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

state: generation 11259 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 06:33:07 +00:00
parent 8eae9160de
commit e7e76a6f41
5 changed files with 74 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

165
.modelhub_state/recovery_intents.jsonl
View File

@@ -1979,62 +1979,62 @@
{"batchId": "89f5a51c8f42456690e034f6ed756db0", "completedAt": "2026-09-21T05:25:16.534383+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:25:13.840014+00:00", "framework": "vllm_tokenizer_patch", "intentId": "eaab1a2818cc4364a7a14ccc75f3032e", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-21T06:20:28.415044+00:00", "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4994586", "taskType": "text-generation"} {"batchId": "89f5a51c8f42456690e034f6ed756db0", "completedAt": "2026-09-21T05:25:16.534383+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:25:13.840014+00:00", "framework": "vllm_tokenizer_patch", "intentId": "eaab1a2818cc4364a7a14ccc75f3032e", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-21T06:20:28.415044+00:00", "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4994586", "taskType": "text-generation"}
{"batchId": "4f38c9647f3c466899bf3e87fd0a6ea3", "completedAt": "2026-09-21T05:35:36.489231+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:28:01.379043+00:00", "framework": "vllm_tokenizer_patch", "intentId": "636b712bb6b74f3da6d6d714e3bc4aca", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T06:20:28.412943+00:00", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4994617", "taskType": "text-generation"} {"batchId": "4f38c9647f3c466899bf3e87fd0a6ea3", "completedAt": "2026-09-21T05:35:36.489231+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:28:01.379043+00:00", "framework": "vllm_tokenizer_patch", "intentId": "636b712bb6b74f3da6d6d714e3bc4aca", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T06:20:28.412943+00:00", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4994617", "taskType": "text-generation"}
{"batchId": "bc7f734f92914dd480e72d6208547437", "completedAt": "2026-09-21T05:42:36.850300+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:42:27.953102+00:00", "framework": "vllm-customized", "intentId": "bb2cf9523ab94bdcb45541139e1b2d7b", "lastModified": "2026-09-21T05:32:36+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "reason": null, "reconciledAt": "2026-09-21T06:20:28.413179+00:00", "repoId": "Arain119/Sophia", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4994779", "taskType": "text-generation"} {"batchId": "bc7f734f92914dd480e72d6208547437", "completedAt": "2026-09-21T05:42:36.850300+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:42:27.953102+00:00", "framework": "vllm-customized", "intentId": "bb2cf9523ab94bdcb45541139e1b2d7b", "lastModified": "2026-09-21T05:32:36+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "reason": null, "reconciledAt": "2026-09-21T06:20:28.413179+00:00", "repoId": "Arain119/Sophia", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4994779", "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.394943+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cb1e120f5cea40d890c908f7b6dcbe85", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669440+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395052+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1660620787e8408a992a080fd4c4cd5f", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "reason": null, "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395052+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1660620787e8408a992a080fd4c4cd5f", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669445+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395107+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e8ca54ffa9e4465dbfdd67341102b868", "lastModified": "2026-08-24T18:15:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "reason": null, "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4995262", "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395107+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e8ca54ffa9e4465dbfdd67341102b868", "lastModified": "2026-08-24T18:15:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669456+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395255+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c66b1b701dc94fd7b119cc7a0ccfd4ae", "lastModified": "2026-08-24T17:55:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "reason": null, "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4995261", "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "24f62f87033845c1a6dbb70c998bb429", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669607+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.398071+00:00", "framework": "vllm-customized", "intentId": "2a066644f1e548fd9121f1b78ca87dda", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395206+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b4926fba95a54a65a2ef2a1297ebe11a", "lastModified": "2026-08-24T17:49:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669604+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.398013+00:00", "framework": "vllm-customized", "intentId": "878d497579ab44d5baa6b918ba0aaff0", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395255+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c66b1b701dc94fd7b119cc7a0ccfd4ae", "lastModified": "2026-08-24T17:55:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669602+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397956+00:00", "framework": "vllm-customized", "intentId": "30a94939f5964518b2330fe23803e0e1", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395305+00:00", "framework": "vllm_tokenizer_patch", "intentId": "02304395dd55481c9dc4a2ae8bc87d3c", "lastModified": "2026-08-24T17:53:32+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669599+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397895+00:00", "framework": "vllm-customized", "intentId": "ac2fff845ede4e6db0a7e90796dce0b2", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395353+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8da5a6fcddcf4b019a4415768f33aa4d", "lastModified": "2026-08-24T19:08:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669596+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397815+00:00", "framework": "vllm-customized", "intentId": "6699c79379af416495fadb2a2bb5f547", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395402+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dbebf748088d493aa2280a0a0c96ad0b", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669594+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397757+00:00", "framework": "vllm-customized", "intentId": "9439ad472a144bde8a751b64d4b8959e", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395450+00:00", "framework": "vllm", "intentId": "a4bfeea8df3f4084bbd3c03d67dbb80f", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669591+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397700+00:00", "framework": "vllm-customized", "intentId": "9f65bb901dba40a990860f323cade531", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395498+00:00", "framework": "vllm", "intentId": "d24898ec08d04b0eaa84b1021f858592", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669588+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397631+00:00", "framework": "vllm-customized", "intentId": "511e4a8e2c4b4d2894cebe63b080ce28", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395546+00:00", "framework": "vllm-mlu", "intentId": "635035ba1cb1499e8e3c4f9b4514eee8", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669585+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397574+00:00", "framework": "vllm-customized", "intentId": "eb4fde14582f4513bef9b3721f7cddfc", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395611+00:00", "framework": "vllm-mlu", "intentId": "a975e9bbd08f405d8153bc8a8db65846", "lastModified": "2026-08-24T18:26:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a16-per-channel", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669582+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397518+00:00", "framework": "vllm-customized", "intentId": "9dec1cbd9d0a4eaf8bc2e303b5f29b6d", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395688+00:00", "framework": "vllm-mlu", "intentId": "137841d4a0c14c8b9ad73d089807b62c", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669579+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397461+00:00", "framework": "vllm-customized", "intentId": "4d3798bcc3ef44d9bf02d1f9c8520199", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395750+00:00", "framework": "vllm-mlu", "intentId": "c478a4b72c1f4d6f9e73dab64a2a06f0", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669576+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397404+00:00", "framework": "vllm-customized", "intentId": "168afc3af4e24c67949dbb90e5cd8aa6", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395813+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5d87acf8315149a3acfdba428916065b", "lastModified": "2026-08-24T19:06:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669573+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397347+00:00", "framework": "vllm-customized", "intentId": "29b6a3fa586041c48fc73d55cbbf5266", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395863+00:00", "framework": "vllm_tokenizer_patch", "intentId": "156d6b4cbfa741a6828cd757ef09407a", "lastModified": "2026-09-09T07:06:46+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669570+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397290+00:00", "framework": "vllm-customized", "intentId": "ec2fb55fdae94667855de87071d2a35b", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395913+00:00", "framework": "vllm_tokenizer_patch", "intentId": "87bc0b381f724f6db140e2ee96321071", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669567+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397233+00:00", "framework": "vllm-customized", "intentId": "f7ac0ba7d47447209fe10abc780cf0c8", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395961+00:00", "framework": "vllm", "intentId": "ce5f9688359e4aa790142fce9f70a2b9", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669565+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397176+00:00", "framework": "vllm-customized", "intentId": "9d71bca1a7d449c0aacd93db4a8a4799", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396018+00:00", "framework": "vllm", "intentId": "c3200696583b4433a5f59657566dde41", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669562+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397111+00:00", "framework": "vllm-customized", "intentId": "13a6d043f4334d8ab928bb0eb5e2c117", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396074+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2fe77a24cf8e4a0abaf14777dad91edc", "lastModified": "2026-08-31T03:35:12+00:00", "modelAddress": "https://modelscope.cn/models/logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669559+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397054+00:00", "framework": "vllm-customized", "intentId": "ea5f73eb3c6e4078b7a2e66235a51c43", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396118+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9e37f06b53d24883a7d53f9e24f39b2e", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669556+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396998+00:00", "framework": "vllm-customized", "intentId": "f38faa57ee3a4cfa8d7d2aab2742f475", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396160+00:00", "framework": "vllm", "intentId": "38a7dd9b18ba4c7c9371dccadc84447c", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669553+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396942+00:00", "framework": "vllm-customized", "intentId": "8df84161e91e400bba885a745f170d1c", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396208+00:00", "framework": "vllm", "intentId": "94c16b015a0c4e71bc73ac86bfa0bbbe", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669550+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396885+00:00", "framework": "vllm-customized", "intentId": "5235a8707198491ea1233e1fcd01e618", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396256+00:00", "framework": "vllm", "intentId": "ff7b62b83d98446cabc7fb74c7570ca8", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669547+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396828+00:00", "framework": "vllm-customized", "intentId": "f71d740509f8423592fc5a0a13b33184", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396302+00:00", "framework": "vllm-customized", "intentId": "f8c0d69c2b2f414e82361452294ecff9", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669545+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396772+00:00", "framework": "vllm-customized", "intentId": "e43d862dd5a249ab93f338d00f1d1452", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396360+00:00", "framework": "vllm-customized", "intentId": "51e3fae143e84ee8b375cfd154976801", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669542+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396715+00:00", "framework": "vllm-customized", "intentId": "f0ca5d0db5924b7b99f06e37ac0408cd", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396417+00:00", "framework": "vllm-customized", "intentId": "5dafb2f1e5a146ea8a5b0ebb95af9d7c", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669539+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396644+00:00", "framework": "vllm-customized", "intentId": "6c33144965fb4b44874e07f961cefd4e", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396473+00:00", "framework": "vllm-customized", "intentId": "13d15172ddbb471d85d525405e427869", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669536+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396587+00:00", "framework": "vllm-customized", "intentId": "c267fe2469cc41cc9a45b7b6abae86fb", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396530+00:00", "framework": "vllm-customized", "intentId": "0bafff292be04a9a965c50b7bffcb4b7", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669533+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396530+00:00", "framework": "vllm-customized", "intentId": "0bafff292be04a9a965c50b7bffcb4b7", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396587+00:00", "framework": "vllm-customized", "intentId": "c267fe2469cc41cc9a45b7b6abae86fb", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669530+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396473+00:00", "framework": "vllm-customized", "intentId": "13d15172ddbb471d85d525405e427869", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396644+00:00", "framework": "vllm-customized", "intentId": "6c33144965fb4b44874e07f961cefd4e", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669527+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396417+00:00", "framework": "vllm-customized", "intentId": "5dafb2f1e5a146ea8a5b0ebb95af9d7c", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396715+00:00", "framework": "vllm-customized", "intentId": "f0ca5d0db5924b7b99f06e37ac0408cd", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669524+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396360+00:00", "framework": "vllm-customized", "intentId": "51e3fae143e84ee8b375cfd154976801", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396772+00:00", "framework": "vllm-customized", "intentId": "e43d862dd5a249ab93f338d00f1d1452", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669520+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396302+00:00", "framework": "vllm-customized", "intentId": "f8c0d69c2b2f414e82361452294ecff9", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396828+00:00", "framework": "vllm-customized", "intentId": "f71d740509f8423592fc5a0a13b33184", "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": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669517+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396256+00:00", "framework": "vllm", "intentId": "ff7b62b83d98446cabc7fb74c7570ca8", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396885+00:00", "framework": "vllm-customized", "intentId": "5235a8707198491ea1233e1fcd01e618", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669514+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396208+00:00", "framework": "vllm", "intentId": "94c16b015a0c4e71bc73ac86bfa0bbbe", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396942+00:00", "framework": "vllm-customized", "intentId": "8df84161e91e400bba885a745f170d1c", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669511+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396160+00:00", "framework": "vllm", "intentId": "38a7dd9b18ba4c7c9371dccadc84447c", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396998+00:00", "framework": "vllm-customized", "intentId": "f38faa57ee3a4cfa8d7d2aab2742f475", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669508+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396118+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9e37f06b53d24883a7d53f9e24f39b2e", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397054+00:00", "framework": "vllm-customized", "intentId": "ea5f73eb3c6e4078b7a2e66235a51c43", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669504+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396074+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2fe77a24cf8e4a0abaf14777dad91edc", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397111+00:00", "framework": "vllm-customized", "intentId": "13a6d043f4334d8ab928bb0eb5e2c117", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669501+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.396018+00:00", "framework": "vllm", "intentId": "c3200696583b4433a5f59657566dde41", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397176+00:00", "framework": "vllm-customized", "intentId": "9d71bca1a7d449c0aacd93db4a8a4799", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669499+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395961+00:00", "framework": "vllm", "intentId": "ce5f9688359e4aa790142fce9f70a2b9", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397233+00:00", "framework": "vllm-customized", "intentId": "f7ac0ba7d47447209fe10abc780cf0c8", "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": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669495+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395913+00:00", "framework": "vllm_tokenizer_patch", "intentId": "87bc0b381f724f6db140e2ee96321071", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397290+00:00", "framework": "vllm-customized", "intentId": "ec2fb55fdae94667855de87071d2a35b", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669492+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395863+00:00", "framework": "vllm_tokenizer_patch", "intentId": "156d6b4cbfa741a6828cd757ef09407a", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397347+00:00", "framework": "vllm-customized", "intentId": "29b6a3fa586041c48fc73d55cbbf5266", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669489+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395813+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5d87acf8315149a3acfdba428916065b", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397404+00:00", "framework": "vllm-customized", "intentId": "168afc3af4e24c67949dbb90e5cd8aa6", "lastModified": "2026-08-24T19:40:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669485+00:00", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395750+00:00", "framework": "vllm-mlu", "intentId": "c478a4b72c1f4d6f9e73dab64a2a06f0", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397461+00:00", "framework": "vllm-customized", "intentId": "4d3798bcc3ef44d9bf02d1f9c8520199", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669482+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395688+00:00", "framework": "vllm-mlu", "intentId": "137841d4a0c14c8b9ad73d089807b62c", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397518+00:00", "framework": "vllm-customized", "intentId": "9dec1cbd9d0a4eaf8bc2e303b5f29b6d", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669479+00:00", "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395611+00:00", "framework": "vllm-mlu", "intentId": "a975e9bbd08f405d8153bc8a8db65846", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397574+00:00", "framework": "vllm-customized", "intentId": "eb4fde14582f4513bef9b3721f7cddfc", "lastModified": "2026-08-24T18:06:52+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669475+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395546+00:00", "framework": "vllm-mlu", "intentId": "635035ba1cb1499e8e3c4f9b4514eee8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397631+00:00", "framework": "vllm-customized", "intentId": "511e4a8e2c4b4d2894cebe63b080ce28", "lastModified": "2026-08-24T18:12:10+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669472+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395498+00:00", "framework": "vllm", "intentId": "d24898ec08d04b0eaa84b1021f858592", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397700+00:00", "framework": "vllm-customized", "intentId": "9f65bb901dba40a990860f323cade531", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669469+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395450+00:00", "framework": "vllm", "intentId": "a4bfeea8df3f4084bbd3c03d67dbb80f", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397757+00:00", "framework": "vllm-customized", "intentId": "9439ad472a144bde8a751b64d4b8959e", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669466+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395402+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dbebf748088d493aa2280a0a0c96ad0b", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397815+00:00", "framework": "vllm-customized", "intentId": "6699c79379af416495fadb2a2bb5f547", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669462+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395353+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8da5a6fcddcf4b019a4415768f33aa4d", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397895+00:00", "framework": "vllm-customized", "intentId": "ac2fff845ede4e6db0a7e90796dce0b2", "lastModified": "2026-08-24T20:30:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669459+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395305+00:00", "framework": "vllm_tokenizer_patch", "intentId": "02304395dd55481c9dc4a2ae8bc87d3c", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397956+00:00", "framework": "vllm-customized", "intentId": "30a94939f5964518b2330fe23803e0e1", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669452+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395206+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b4926fba95a54a65a2ef2a1297ebe11a", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.398013+00:00", "framework": "vllm-customized", "intentId": "878d497579ab44d5baa6b918ba0aaff0", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669449+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.395157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "24f62f87033845c1a6dbb70c998bb429", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "56bea225aab940a1bb2497ea0c449398", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.398071+00:00", "framework": "vllm-customized", "intentId": "2a066644f1e548fd9121f1b78ca87dda", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669412+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.394943+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cb1e120f5cea40d890c908f7b6dcbe85", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "15e70e4268ae4d39aac3ad9d3e5137d7", "completedAt": "2026-09-21T05:41:59.133008+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:35:37.352972+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2daa2f9dbff14c9d992288891c9f6dd6", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "15e70e4268ae4d39aac3ad9d3e5137d7", "completedAt": "2026-09-21T05:41:59.133008+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:35:37.352972+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2daa2f9dbff14c9d992288891c9f6dd6", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "15e70e4268ae4d39aac3ad9d3e5137d7", "completedAt": "2026-09-21T05:41:59.133005+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:35:37.352916+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7fcefd86dcf845dd96482585ffd77a29", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "15e70e4268ae4d39aac3ad9d3e5137d7", "completedAt": "2026-09-21T05:41:59.133005+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:35:37.352916+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7fcefd86dcf845dd96482585ffd77a29", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "15e70e4268ae4d39aac3ad9d3e5137d7", "completedAt": "2026-09-21T05:41:59.133002+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:35:37.352844+00:00", "framework": "vllm_fix_tokenizer", "intentId": "59091cd528fc46498b57bf50997e9eed", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "15e70e4268ae4d39aac3ad9d3e5137d7", "completedAt": "2026-09-21T05:41:59.133002+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T05:35:37.352844+00:00", "framework": "vllm_fix_tokenizer", "intentId": "59091cd528fc46498b57bf50997e9eed", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
@@ -2282,56 +2282,3 @@
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794226+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557275+00:00", "framework": "vllm", "intentId": "5e8dcafcbf99443aa10e18d48029ab5b", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794226+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557275+00:00", "framework": "vllm", "intentId": "5e8dcafcbf99443aa10e18d48029ab5b", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794223+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557209+00:00", "framework": "vllm", "intentId": "bfec3340f77e4fca9117e75bc9942e7f", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794223+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557209+00:00", "framework": "vllm", "intentId": "bfec3340f77e4fca9117e75bc9942e7f", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794220+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557158+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a34cd24bb50840f7816615f950193622", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794220+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557158+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a34cd24bb50840f7816615f950193622", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794216+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557113+00:00", "framework": "vllm-patch-tokenizer", "intentId": "55a2331d25014a85a794a2a19a7654a4", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794213+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557060+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3c023b34f3ed41bc9975914a46657ef7", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794210+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.557017+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ee98b74486f045edb99288e1c9847cbb", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794208+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556974+00:00", "framework": "vllm-patch-tokenizer", "intentId": "34a99f392ef44f78bf36d4751329fc8e", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794205+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556931+00:00", "framework": "vllm-patch-tokenizer", "intentId": "32bd89ce57e34bf5bc6e41ae090bab51", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794203+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556888+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9f43e9d56fde4902b2c8bb9e7164bde4", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794200+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556845+00:00", "framework": "vllm-patch-tokenizer", "intentId": "592d807045b64c699612ba48cdbcc548", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794197+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556784+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c1da68243c72435fbc06bd67857b2eb8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794194+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556741+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a22915bfb7044232ab0adacfef9ba7f7", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794192+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556698+00:00", "framework": "vllm-patch-tokenizer", "intentId": "6e8fda31d35e4408933dd1d5d364e5b6", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794188+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556636+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2af0c3193d274e5db701c93055965804", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794185+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556593+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4edae1c7f39c4ed8b65d9bde94f069a9", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794182+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556549+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fc63636bea15486d80b9cbf6fdd004ca", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794180+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556504+00:00", "framework": "vllm_fix_tokenizer", "intentId": "98f6d4a50b9440d2af0102b639a1b1c4", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794176+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556428+00:00", "framework": "vllm", "intentId": "07c722fa36d9457cb946ae0a7a8ddc20", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794173+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556370+00:00", "framework": "vllm", "intentId": "12d53e8e6e1345289173ac3a2c8f1a92", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794170+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556313+00:00", "framework": "vllm", "intentId": "43554e5bf87a4d948a19bb8a94f86eb5", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794166+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556255+00:00", "framework": "vllm", "intentId": "e072741879bc4f6a81e0aa92d9822d6e", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794163+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556197+00:00", "framework": "vllm", "intentId": "5e3a256f580142d688aa695d42c6e2cc", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794160+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556124+00:00", "framework": "vllm", "intentId": "40b69618615a47d5842993e4457fd9eb", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794156+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556066+00:00", "framework": "vllm", "intentId": "449382819eb34dec8a4b035eeb9a1c80", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794153+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.556009+00:00", "framework": "vllm", "intentId": "248e6f5e4ec74fe48f006a41fff88c34", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794147+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.555893+00:00", "framework": "vllm", "intentId": "9917542074c54088a1943221e843ecf6", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794144+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.555835+00:00", "framework": "vllm", "intentId": "687e6b89b8ad4e6da940dbdce5184a3b", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794140+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.555776+00:00", "framework": "vllm", "intentId": "6595ddb8bbc74ba1b422f33a4f33ac8c", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794136+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.555689+00:00", "framework": "vllm", "intentId": "9ebf4b5a63364515a3533b500eaa326e", "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "3dd27b1156b743d6b947bb468f7acbbc", "completedAt": "2026-09-21T04:43:31.794117+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:37:37.555551+00:00", "framework": "vllm", "intentId": "d9693f77ce2c4f9693400b3e85c40031", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "44c8e43b42fd4f4780fe0860d4cb2b68", "completedAt": "2026-09-21T04:33:23.315409+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:32:37.179385+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b802c8a0ecf643119fc3c6354b0f00c4", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "44c8e43b42fd4f4780fe0860d4cb2b68", "completedAt": "2026-09-21T04:33:23.315406+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:32:37.179329+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dfb8166be31b4a8b850891d37ef80948", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "44c8e43b42fd4f4780fe0860d4cb2b68", "completedAt": "2026-09-21T04:33:23.315404+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:32:37.179273+00:00", "framework": "vllm_fix_tokenizer", "intentId": "af28d6d4246a4655b645d4da9309d546", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "44c8e43b42fd4f4780fe0860d4cb2b68", "completedAt": "2026-09-21T04:33:23.315400+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:32:37.179214+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2d49bf1db54c4c9d9777f4bb0b425e97", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "44c8e43b42fd4f4780fe0860d4cb2b68", "completedAt": "2026-09-21T04:33:23.315396+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:32:37.179115+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04e43fed60b04ad28bb686ffffe5adb6", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "44c8e43b42fd4f4780fe0860d4cb2b68", "completedAt": "2026-09-21T04:33:23.315375+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:32:37.178980+00:00", "framework": "vllm_fix_tokenizer", "intentId": "19cf16237d8b49d1bfe3510dc5362de8", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398255+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712670+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d8aeb98b29734e7d97ebd9e27fc65465", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398252+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712610+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0094f9cb801145eebec330b0993bc191", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398249+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712554+00:00", "framework": "vllm_fix_tokenizer", "intentId": "109d4e6878534a4687360df2b6a21f97", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398246+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712499+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a2278f28608640639666f28e2e5b2576", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398244+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712444+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1958b00247a04ec9beb9b337aa44bcd6", "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398241+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712386+00:00", "framework": "vllm", "intentId": "5cb6c46ce836440bb5716c5773b753ae", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398237+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712329+00:00", "framework": "vllm", "intentId": "0ff9377fa0cc4145aaf1877a58d48c26", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398235+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712270+00:00", "framework": "vllm", "intentId": "cf3eadcf8c094e99a1ba460899bdf995", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398232+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712213+00:00", "framework": "vllm", "intentId": "53a11bd42d684c1f88da3990453640fb", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398229+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712155+00:00", "framework": "vllm", "intentId": "241c0ca7c90d43b7b06bafef6b462b57", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398227+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712096+00:00", "framework": "vllm", "intentId": "e7f245554c104e61be05289196113cb6", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398224+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.712046+00:00", "framework": "vllm", "intentId": "5158e91d6387409284c40c9b62930401", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398221+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.711995+00:00", "framework": "vllm", "intentId": "d88013e15bdf49b0aa67aa2b91a19868", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398218+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.711943+00:00", "framework": "vllm", "intentId": "e3125b0ddc3848cc96cac812a153156b", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398215+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.711901+00:00", "framework": "vllm", "intentId": "3428d964e1b14805afae0e8cba2eba20", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398213+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.711859+00:00", "framework": "vllm", "intentId": "a35bff6dc9dc4f04bdba609fe66fa94b", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398210+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.711818+00:00", "framework": "vllm", "intentId": "638a6ef1492a4309ac45f95ebf561dd4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398207+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.711767+00:00", "framework": "vllm", "intentId": "28a88af9b9c84ac48e0850d68c566441", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398204+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.711702+00:00", "framework": "vllm", "intentId": "217ca9a65e9b496894f6393d9028046d", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d7eb8c36d704d7fad0bd0106dea8354", "completedAt": "2026-09-21T04:32:36.398201+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T04:25:27.711653+00:00", "framework": "vllm", "intentId": "83d5153a96464463a4fb1b056f59c391", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}

10
.modelhub_state/routing_intelligence.json
View File

@@ -1,6 +1,6 @@
{ {
"acceptedByCategory": { "acceptedByCategory": {
"unified_success_first": 2118 "unified_success_first": 2121
}, },
"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": 141, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 141,
"text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|llamacpp": 13,
"text-generation|Ascend_910-b4|vllm": 22, "text-generation|Ascend_910-b4|vllm": 22,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 133, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 136,
"text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm": 81,
"text-generation|Biren_166m|vllm_fix_tokenizer": 117, "text-generation|Biren_166m|vllm_fix_tokenizer": 117,
"text-generation|Cambricon_mlu-370-x4|vllm": 68, "text-generation|Cambricon_mlu-370-x4|vllm": 68,
@@ -38,8 +38,8 @@
"text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 120 "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 120
}, },
"acceptedSinceRefresh": 2118, "acceptedSinceRefresh": 2121,
"acceptedTotal": 2118, "acceptedTotal": 2121,
"generatedAt": "2026-09-21T05:42:36.793787+00:00", "generatedAt": "2026-09-21T06:33:07.605581+00:00",
"version": 1 "version": 1
} }

3
ledger/submissions.jsonl
View File

@@ -1163,3 +1163,6 @@
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T20:09:24.405809+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986872", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T20:09:24.405809+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986872", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T20:09:24.421834+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T20:09:24.421834+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "submitTime": "2026-09-21T06:25:35.861357+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995262", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "submitTime": "2026-09-21T06:25:35.859746+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995261", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}

14
manifest.json
View File

@@ -10,16 +10,16 @@
".modelhub_state/queue_cleanup_latest.json": "0de105598c9478c6cb1c89a58c4794a2395e2c58f508a89a0e4c6fd6e5c312a7", ".modelhub_state/queue_cleanup_latest.json": "0de105598c9478c6cb1c89a58c4794a2395e2c58f508a89a0e4c6fd6e5c312a7",
".modelhub_state/recent_outcomes.jsonl": "76fe67771755e6301126f05f3e455cdbd8ac5c3ae03d76c56c8d79bf16fbd273", ".modelhub_state/recent_outcomes.jsonl": "76fe67771755e6301126f05f3e455cdbd8ac5c3ae03d76c56c8d79bf16fbd273",
".modelhub_state/recovery_active_tasks.jsonl": "517e87b09099a844ef923cb8852caf4ea2047e2284384aa8799cb7da4d527c78", ".modelhub_state/recovery_active_tasks.jsonl": "517e87b09099a844ef923cb8852caf4ea2047e2284384aa8799cb7da4d527c78",
".modelhub_state/recovery_intents.jsonl": "1e28a3e683a369270f71f321b4125c586d8c1d042a18df5307e7c4d64cfbf0ed", ".modelhub_state/recovery_intents.jsonl": "412bdfddc7546508138ebdfebadd779a9cfc16495a0b36d66eb6a98e85a1f1c1",
".modelhub_state/routing_intelligence.json": "ea955c6b3c0bf7864fd2cf8ec51a66c344763482eb7715662096bcaceb384776", ".modelhub_state/routing_intelligence.json": "dfd95458c8a60ec74d52cd7b854ee46a3a6e947f811620801a4feea04ec55219",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "35607db286351fd8ea183d983813176f49488c34f0544afa6f838d26a5548746", "ledger/submissions.jsonl": "12abdc0542ec04ff4c626a3f26000a8d779b71f3756ca21ed580e2445aacda6e",
"outcomes/submissions.jsonl": "075cfefe480ae3d968b13e778678683c43385f790f99c395f31f084f5dfde7f8" "outcomes/submissions.jsonl": "3dc5e1549c13358aeb9aa3f1a5f3a24dcaf7050cfb9de431b2684fd7894b9339"
}, },
"generation": 11258, "generation": 11259,
"phase": "intent", "phase": "result",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-21T06:25:22.536138+00:00", "updatedAt": "2026-09-21T06:33:07.809614+00:00",
"writerId": "8b35139af6674067a339a670222d4b67" "writerId": "8b35139af6674067a339a670222d4b67"
} }

3
outcomes/submissions.jsonl
View File

@@ -1118,3 +1118,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T05:25:16.370644+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994586", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T05:25:16.370644+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994586", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612468}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T05:28:10.540389+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994617", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612468}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T05:28:10.540389+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994617", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 13.067, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 8740644030, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11692052998}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T05:42:36.743182+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4994779", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 13.067, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 8740644030, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11692052998}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T05:42:36.743182+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4994779", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "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": 9093197700, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093197700}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T06:25:35.861357+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995262", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013064, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197403, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093197403}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T06:25:35.859746+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995261", "taskType": "text-generation", "verifyResult": null}