentId": "4ddbe149a6ee4b21b73aed4dd7c1c935", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969866+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622566+00:00", "framework": "vllm-patch-tokenizer", "intentId": "87cbc60a0ab64914aac6dc66612a3b7f", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969864+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622525+00:00", "framework": "vllm-patch-tokenizer", "intentId": "dc54b6b793c341bd978cc7e4730052ec", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969861+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622483+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a81dbed676064007a165a7e2b37e6f99", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969854+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622359+00:00", "framework": "vllm-patch-tokenizer", "intentId": "89a4496d30cc4ae7a5002ee3042b3abf", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969851+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622318+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4aa1e983598a4053beb6ff707822c4b8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969849+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622277+00:00", "framework": "vllm-patch-tokenizer", "intentId": "921a89d747a94087b42ac54813b580a7", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969847+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622235+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a9f2349ecc8d40d89934159bdf08b43e", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969844+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622194+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9a3870898cb148b1ac64e3881d8eebb9", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969841+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622153+00:00", "framework": "vllm-patch-tokenizer", "intentId": "72654ae8412b471a8b0332b35ab9ef1b", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969838+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622112+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c595208a2913496489aa69817df77627", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969835+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622070+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f87c7e5aee084699baa8e7b74f729e97", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969833+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.622028+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e89f78c62222493586781bf923c1211b", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969830+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621968+00:00", "framework": "transformers", "intentId": "fbb62e5459994b08bb11d28217a35474", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969828+00:00", "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621908+00:00", "framework": "transformers", "intentId": "41d337ffcd304476ac433ae96b1cad84", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969825+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621848+00:00", "framework": "transformers", "intentId": "3aae176ebf6d4b72ae4790bac0cb9d78", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969823+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621788+00:00", "framework": "transformers", "intentId": "52abb43a2af2448e9ef7d36b6829a7f4", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969821+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621727+00:00", "framework": "transformers", "intentId": "ff39260d438a412f850cccea7da747b7", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969818+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621661+00:00", "framework": "transformers", "intentId": "dcb21651688e47758631feab62a60a3b", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969815+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621601+00:00", "framework": "transformers", "intentId": "af14d99d1ec347249ad245e8c7a910cd", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969811+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621540+00:00", "framework": "transformers", "intentId": "a22636f0e6674cd0a818553b99afcdce", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969808+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621480+00:00", "framework": "transformers", "intentId": "2468c06ff25748b08dc6985d137964b4", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969804+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621420+00:00", "framework": "transformers", "intentId": "83efd8a8e57b4d7d96fce383d8244ef3", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969798+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621298+00:00", "framework": "transformers", "intentId": "807223c991824eb7adea5d12869836c5", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969794+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621236+00:00", "framework": "transformers", "intentId": "48fac18a8aad40ebbfe1ee68b52236b1", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969790+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621195+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5b732bb1918d4ee7af3927f09a4c4646", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969787+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621153+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c53273d6b17e4fcfa3cddf38d5655fc2", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969783+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621099+00:00", "framework": "vllm_fix_tokenizer", "intentId": "08e81d8b632448529211eab8c9bd9f99", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969780+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621057+00:00", "framework": "vllm_fix_tokenizer", "intentId": "75fde94bc4fd474faf6cc2e7c64662fb", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969777+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.621016+00:00", "framework": "vllm_fix_tokenizer", "intentId": "441834c6c3e944359986d2d3fbf2d119", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969773+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620974+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9301f0e329a243cea0d071f432da52a4", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969770+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620932+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4f46722d3a474592a75864eb0e8c4582", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969766+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620890+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d966061690d41a6acc3ab12eb7b92e5", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969763+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620847+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0e21901591494784ae6952f23a32f0d5", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969760+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620805+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d4bb21bf98c64e858748364e98c6a5ac", "repoId": "RedHatAI/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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969757+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620763+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f4387aea625b4501b3e1b7345465b688", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969755+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620721+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5753118d83274f9883043d8a85d69b99", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969752+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620661+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6bf33d93784240a2a1f049aadecf3340", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}

20
.modelhub_state/routing_intelligence.json
View File

@@ -1,16 +1,16 @@
{ {
"acceptedByCategory": { "acceptedByCategory": {
"unified_success_first": 2301 "unified_success_first": 2314
}, },
"acceptedByRoute": { "acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|llamacpp": 17,
"text-generation|Ascend_910-b3|vllm": 40, "text-generation|Ascend_910-b3|vllm": 40,
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 162, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 163,
"text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|llamacpp": 13,
"text-generation|Ascend_910-b4|vllm": 27, "text-generation|Ascend_910-b4|vllm": 27,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 141, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 147,
"text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm": 81,
"text-generation|Biren_166m|vllm_fix_tokenizer": 128, "text-generation|Biren_166m|vllm_fix_tokenizer": 129,
"text-generation|Cambricon_mlu-370-x4|vllm": 72, "text-generation|Cambricon_mlu-370-x4|vllm": 72,
"text-generation|Cambricon_mlu-370-x4|vllm-customized": 6, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 6,
"text-generation|Cambricon_mlu-370-x4|vllm-mlu": 89, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 89,
@@ -19,14 +19,14 @@
"text-generation|Cambricon_mlu-370-x8|vllm-mlu": 97, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 97,
"text-generation|Iluvatar_bi-100|transformers": 20, "text-generation|Iluvatar_bi-100|transformers": 20,
"text-generation|Iluvatar_bi-150|llamacpp": 16, "text-generation|Iluvatar_bi-150|llamacpp": 16,
"text-generation|Iluvatar_bi-150|transformers": 38, "text-generation|Iluvatar_bi-150|transformers": 41,
"text-generation|Iluvatar_bi-150|vllm": 9, "text-generation|Iluvatar_bi-150|vllm": 9,
"text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 102, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 102,
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 52, "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 53,
"text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 12, "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 12,
"text-generation|Iluvatar_mrv-100|vllm": 63, "text-generation|Iluvatar_mrv-100|vllm": 63,
"text-generation|Kunlunxin_p-800|vllm": 62, "text-generation|Kunlunxin_p-800|vllm": 62,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 184, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 185,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 88, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 88,
"text-generation|MetaX_c-500|vllm": 104, "text-generation|MetaX_c-500|vllm": 104,
"text-generation|Mthreads_s4000|llamacpp": 17, "text-generation|Mthreads_s4000|llamacpp": 17,
@@ -38,8 +38,8 @@
"text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 134 "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 134
}, },
"acceptedSinceRefresh": 2301, "acceptedSinceRefresh": 2314,
"acceptedTotal": 2301, "acceptedTotal": 2314,
"generatedAt": "2026-09-21T17:22:42.217393+00:00", "generatedAt": "2026-09-21T17:36:55.886000+00:00",
"version": 1 "version": 1
} }

20
ledger/submissions.jsonl
View File

@@ -1012,13 +1012,6 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-21T17:14:32.848203+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-21T17:14:32.848203+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-21T17:14:33.065595+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-21T17:14:33.065595+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"}
{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "submitTime": "2026-09-21T17:17:44.806635+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} {"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "submitTime": "2026-09-21T17:17:44.806635+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T19:48:14.739365+00:00", "targetGpu": "Biren_166m", "taskId": "4986621", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T19:48:14.745647+00:00", "targetGpu": "Biren_166m", "taskId": "4986622", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "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": "2026-09-20T19:48:14.804006+00:00", "targetGpu": "Biren_166m", "taskId": "4986623", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "submitTime": "2026-09-20T20:09:23.967582+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986857", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-20T20:21:26.745613+00:00", "targetGpu": "Biren_166m", "taskId": "4987023", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-20T20:33:30.958684+00:00", "targetGpu": "Biren_166m", "taskId": "4987157", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T20:33:46.481514+00:00", "targetGpu": "Biren_166m", "taskId": "4987185", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "submitTime": "2026-09-20T20:35:36.652541+00:00", "targetGpu": "Biren_166m", "taskId": "4987186", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "submitTime": "2026-09-20T20:35:36.652541+00:00", "targetGpu": "Biren_166m", "taskId": "4987186", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "submitTime": "2026-09-20T20:35:36.766659+00:00", "targetGpu": "Biren_166m", "taskId": "4987187", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "submitTime": "2026-09-20T20:35:36.766659+00:00", "targetGpu": "Biren_166m", "taskId": "4987187", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-20T20:39:13.053978+00:00", "targetGpu": "Biren_166m", "taskId": "4987256", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-20T20:39:13.053978+00:00", "targetGpu": "Biren_166m", "taskId": "4987256", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
@@ -1224,3 +1217,16 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-21T17:03:32.240792+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004389", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-21T17:03:32.240792+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004389", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-21T17:03:32.401500+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004440", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-21T17:03:32.401500+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004440", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-21T17:04:37.582797+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004419", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-21T17:04:37.582797+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004419", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "modelId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "submitTime": "2026-09-21T17:25:56.810809+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004733", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "submitTime": "2026-09-21T17:25:56.793359+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004731", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "modelId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "submitTime": "2026-09-21T17:25:56.795707+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004732", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-group128-v2", "modelId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "submitTime": "2026-09-21T17:25:56.838948+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004736", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "submitTime": "2026-09-21T17:25:56.835965+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004737", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "modelId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "submitTime": "2026-09-21T17:25:56.837536+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004738", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/InternScience/Agents-A1", "modelId": "InternScience/Agents-A1", "submitTime": "2026-09-21T17:25:56.859522+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5004735", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "submitTime": "2026-09-21T17:25:56.841052+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5004734", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "submitTime": "2026-09-21T17:28:33.935492+00:00", "targetGpu": "Biren_166m", "taskId": "5004770", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "submitTime": "2026-09-21T17:29:54.495099+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004794", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "modelId": "inclusionAI/Ling-3.0-tiny", "submitTime": "2026-09-21T17:32:19.865353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004804", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "submitTime": "2026-09-21T17:34:06.574134+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004817", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "submitTime": "2026-09-21T17:34:20.344385+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004818", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}

14
manifest.json
View File

@@ -10,16 +10,16 @@
".modelhub_state/queue_cleanup_latest.json": "96de561331568d32afa16a3d1299e6bf6ad1009a8239697991dc48f28baf298b", ".modelhub_state/queue_cleanup_latest.json": "96de561331568d32afa16a3d1299e6bf6ad1009a8239697991dc48f28baf298b",
".modelhub_state/recent_outcomes.jsonl": "adacc6fe27e3a1932db735b92cb69e36743fabd1230cdf1f93e3f68004d1e464", ".modelhub_state/recent_outcomes.jsonl": "adacc6fe27e3a1932db735b92cb69e36743fabd1230cdf1f93e3f68004d1e464",
".modelhub_state/recovery_active_tasks.jsonl": "e7ada21697cf4cd61357e3631a7251ba975f241503787027e0038a8407066550", ".modelhub_state/recovery_active_tasks.jsonl": "e7ada21697cf4cd61357e3631a7251ba975f241503787027e0038a8407066550",
".modelhub_state/recovery_intents.jsonl": "c2a2cf978db6c1833208dfb710e141a86ba655934ade648ac2bb0410be3650b7", ".modelhub_state/recovery_intents.jsonl": "d8195113738301d6039e46acf96d722ee74a375c07d62b674d14650f12c6d7a7",
".modelhub_state/routing_intelligence.json": "7c9ce6f6347827ab936b32b7702acc215cfae6e2b09d1165331fc9593cfc3cd0", ".modelhub_state/routing_intelligence.json": "1ae2ba79b91f6b3c3f98784a92477a082da648b2d745c789fb741a20753617fd",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "3f2f2919cc79bd30be7fe83064dba38b4265cf6c9a97a52b148681907987be98", "ledger/submissions.jsonl": "0eed9debac90381a74dd2508c420970ed18d03366a5a0cbd821ec68c4a697cda",
"outcomes/submissions.jsonl": "d2ced1019c8f28ee93ebe9b83ec17e2bfc40fbdb287ee74b8cb578b241336b76" "outcomes/submissions.jsonl": "e73252ff4eb13883f744c1e0e36506a7f1c87ea390f853fda839673aaa4df35c"
}, },
"generation": 11577, "generation": 11578,
"phase": "intent", "phase": "result",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-21T17:25:49.210477+00:00", "updatedAt": "2026-09-21T17:36:56.111621+00:00",
"writerId": "8b35139af6674067a339a670222d4b67" "writerId": "8b35139af6674067a339a670222d4b67"
} }

13
outcomes/submissions.jsonl
View File

@@ -1137,3 +1137,16 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:14:32.848203+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:14:32.848203+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:14:33.065595+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:14:33.065595+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175161, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T15:02:24.876374+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 2018175161}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:17:44.806635+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175161, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T15:02:24.876374+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 2018175161}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:17:44.806635+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232041608, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233890310, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233890310}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:25:56.810809+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004733", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490490, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490490}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:25:56.793359+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004731", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013064, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197401, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093197401}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:25:56.795707+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004732", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 761968600, "estimatedRequiredGiB": 0.854, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 763816934, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 763816934}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:25:56.838948+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004736", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9518081332, "estimatedRequiredGiB": 10.648, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9527265621, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9527265621}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:25:56.835965+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004737", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490505, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490505}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:25:56.837536+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004738", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "InternScience/Agents-A1", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70218761584, "estimatedRequiredGiB": 78.514, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 70253394423, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 70253394423}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:25:56.859522+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5004735", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1048871402, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1048871402}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:25:56.841052+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5004734", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51304360808, "estimatedRequiredGiB": 57.349, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 51315158961, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 51315158961}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:28:33.935492+00:00", "targetGpu": "Biren_166m", "taskId": "5004770", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T05:42:03.443541+00:00", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:29:54.495099+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004794", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:32:19.865353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004804", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-20T14:34:57.856723+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093251763}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:34:06.574134+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004817", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13594088584, "estimatedRequiredGiB": 15.203, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-21T17:34:20.344385+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004818", "taskType": "text-generation", "verifyResult": null}