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

state: generation 11618 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 19:00:54 +00:00
parent 6ca6ec35f5
commit 72679cd29b
5 changed files with 68 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

154
.modelhub_state/recovery_intents.jsonl
View File

@@ -2224,58 +2224,58 @@
{"batchId": "554333b73fae4aff812b15c98c0cc5ac", "completedAt": "2026-09-21T18:38:20.670136+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:38:00.093849+00:00", "framework": "vllm_tokenizer_patch", "intentId": "509188f935214c76922e8c1a066cbf37", "lastModified": "2026-09-21T18:33:37+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "reason": null, "reconciledAt": "2026-09-21T18:47:39.570356+00:00", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5005584", "taskType": "text-generation"}
{"batchId": "554333b73fae4aff812b15c98c0cc5ac", "completedAt": "2026-09-21T18:38:20.670140+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:38:00.093899+00:00", "framework": "vllm_tokenizer_patch", "intentId": "34b1747322c94962b2e628217a405376", "lastModified": "2026-09-21T18:24:35+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "reason": null, "reconciledAt": "2026-09-21T18:47:39.570091+00:00", "repoId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5005583", "taskType": "text-generation"}
{"batchId": "554333b73fae4aff812b15c98c0cc5ac", "completedAt": "2026-09-21T18:38:20.670143+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:38:00.093947+00:00", "framework": "vllm_tokenizer_patch", "intentId": "277cf31d836c4aca8be2798621eeb92b", "lastModified": "2026-09-21T18:28:31+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g8-v2_C", "reason": null, "reconciledAt": "2026-09-21T18:47:39.573223+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5005588", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204033+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3e6477a6eb2049c59c4ac4cd6f3008a0", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204189+00:00", "framework": "vllm_fix_tokenizer", "intentId": "51bcc450754b4c7b8030afaab99a8396", "lastModified": "2026-08-24T15:14:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "repoId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204273+00:00", "framework": "vllm_fix_tokenizer", "intentId": "88205bd159084de7b7af3b43f277b610", "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": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204352+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b0c1c87c9153487e9f887e5881a3414f", "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, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204429+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cb622e40196b40e59a849c9780a7cb06", "lastModified": "2026-08-24T15:42:55+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "repoId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204507+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d1aae7f5ed7456d8bb448bbe333c557", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204584+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c8210884e524c81b62b7ac6bac5b472", "lastModified": "2026-08-24T15:48:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204660+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c9802c6bd6ad4539bd53db9176966890", "lastModified": "2026-08-24T15:07:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Qwen2-1.5B-Instruct-FP8W8", "repoId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204748+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e5ea7ac4d9924a229286e55846078dac", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204825+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f531e0a873f94699aa113fe6c7e59c8e", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204905+00:00", "framework": "vllm_tokenizer_patch", "intentId": "605d09f48bf24dd6a5cf8c244444efe9", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204970+00:00", "framework": "vllm_tokenizer_patch", "intentId": "379ae9b423dd4e739f461e92c74539a5", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205034+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2f10f9b77e76401eab3462b656f93c13", "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, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205097+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7097951f4864412081dc409ab7c53c6d", "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, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205166+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5da08a2f14da48fdba19ba0e3beb6326", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205233+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ccc0af6b7cb04fd595579f83f7bad7b8", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205297+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c43dd8e58c3c487cb268bc426b66cf90", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205347+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9034d34742774a32af0e5f12342cebb0", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205386+00:00", "framework": "vllm-mlu", "intentId": "bca0de3d977e436a91df6c48fedbdef9", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205453+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a6f50d750de14eaea8a4f98f8fa7f656", "lastModified": "2026-08-24T18:12:10+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205504+00:00", "framework": "vllm", "intentId": "90200c66389b4bd49a5b6e0c4a23dad1", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205574+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b399c8999afa4803b46a6f4a0d42f8ce", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205618+00:00", "framework": "vllm_fix_tokenizer", "intentId": "080b9cc289c94081a02e37f098435815", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205661+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04ab68aa473d4a8694dec6871aa595f4", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205722+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f1e533bd745d4909b0d56b0a4fd629ee", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205765+00:00", "framework": "vllm_fix_tokenizer", "intentId": "691ff2bbe1b44bfbb120eebd4c37688f", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205808+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a60fb299c8f54b548010eece0c4c31c2", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205851+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b4e544085c6e4aacad2c38b188a76309", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205893+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c4d3f03d60cd4edc9e0e1bc2d712669a", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205935+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4adfe8154c3840a4816dbbe6e8d7d295", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205978+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d9296628f26485db1c49c2d9a680474", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206020+00:00", "framework": "vllm_fix_tokenizer", "intentId": "39b99eaec1c64aa8894702fd884270d9", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206063+00:00", "framework": "vllm_fix_tokenizer", "intentId": "45fed9fc7816435bb618084d8eca03d4", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206106+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a158f874b18b45209dbaa79d779fcc2a", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206148+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2f5e6a49eee1412788a4400a68a90959", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206191+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8a37e26f31114c2a99ed19f879834c9e", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206233+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c7871a2bd8049aaa9ac4b0a2e99d2c9", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206275+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0fb63f6f18184f26a63870a9caf49697", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206318+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8328972ec03a40e880e8a50f238200fd", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206360+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4687defa40064da59598ec505d8992e8", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206402+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a73d525e84a04db580867e45b00e26cd", "lastModified": "2026-08-24T20:02:14+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206445+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4b4ae3414f994d6c9b5130137377eb16", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206488+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7a949dc579804ad4b056eac994f006b8", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206530+00:00", "framework": "vllm_fix_tokenizer", "intentId": "61aa14c00dc441b3bc9285cefafbbcbb", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206572+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8ac7022c27b5476191fc0b945a0efb7d", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206615+00:00", "framework": "vllm_fix_tokenizer", "intentId": "17cd07229fb143d29a000811a0c648bd", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206657+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8d4431e254ba4304b64152d3c2ceab84", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206708+00:00", "framework": "transformers", "intentId": "70b95c03b0c44257a6b50fb03f4ac576", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206770+00:00", "framework": "transformers", "intentId": "c501c8100b684bc0aa2191d8858fea75", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206832+00:00", "framework": "transformers", "intentId": "a926a601a74142c19396c8deac65805f", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206893+00:00", "framework": "transformers", "intentId": "33db8f0273904b59bf89b911490d601b", "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": "959246bd0c784abfa3c49dbb043460c4", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206961+00:00", "framework": "transformers", "intentId": "0fda5b42904d493ebadbcd152c495ff7", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244557+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204273+00:00", "framework": "vllm_fix_tokenizer", "intentId": "88205bd159084de7b7af3b43f277b610", "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": "Kunlunxin_p-800", "taskId": "5005756", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244572+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204660+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c9802c6bd6ad4539bd53db9176966890", "lastModified": "2026-08-24T15:07:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Qwen2-1.5B-Instruct-FP8W8", "reason": null, "repoId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5005783", "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244710+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206961+00:00", "framework": "transformers", "intentId": "0fda5b42904d493ebadbcd152c495ff7", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244707+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206893+00:00", "framework": "transformers", "intentId": "33db8f0273904b59bf89b911490d601b", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244705+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206832+00:00", "framework": "transformers", "intentId": "a926a601a74142c19396c8deac65805f", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244702+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206770+00:00", "framework": "transformers", "intentId": "c501c8100b684bc0aa2191d8858fea75", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244700+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206708+00:00", "framework": "transformers", "intentId": "70b95c03b0c44257a6b50fb03f4ac576", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244697+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206657+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8d4431e254ba4304b64152d3c2ceab84", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244695+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206615+00:00", "framework": "vllm_fix_tokenizer", "intentId": "17cd07229fb143d29a000811a0c648bd", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244692+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206572+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8ac7022c27b5476191fc0b945a0efb7d", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244689+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206530+00:00", "framework": "vllm_fix_tokenizer", "intentId": "61aa14c00dc441b3bc9285cefafbbcbb", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244685+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206488+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7a949dc579804ad4b056eac994f006b8", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244681+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206445+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4b4ae3414f994d6c9b5130137377eb16", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244677+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206402+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a73d525e84a04db580867e45b00e26cd", "repoId": "RedHatAI/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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244673+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206360+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4687defa40064da59598ec505d8992e8", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244661+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206318+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8328972ec03a40e880e8a50f238200fd", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244659+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206275+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0fb63f6f18184f26a63870a9caf49697", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244656+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206233+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c7871a2bd8049aaa9ac4b0a2e99d2c9", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244653+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206191+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8a37e26f31114c2a99ed19f879834c9e", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244650+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206148+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2f5e6a49eee1412788a4400a68a90959", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244647+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206106+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a158f874b18b45209dbaa79d779fcc2a", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244645+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206063+00:00", "framework": "vllm_fix_tokenizer", "intentId": "45fed9fc7816435bb618084d8eca03d4", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244642+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.206020+00:00", "framework": "vllm_fix_tokenizer", "intentId": "39b99eaec1c64aa8894702fd884270d9", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244639+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205978+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d9296628f26485db1c49c2d9a680474", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244637+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205935+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4adfe8154c3840a4816dbbe6e8d7d295", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244634+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205893+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c4d3f03d60cd4edc9e0e1bc2d712669a", "repoId": "neuralmagic/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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244631+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205851+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b4e544085c6e4aacad2c38b188a76309", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244628+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205808+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a60fb299c8f54b548010eece0c4c31c2", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244625+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205765+00:00", "framework": "vllm_fix_tokenizer", "intentId": "691ff2bbe1b44bfbb120eebd4c37688f", "repoId": "neuralmagic/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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244623+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205722+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f1e533bd745d4909b0d56b0a4fd629ee", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244620+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205661+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04ab68aa473d4a8694dec6871aa595f4", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244617+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205618+00:00", "framework": "vllm_fix_tokenizer", "intentId": "080b9cc289c94081a02e37f098435815", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244614+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205574+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b399c8999afa4803b46a6f4a0d42f8ce", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244612+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205504+00:00", "framework": "vllm", "intentId": "90200c66389b4bd49a5b6e0c4a23dad1", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244609+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205453+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a6f50d750de14eaea8a4f98f8fa7f656", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244606+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205386+00:00", "framework": "vllm-mlu", "intentId": "bca0de3d977e436a91df6c48fedbdef9", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244603+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205347+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9034d34742774a32af0e5f12342cebb0", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244600+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205297+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c43dd8e58c3c487cb268bc426b66cf90", "repoId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244597+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205233+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ccc0af6b7cb04fd595579f83f7bad7b8", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244593+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205166+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5da08a2f14da48fdba19ba0e3beb6326", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244590+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205097+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7097951f4864412081dc409ab7c53c6d", "repoId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244587+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.205034+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2f10f9b77e76401eab3462b656f93c13", "repoId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244584+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204970+00:00", "framework": "vllm_tokenizer_patch", "intentId": "379ae9b423dd4e739f461e92c74539a5", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244581+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204905+00:00", "framework": "vllm_tokenizer_patch", "intentId": "605d09f48bf24dd6a5cf8c244444efe9", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244578+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204825+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f531e0a873f94699aa113fe6c7e59c8e", "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": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244575+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204748+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e5ea7ac4d9924a229286e55846078dac", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244569+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204584+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c8210884e524c81b62b7ac6bac5b472", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244566+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204507+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d1aae7f5ed7456d8bb448bbe333c557", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244563+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204429+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cb622e40196b40e59a849c9780a7cb06", "repoId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244560+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204352+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b0c1c87c9153487e9f887e5881a3414f", "repoId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244553+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204189+00:00", "framework": "vllm_fix_tokenizer", "intentId": "51bcc450754b4c7b8030afaab99a8396", "repoId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "959246bd0c784abfa3c49dbb043460c4", "completedAt": "2026-09-21T19:00:54.244530+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:50:38.204033+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3e6477a6eb2049c59c4ac4cd6f3008a0", "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": "482bae54c5214cadbd947a104733ee19", "completedAt": "2026-09-21T18:37:25.725563+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:32:48.226435+00:00", "framework": "vllm", "intentId": "9cc7495944004660ae552b48c8ac120d", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "482bae54c5214cadbd947a104733ee19", "completedAt": "2026-09-21T18:37:25.725560+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:32:48.226377+00:00", "framework": "vllm", "intentId": "87471f0dc8844ee3b104ce5837316d82", "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": "482bae54c5214cadbd947a104733ee19", "completedAt": "2026-09-21T18:37:25.725557+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:32:48.226316+00:00", "framework": "vllm", "intentId": "f7904ab3354c49eab8ff90f7b551bcfb", "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"}
@@ -2526,53 +2526,3 @@
{"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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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": "2026-09-21T17:22:42.281166+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": "2026-09-21T17:22:42.281158+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498641+00:00", "framework": "vllm-customized", "intentId": "b22dfe70d4124f8aa729e250669278c9", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281154+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498587+00:00", "framework": "vllm-customized", "intentId": "142c8f774ba9469087994045a2a63a64", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281151+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498534+00:00", "framework": "vllm-customized", "intentId": "b81de202590441989dc13a09f8ed9e6d", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281147+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498460+00:00", "framework": "vllm-customized", "intentId": "eb2a80481ca74061ab1aabc24875084c", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281144+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498406+00:00", "framework": "vllm-customized", "intentId": "e6fe791d1cc44443a0d9be847a3e460d", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281140+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498351+00:00", "framework": "vllm-customized", "intentId": "e51eb34d070948e29a6072f2860c3eb4", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281137+00:00", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498292+00:00", "framework": "vllm-customized", "intentId": "8da283666f8549d499d40b8042b3195b", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281133+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498234+00:00", "framework": "vllm-customized", "intentId": "747eda1dbafe4342b94ed38bda23d415", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281130+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498176+00:00", "framework": "vllm-customized", "intentId": "2d8e15dd3ce1418dbd1db8ee99865e4f", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281125+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498050+00:00", "framework": "vllm-customized", "intentId": "a65e2095832343449bdb61b831ba7b32", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281122+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497978+00:00", "framework": "vllm-customized", "intentId": "1dd80c6849ce4bde83470ec89b3aec67", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281119+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497920+00:00", "framework": "vllm-customized", "intentId": "5b05e0b5a4a2430ba883700a9b00e819", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281115+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497861+00:00", "framework": "vllm-customized", "intentId": "44492baee8e64456a47c47c62b317921", "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"}

10
.modelhub_state/routing_intelligence.json
View File

@@ -1,6 +1,6 @@
{
"acceptedByCategory": {
"unified_success_first": 2363
"unified_success_first": 2365
},
"acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17,
@@ -26,7 +26,7 @@
"text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 14,
"text-generation|Iluvatar_mrv-100|vllm": 63,
"text-generation|Kunlunxin_p-800|vllm": 64,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 189,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 191,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 96,
"text-generation|MetaX_c-500|vllm": 105,
"text-generation|Mthreads_s4000|llamacpp": 17,
@@ -38,8 +38,8 @@
"text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 134
},
"acceptedSinceRefresh": 2363,
"acceptedTotal": 2363,
"generatedAt": "2026-09-21T18:38:20.602395+00:00",
"acceptedSinceRefresh": 2365,
"acceptedTotal": 2365,
"generatedAt": "2026-09-21T19:00:54.179213+00:00",
"version": 1
}