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

state: generation 10349 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 07:25:59 +00:00
parent 9f061c752f
commit dd1d482bb9
5 changed files with 79 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

174
.modelhub_state/recovery_intents.jsonl
View File

@@ -1563,65 +1563,65 @@
{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906800+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607543+00:00", "framework": "vllm-mlu", "intentId": "e0d69886155b4d16b616f9ea9c7a274f", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "reason": null, "reconciledAt": "2026-09-20T07:14:45.271286+00:00", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972418", "taskType": "text-generation"} {"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906800+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607543+00:00", "framework": "vllm-mlu", "intentId": "e0d69886155b4d16b616f9ea9c7a274f", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "reason": null, "reconciledAt": "2026-09-20T07:14:45.271286+00:00", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972418", "taskType": "text-generation"}
{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906813+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607849+00:00", "framework": "vllm", "intentId": "ca5bfefc64874bbb89cd21f3e918036e", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "reason": null, "reconciledAt": "2026-09-20T07:14:45.270125+00:00", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "taskType": "text-generation"} {"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906813+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607849+00:00", "framework": "vllm", "intentId": "ca5bfefc64874bbb89cd21f3e918036e", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "reason": null, "reconciledAt": "2026-09-20T07:14:45.270125+00:00", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "taskType": "text-generation"}
{"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602145+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.622658+00:00", "framework": "vllm-mlu", "intentId": "49fbc5996f5543629ae3615677e7325a", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T07:14:45.268732+00:00", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4972568", "taskType": "text-generation"} {"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602145+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.622658+00:00", "framework": "vllm-mlu", "intentId": "49fbc5996f5543629ae3615677e7325a", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T07:14:45.268732+00:00", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4972568", "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.040836+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a53623abb16b436fb10ee1a2a83498fd", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851640+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.040836+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a53623abb16b436fb10ee1a2a83498fd", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4972960", "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.040945+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ce244ee0c764ef689587bc3f68ef896", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851701+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041252+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fa03a1b1ba9644a8b9ad6a4ceefd4c2a", "lastModified": "2026-09-04T14:33:33+00:00", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "reason": null, "repoId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4972959", "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041001+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7320383e619f4900b91abcd0cb0c8162", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851860+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043514+00:00", "framework": "transformers", "intentId": "36c0a623e3cd4d1394bfdba49b062f16", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "reason": null, "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4973030", "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041052+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5c36321aa3e9458787748a2fac9dfb85", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851871+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043768+00:00", "framework": "transformers", "intentId": "c28f82ebec9e4b47834854c7ece9d921", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041103+00:00", "framework": "vllm_tokenizer_patch", "intentId": "790d19a64c644639965c6cb51a6f19d8", "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": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851868+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043706+00:00", "framework": "transformers", "intentId": "6c75223df80a4fdc9be5ed71d3bf6f74", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041153+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9f1b8b16b0194bf1b272ff326adce723", "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": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851865+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043637+00:00", "framework": "transformers", "intentId": "45a191b8a3b44b3c8d579e816c603913", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041202+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b2423da7b40b45988c5864ebe13336c1", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851862+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043576+00:00", "framework": "transformers", "intentId": "f91390c6d585423b8b8ff3647e2ed495", "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041252+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fa03a1b1ba9644a8b9ad6a4ceefd4c2a", "lastModified": "2026-09-04T14:33:33+00:00", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "repoId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851857+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043453+00:00", "framework": "transformers", "intentId": "359a2235086a4b91b9ad7e33d4b6b9d1", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7af46f33578c4c0baccdf188ff265d37", "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": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851854+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043391+00:00", "framework": "transformers", "intentId": "55996b1810414358a6dc678706fb6a4b", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041341+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b159d3642c18461cb5b4821b66b481bf", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851851+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043328+00:00", "framework": "transformers", "intentId": "31991cb39c6543aba36a7ab192dcefea", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041379+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7a61be33c7334b22adab37aca84b6a39", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851848+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043266+00:00", "framework": "transformers", "intentId": "9fe908af023c4762b97157f8e00eee28", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041417+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e1e6cc2191ab435aa4ed2e51f3dbbb5a", "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": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851845+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043203+00:00", "framework": "transformers", "intentId": "0785d37315ec48bf873b38bead77ae45", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041454+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a4f504b839c84ae69a06ecbb2634cffc", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851842+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043161+00:00", "framework": "vllm_fix_tokenizer", "intentId": "84926893e8604a47895bf2f0f64bb51c", "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": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041492+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7fe4b920750c4da39ad19cbe1737afbf", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851839+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043118+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9c44e7c9acf48d1bf9ff2b59ffcac2e", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041529+00:00", "framework": "vllm_tokenizer_patch", "intentId": "28f7969f99ab4ef49a96d20fe0ae3809", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851836+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043076+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8ac8d54af62645d8aee95626c0687a05", "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": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041567+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5f139c322abf4b37b2948b63b3fcc472", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851833+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043034+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e8cdefb4c52245929e3de37792ded276", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041605+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8d92fb1df51340d4b6fec9ba1c856b1e", "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": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851830+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042991+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ae7eda9683f44eb3880f601163e4676a", "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": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041642+00:00", "framework": "vllm_tokenizer_patch", "intentId": "142e99a1c5ea45f7940b045010fd96a8", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851827+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042949+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c82277adaf6497a8c957a86333a3fa6", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041692+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5b1aa3fd710746cc929e8df66c505f76", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851824+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042907+00:00", "framework": "vllm_fix_tokenizer", "intentId": "43b9f4d220e149f9b3693d22d3b7b130", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041730+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0344d68bb2414ae08f54082d4078689d", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851821+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042864+00:00", "framework": "vllm_fix_tokenizer", "intentId": "44438d43497f4af296b89b2faf295970", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c104a531f1674926a6a81df4edd111ba", "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": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851818+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042821+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed4e3e10ccbd42078e109fa137e67a6c", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041806+00:00", "framework": "vllm-mlu", "intentId": "3cbbbb3b465e45558545afbe58355929", "lastModified": "2026-08-24T20:31:44+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851815+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042777+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3616524eb02d44c695f69e62833e7217", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041872+00:00", "framework": "vllm", "intentId": "c790326d1b684e19aafa42460f2ab217", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851811+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042724+00:00", "framework": "vllm", "intentId": "ee9fb00254e64aaa99a3d14af3e5cdb4", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041930+00:00", "framework": "vllm", "intentId": "042099dde6874096af6836ef21956bfb", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851807+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042661+00:00", "framework": "vllm", "intentId": "8c6f415bd38d4c6d89478e858912d420", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041983+00:00", "framework": "vllm", "intentId": "be5995eb8b024370bb39d450f860946b", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851804+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042608+00:00", "framework": "vllm", "intentId": "a07d0b89223344a4be5e466452999139", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042037+00:00", "framework": "vllm", "intentId": "bba5fc3c16a645f288acff375cb5a657", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851800+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042554+00:00", "framework": "vllm", "intentId": "878836c3a87b43cabe16127903252b31", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042089+00:00", "framework": "vllm", "intentId": "cb391b3738da4095b7b2227a5a9a3c55", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851796+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042500+00:00", "framework": "vllm", "intentId": "92903e04e6a746838e079b27f481c795", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042141+00:00", "framework": "vllm", "intentId": "1e5f285c86384b0abd4b399bd67a195b", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851792+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042449+00:00", "framework": "vllm", "intentId": "8b52046ac9784b9893b4b65d64614252", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042193+00:00", "framework": "vllm", "intentId": "2b04efd458eb48e89565f11c18fad71b", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851788+00:00", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042398+00:00", "framework": "vllm", "intentId": "07706c327d7e40ebb194a893c065b988", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042244+00:00", "framework": "vllm", "intentId": "c62b9454421f4be8b7813cf111dc7e82", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851785+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042347+00:00", "framework": "vllm", "intentId": "66e3d4655dd8469c83de96c8625c06dd", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042296+00:00", "framework": "vllm", "intentId": "42fe9b09e7ab4425afc68bf6b70d41ce", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851781+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042296+00:00", "framework": "vllm", "intentId": "42fe9b09e7ab4425afc68bf6b70d41ce", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042347+00:00", "framework": "vllm", "intentId": "66e3d4655dd8469c83de96c8625c06dd", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851777+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042244+00:00", "framework": "vllm", "intentId": "c62b9454421f4be8b7813cf111dc7e82", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042398+00:00", "framework": "vllm", "intentId": "07706c327d7e40ebb194a893c065b988", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851773+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042193+00:00", "framework": "vllm", "intentId": "2b04efd458eb48e89565f11c18fad71b", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042449+00:00", "framework": "vllm", "intentId": "8b52046ac9784b9893b4b65d64614252", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851769+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042141+00:00", "framework": "vllm", "intentId": "1e5f285c86384b0abd4b399bd67a195b", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042500+00:00", "framework": "vllm", "intentId": "92903e04e6a746838e079b27f481c795", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851765+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042089+00:00", "framework": "vllm", "intentId": "cb391b3738da4095b7b2227a5a9a3c55", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042554+00:00", "framework": "vllm", "intentId": "878836c3a87b43cabe16127903252b31", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851754+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042037+00:00", "framework": "vllm", "intentId": "bba5fc3c16a645f288acff375cb5a657", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042608+00:00", "framework": "vllm", "intentId": "a07d0b89223344a4be5e466452999139", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851751+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041983+00:00", "framework": "vllm", "intentId": "be5995eb8b024370bb39d450f860946b", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042661+00:00", "framework": "vllm", "intentId": "8c6f415bd38d4c6d89478e858912d420", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851748+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041930+00:00", "framework": "vllm", "intentId": "042099dde6874096af6836ef21956bfb", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042724+00:00", "framework": "vllm", "intentId": "ee9fb00254e64aaa99a3d14af3e5cdb4", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851746+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041872+00:00", "framework": "vllm", "intentId": "c790326d1b684e19aafa42460f2ab217", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042777+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3616524eb02d44c695f69e62833e7217", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851742+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041806+00:00", "framework": "vllm-mlu", "intentId": "3cbbbb3b465e45558545afbe58355929", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042821+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed4e3e10ccbd42078e109fa137e67a6c", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851739+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c104a531f1674926a6a81df4edd111ba", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042864+00:00", "framework": "vllm_fix_tokenizer", "intentId": "44438d43497f4af296b89b2faf295970", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851737+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041730+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0344d68bb2414ae08f54082d4078689d", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042907+00:00", "framework": "vllm_fix_tokenizer", "intentId": "43b9f4d220e149f9b3693d22d3b7b130", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851734+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041692+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5b1aa3fd710746cc929e8df66c505f76", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042949+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c82277adaf6497a8c957a86333a3fa6", "lastModified": "2026-09-01T03:45:04+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851731+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041642+00:00", "framework": "vllm_tokenizer_patch", "intentId": "142e99a1c5ea45f7940b045010fd96a8", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.042991+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ae7eda9683f44eb3880f601163e4676a", "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": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851728+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041605+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8d92fb1df51340d4b6fec9ba1c856b1e", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043034+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e8cdefb4c52245929e3de37792ded276", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851725+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041567+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5f139c322abf4b37b2948b63b3fcc472", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043076+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8ac8d54af62645d8aee95626c0687a05", "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": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851722+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041529+00:00", "framework": "vllm_tokenizer_patch", "intentId": "28f7969f99ab4ef49a96d20fe0ae3809", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043118+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9c44e7c9acf48d1bf9ff2b59ffcac2e", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851719+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041492+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7fe4b920750c4da39ad19cbe1737afbf", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043161+00:00", "framework": "vllm_fix_tokenizer", "intentId": "84926893e8604a47895bf2f0f64bb51c", "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": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851716+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041454+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a4f504b839c84ae69a06ecbb2634cffc", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043203+00:00", "framework": "transformers", "intentId": "0785d37315ec48bf873b38bead77ae45", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851713+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041417+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e1e6cc2191ab435aa4ed2e51f3dbbb5a", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043266+00:00", "framework": "transformers", "intentId": "9fe908af023c4762b97157f8e00eee28", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851710+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041379+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7a61be33c7334b22adab37aca84b6a39", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043328+00:00", "framework": "transformers", "intentId": "31991cb39c6543aba36a7ab192dcefea", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851707+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041341+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b159d3642c18461cb5b4821b66b481bf", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043391+00:00", "framework": "transformers", "intentId": "55996b1810414358a6dc678706fb6a4b", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851703+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041301+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7af46f33578c4c0baccdf188ff265d37", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043453+00:00", "framework": "transformers", "intentId": "359a2235086a4b91b9ad7e33d4b6b9d1", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851697+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041202+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b2423da7b40b45988c5864ebe13336c1", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043514+00:00", "framework": "transformers", "intentId": "36c0a623e3cd4d1394bfdba49b062f16", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851694+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041153+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9f1b8b16b0194bf1b272ff326adce723", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043576+00:00", "framework": "transformers", "intentId": "f91390c6d585423b8b8ff3647e2ed495", "lastModified": "2026-09-11T12:06:58+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851689+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041103+00:00", "framework": "vllm_tokenizer_patch", "intentId": "790d19a64c644639965c6cb51a6f19d8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043637+00:00", "framework": "transformers", "intentId": "45a191b8a3b44b3c8d579e816c603913", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851685+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041052+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5c36321aa3e9458787748a2fac9dfb85", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043706+00:00", "framework": "transformers", "intentId": "6c75223df80a4fdc9be5ed71d3bf6f74", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851680+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041001+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7320383e619f4900b91abcd0cb0c8162", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8059016df904d1cbb34b18372c8644d", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.043768+00:00", "framework": "transformers", "intentId": "c28f82ebec9e4b47834854c7ece9d921", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851663+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.040945+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ce244ee0c764ef689587bc3f68ef896", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432012+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.642022+00:00", "framework": "vllm", "intentId": "530a73b5bd6f4c5f98e1f04a2eed1768", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432012+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.642022+00:00", "framework": "vllm", "intentId": "530a73b5bd6f4c5f98e1f04a2eed1768", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432007+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641955+00:00", "framework": "vllm", "intentId": "e4c5b4949e2b41ce9854775a54fbd5f9", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432007+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641955+00:00", "framework": "vllm", "intentId": "e4c5b4949e2b41ce9854775a54fbd5f9", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432003+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641888+00:00", "framework": "vllm", "intentId": "492ba554c7054dffaaa97069a5ea24f7", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432003+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641888+00:00", "framework": "vllm", "intentId": "492ba554c7054dffaaa97069a5ea24f7", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
@@ -1866,59 +1866,3 @@
{"batchId": "22985c0652314c9da91d705e62b9a761", "completedAt": "2026-09-20T06:22:58.008266+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:15:57.086795+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f68ead31eb8340079ee5dd8f52f8016a", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "22985c0652314c9da91d705e62b9a761", "completedAt": "2026-09-20T06:22:58.008266+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:15:57.086795+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f68ead31eb8340079ee5dd8f52f8016a", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736464+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619879+00:00", "framework": "vllm", "intentId": "6b3a8de2b10a428c9ddf9d22b3181296", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736464+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619879+00:00", "framework": "vllm", "intentId": "6b3a8de2b10a428c9ddf9d22b3181296", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736461+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619821+00:00", "framework": "vllm", "intentId": "b9843c023d764a80b3d64be3bd78f7e3", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736461+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619821+00:00", "framework": "vllm", "intentId": "b9843c023d764a80b3d64be3bd78f7e3", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736459+00:00", "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619764+00:00", "framework": "vllm", "intentId": "02e8d73581314d238754c645ce8907e2", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736456+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619716+00:00", "framework": "vllm", "intentId": "db8217ee32ce40898df385931554cce7", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736454+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619663+00:00", "framework": "vllm", "intentId": "de2e77bca3ae46298864d9f6ede6e9b0", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736451+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619621+00:00", "framework": "vllm-patch-tokenizer", "intentId": "80b5c6df05e64d7aa499ffdaaf14d8b8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736449+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619578+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b48320be72cb4cf58938a4586292fa74", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736446+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619516+00:00", "framework": "transformers", "intentId": "4f2bf0c28a9e431bae833e1c54592255", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736443+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619453+00:00", "framework": "transformers", "intentId": "70d2c6d645f14187849ca5ac484eb6c3", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736441+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619390+00:00", "framework": "transformers", "intentId": "fc155c960e474a01aaf4fcfb7da1b552", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736438+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619347+00:00", "framework": "vllm_fix_tokenizer", "intentId": "84221d338f9449b0b365eb2a18d23d65", "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": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736435+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619304+00:00", "framework": "vllm_fix_tokenizer", "intentId": "79bc1d2df304476b96747789840c858d", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736433+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619260+00:00", "framework": "vllm_fix_tokenizer", "intentId": "22f271d3aca142a6973dee52226ebc21", "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": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736430+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619216+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2901e5020fc546e58114d8e2c66c4ac6", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736427+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619162+00:00", "framework": "vllm", "intentId": "c0661e2744af4df1b9eb06312beeb41d", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736425+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619107+00:00", "framework": "vllm", "intentId": "13d056be558149d7a89501e23bc020ae", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736423+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619054+00:00", "framework": "vllm", "intentId": "86f667211adb46c89b6a274deb5a77b5", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736420+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.619000+00:00", "framework": "vllm", "intentId": "b3e518e77a534894b859c7d0177371ba", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736417+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618945+00:00", "framework": "vllm", "intentId": "dee20dcfb7234f4fab152aec6d930623", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736414+00:00", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618893+00:00", "framework": "vllm", "intentId": "68f05b958f0c430e951c4936ede637fa", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736412+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618841+00:00", "framework": "vllm", "intentId": "4b1c507b4044417dad371ec41705ab26", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736410+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618789+00:00", "framework": "vllm", "intentId": "d60ccdeaa88b41188e43ebc1acdff189", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736407+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618735+00:00", "framework": "vllm", "intentId": "5be3e83013f9489d9bfe1a22f8e8cd4f", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736404+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618678+00:00", "framework": "vllm", "intentId": "f782ac755ad64b049b8a6c42eb9cc9ac", "repoId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736402+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618610+00:00", "framework": "vllm-mlu", "intentId": "2f75b3b1ccd946b995f9f7d694af327d", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736399+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618544+00:00", "framework": "vllm-mlu", "intentId": "4ba2ec64ac3b4424a1dfeb8177a1d11b", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736396+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618507+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a24804ca4d9c4e80a94175cd0edb8399", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736393+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618470+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ac1ac850c8824627813de01e82e7d0c8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736391+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618433+00:00", "framework": "vllm_tokenizer_patch", "intentId": "771a6c147555464baa53e6a4b22e4f49", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736388+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618396+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7593fd1ae3074676ba81ff1cba7bbc42", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736386+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618358+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5835847988a7449b8ad9bd4b3dbd6eb1", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736383+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618321+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f1fbd28ef764414397851f629d7e5a1c", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736381+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618284+00:00", "framework": "vllm_tokenizer_patch", "intentId": "34f96f6116e94192a44cbe15ed369917", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736378+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618246+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cc394172deed4ad491d67e3f692d1b96", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736375+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618206+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a931febfd8364e6d917c236dc64a7664", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736373+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618159+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b9d9cd0d2db3466bb53b7d252f57cf39", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736370+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618110+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5726a064816a4e31a5069c75f15ee93b", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736367+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618061+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b284d54a2c304c6daa6a34143c7c7b2a", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736364+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.618011+00:00", "framework": "vllm_tokenizer_patch", "intentId": "249ecde701cb4e40868a8a43833ed40a", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736361+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.617968+00:00", "framework": "vllm_fix_tokenizer", "intentId": "25182f545e974a26bbb0ef5dc442587e", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736358+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.617926+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc9d1ce38acf4ca6afbddc29f71cf064", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736355+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.617882+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0c28b880f7804c348f33aee063c00d80", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736352+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.617831+00:00", "framework": "vllm_tokenizer_patch", "intentId": "46497b1caef24f5b99bfd3afbfb608c9", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736345+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.617729+00:00", "framework": "vllm_tokenizer_patch", "intentId": "473a7ed0e8b14a51a79a01ccfec91c15", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736340+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.617660+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8812fdf86d4f46588ced396ce2edf37d", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "9b66f3a164ed48ca9a534db1d291df0f", "completedAt": "2026-09-20T04:41:55.736317+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:36:47.617545+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ca189626db2242c1af97f36b666ba3cc", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606457+00:00", "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.373005+00:00", "framework": "vllm", "intentId": "5265323f99c64cc89c94370f67aac3dd", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606454+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372955+00:00", "framework": "vllm", "intentId": "7c51582991c54dafac5e215dd0b22bdc", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606452+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372893+00:00", "framework": "transformers", "intentId": "1e10f0bd563344798e43900b7ed552e5", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606449+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372829+00:00", "framework": "transformers", "intentId": "02dff8c81dec4b05ac0383715ec5196e", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606446+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372785+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d8a9c70e224244e296a2cd2eb7cbb2ab", "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": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606444+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372741+00:00", "framework": "vllm_fix_tokenizer", "intentId": "de9f7af1a31149c190ffdfe4cd5cdb73", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606441+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372698+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e8f86e1ef39048e689b1f4a6cce13c7c", "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": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606437+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372600+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4fb0a494e9b64d12a4071cc5255f885b", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606434+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372545+00:00", "framework": "vllm", "intentId": "d68071eb74eb41c88b395243ed4b0a66", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606429+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372436+00:00", "framework": "vllm", "intentId": "8b57328570a342ee8bc4c02066946d71", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606426+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372380+00:00", "framework": "vllm", "intentId": "46928b0005ad476c837747a9476375b5", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "de6502267c8e4e5c90edbc55774b6cef", "completedAt": "2026-09-20T04:29:13.606421+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:26:44.372269+00:00", "framework": "vllm", "intentId": "9de4d079face401c9d8f4ea3cbcabb74", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}

14
.modelhub_state/routing_intelligence.json
View File

@@ -1,6 +1,6 @@
{ {
"acceptedByCategory": { "acceptedByCategory": {
"unified_success_first": 1703 "unified_success_first": 1706
}, },
"acceptedByRoute": { "acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|llamacpp": 17,
@@ -8,7 +8,7 @@
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 117, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 117,
"text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|llamacpp": 13,
"text-generation|Ascend_910-b4|vllm": 18, "text-generation|Ascend_910-b4|vllm": 18,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 108, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 109,
"text-generation|Biren_166m|vllm": 71, "text-generation|Biren_166m|vllm": 71,
"text-generation|Biren_166m|vllm_fix_tokenizer": 13, "text-generation|Biren_166m|vllm_fix_tokenizer": 13,
"text-generation|Cambricon_mlu-370-x4|vllm": 48, "text-generation|Cambricon_mlu-370-x4|vllm": 48,
@@ -18,14 +18,14 @@
"text-generation|Cambricon_mlu-370-x8|vllm-customized": 26, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 26,
"text-generation|Cambricon_mlu-370-x8|vllm-mlu": 89, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 89,
"text-generation|Iluvatar_bi-150|llamacpp": 16, "text-generation|Iluvatar_bi-150|llamacpp": 16,
"text-generation|Iluvatar_bi-150|transformers": 16, "text-generation|Iluvatar_bi-150|transformers": 17,
"text-generation|Iluvatar_bi-150|vllm": 7, "text-generation|Iluvatar_bi-150|vllm": 7,
"text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 101, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 101,
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 32, "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 32,
"text-generation|Iluvatar_mrv-100|vllm": 61, "text-generation|Iluvatar_mrv-100|vllm": 61,
"text-generation|Kunlunxin_p-800|vllm": 3, "text-generation|Kunlunxin_p-800|vllm": 3,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 165, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 165,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 54, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 55,
"text-generation|MetaX_c-500|vllm": 104, "text-generation|MetaX_c-500|vllm": 104,
"text-generation|Mthreads_s4000|llamacpp": 17, "text-generation|Mthreads_s4000|llamacpp": 17,
"text-generation|Mthreads_s4000|vllm": 98, "text-generation|Mthreads_s4000|vllm": 98,
@@ -36,8 +36,8 @@
"text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 107 "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 107
}, },
"acceptedSinceRefresh": 1703, "acceptedSinceRefresh": 1706,
"acceptedTotal": 1703, "acceptedTotal": 1706,
"generatedAt": "2026-09-20T06:59:26.359382+00:00", "generatedAt": "2026-09-20T07:25:58.792324+00:00",
"version": 1 "version": 1
} }

3
ledger/submissions.jsonl
View File

@@ -1049,3 +1049,6 @@
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T05:16:13.358703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971314", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T05:16:13.358703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971314", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "modelId": "BAAI/RoboBrain2.5-8B-MT", "submitTime": "2026-09-20T05:16:13.351034+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "modelId": "BAAI/RoboBrain2.5-8B-MT", "submitTime": "2026-09-20T05:16:13.351034+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "modelId": "inclusionAI/Ling-3.0-tiny", "submitTime": "2026-09-20T06:19:35.394755+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4972231", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "modelId": "inclusionAI/Ling-3.0-tiny", "submitTime": "2026-09-20T06:19:35.394755+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4972231", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "submitTime": "2026-09-20T07:19:46.762739+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972960", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "submitTime": "2026-09-20T07:19:46.756927+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972959", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "modelId": "LiquidAI/LFM2.5-8B-A1B", "submitTime": "2026-09-20T07:24:14.091402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4973030", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}

14
manifest.json
View File

@@ -9,16 +9,16 @@
".modelhub_state/queue_cleanup_latest.json": "a43deb60b6f751b76576986b5c89b51a2b8d469239d82ff9136f564b25b03b2c", ".modelhub_state/queue_cleanup_latest.json": "a43deb60b6f751b76576986b5c89b51a2b8d469239d82ff9136f564b25b03b2c",
".modelhub_state/recent_outcomes.jsonl": "4b7938bcc5b2b904aebaad1319021584da98a5d1dd5fda519e187df40272316c", ".modelhub_state/recent_outcomes.jsonl": "4b7938bcc5b2b904aebaad1319021584da98a5d1dd5fda519e187df40272316c",
".modelhub_state/recovery_active_tasks.jsonl": "acf6046165391253164b8db80f3ac0d3b9fdaf61fec68ca0b4af5ce9027841eb", ".modelhub_state/recovery_active_tasks.jsonl": "acf6046165391253164b8db80f3ac0d3b9fdaf61fec68ca0b4af5ce9027841eb",
".modelhub_state/recovery_intents.jsonl": "234537987f1488091eef527a584585a00026e5d5b7c25cc6cbd91301a1989d13", ".modelhub_state/recovery_intents.jsonl": "8bf8dd89fa550526767db5969415903ce6953bac81cc4231e232945e3f7b26e5",
".modelhub_state/routing_intelligence.json": "72fc513483c0e7903196e0b87c49363df43f156d3489d1cc997bfcb5e6ce7b66", ".modelhub_state/routing_intelligence.json": "b27d107d06b4bbc2cbaa84875e824cd9fa039d9336ff02d963d4faeae2fa0466",
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "1db6f8e03fd043d3e9ff3b966fe9150999a1adba0379da3609e6234516af100f", "ledger/submissions.jsonl": "4f23b10699f51e8078f87be4a8f1b63b181941ac3aab87954e963095a78e6333",
"outcomes/submissions.jsonl": "86636d3b59ed582198bf97d0118643716679c059d9710f85cd39d56b9faccef4" "outcomes/submissions.jsonl": "5c1be88a21345c29698d1ad5908dfdb5b9972846705e51c3cc9c2ea9a6d63024"
}, },
"generation": 10348, "generation": 10349,
"phase": "intent", "phase": "result",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-20T07:19:40.168276+00:00", "updatedAt": "2026-09-20T07:25:58.982925+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996" "writerId": "fc715c06e24c4db2ae3e425e435db996"
} }

3
outcomes/submissions.jsonl
View File

@@ -1081,3 +1081,6 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:33:31.623471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972418", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:33:31.623471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972418", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:34:00.535697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:34:00.535697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:49:15.390546+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4972568", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:49:15.390546+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4972568", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093204103, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093204103}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T07:19:46.762739+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972960", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 44221632439, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T07:19:46.756927+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972959", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T07:24:14.091402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4973030", "taskType": "text-generation", "verifyResult": null}