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

state: generation 11014 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 00:01:50 +00:00
parent 83f8034607
commit 111f461d80
5 changed files with 77 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

161
.modelhub_state/recovery_intents.jsonl
View File

@@ -1862,61 +1862,61 @@
{"batchId": "dcfdc50f26d34a898ad29104360aee46", "completedAt": "2026-09-20T23:23:58.624916+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:23:50.532836+00:00", "framework": "vllm-customized", "intentId": "ce7bbcc0a94e474fae189414d42e70b5", "lastModified": "2026-09-14T13:40:21+00:00", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "reason": null, "reconciledAt": "2026-09-20T23:50:39.603310+00:00", "repoId": "IntervitensInc/kek_mk3", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4989458", "taskType": "text-generation"} {"batchId": "dcfdc50f26d34a898ad29104360aee46", "completedAt": "2026-09-20T23:23:58.624916+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:23:50.532836+00:00", "framework": "vllm-customized", "intentId": "ce7bbcc0a94e474fae189414d42e70b5", "lastModified": "2026-09-14T13:40:21+00:00", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "reason": null, "reconciledAt": "2026-09-20T23:50:39.603310+00:00", "repoId": "IntervitensInc/kek_mk3", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4989458", "taskType": "text-generation"}
{"batchId": "dcfdc50f26d34a898ad29104360aee46", "completedAt": "2026-09-20T23:23:58.624920+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:23:50.532900+00:00", "framework": "vllm-customized", "intentId": "6fba7c6c926240eaae6c0a0ac6f5a021", "lastModified": "2026-09-20T14:39:19+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "reason": null, "reconciledAt": "2026-09-20T23:50:39.602883+00:00", "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4989456", "taskType": "text-generation"} {"batchId": "dcfdc50f26d34a898ad29104360aee46", "completedAt": "2026-09-20T23:23:58.624920+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:23:50.532900+00:00", "framework": "vllm-customized", "intentId": "6fba7c6c926240eaae6c0a0ac6f5a021", "lastModified": "2026-09-20T14:39:19+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "reason": null, "reconciledAt": "2026-09-20T23:50:39.602883+00:00", "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4989456", "taskType": "text-generation"}
{"batchId": "455a4890ba60469d99a08615d610e604", "completedAt": "2026-09-20T23:30:59.854262+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:30:58.699529+00:00", "framework": "vllm", "intentId": "9c2bea264085439d9c3b740c2652792c", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "reason": null, "reconciledAt": "2026-09-20T23:50:39.604923+00:00", "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4989519", "taskType": "text-generation"} {"batchId": "455a4890ba60469d99a08615d610e604", "completedAt": "2026-09-20T23:30:59.854262+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:30:58.699529+00:00", "framework": "vllm", "intentId": "9c2bea264085439d9c3b740c2652792c", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "reason": null, "reconciledAt": "2026-09-20T23:50:39.604923+00:00", "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4989519", "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294034+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cccd1c22862d4c338cdc7697b93410bf", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409596+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294203+00:00", "framework": "vllm", "intentId": "b4e5d44b2abd4e6489798f73c363c1dd", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "reason": null, "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4989936", "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294155+00:00", "framework": "vllm_fix_tokenizer", "intentId": "383d6398a9c241b89a5fc07dbce3275b", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409624+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294684+00:00", "framework": "vllm", "intentId": "f535111b6c5e46eab81c4975f6c22884", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "reason": null, "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4989937", "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294203+00:00", "framework": "vllm", "intentId": "b4e5d44b2abd4e6489798f73c363c1dd", "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": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409648+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295092+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bcff22fcbd3c49979186dc7cd34eaf93", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4989961", "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294266+00:00", "framework": "vllm", "intentId": "c585753ca22d4de0aa7506f5b8368380", "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": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409763+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296597+00:00", "framework": "vllm", "intentId": "7a8bc032929c49778a43693675f38792", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "reason": null, "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4989991", "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294325+00:00", "framework": "vllm", "intentId": "1a8b50128aac4685879530f3c1b7f87a", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409769+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296716+00:00", "framework": "vllm", "intentId": "770fe7e54c19496782bf93e98a91d514", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294384+00:00", "framework": "vllm", "intentId": "d82ba6abfa1d4d46becebfc0d4c64ee8", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409766+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296651+00:00", "framework": "vllm", "intentId": "69ae61e8595a48abb9600a2cb3a58cd2", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294441+00:00", "framework": "vllm", "intentId": "673b972157504ac8a2b8d3912392e41b", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409760+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296541+00:00", "framework": "vllm", "intentId": "7c4c025ff23f43e693a0ddf9ad64a41a", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294499+00:00", "framework": "vllm", "intentId": "73fe840d5aed420f8f367913b98be1e4", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409757+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296498+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9eb00e868b154d959ea66f454d7b7116", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294556+00:00", "framework": "vllm", "intentId": "be89658e3e3a469f8e08ef8dd7dbf2a1", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409754+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296456+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bd53b609ee574f2285f1a618108a259b", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294621+00:00", "framework": "vllm", "intentId": "9640d0ea4b28474fba9a46c1c4ead978", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409751+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296413+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d9a37536fdd6461395a5c54977e69fd5", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294684+00:00", "framework": "vllm", "intentId": "f535111b6c5e46eab81c4975f6c22884", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409749+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296364+00:00", "framework": "vllm_fix_tokenizer", "intentId": "755e1ed8540c476e93c7418137ff8170", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294742+00:00", "framework": "vllm", "intentId": "d03c5ebcc6ba4faba602b61e2389698c", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409746+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296322+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b914f5f7694a47e7ae2913044883a2f1", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294799+00:00", "framework": "vllm", "intentId": "832cd72d07624c4a951b2bf96a702d77", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409743+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296279+00:00", "framework": "vllm_fix_tokenizer", "intentId": "59bc6044d8c24e158e7acb44040f7903", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294856+00:00", "framework": "vllm", "intentId": "34bfcce23a9a434e89b878e07ef02c8b", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409740+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296237+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e84f83c6bfb346f8a4597276f1c459f7", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294920+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d91e6a316a84fa39de96952d299222a", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409737+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296194+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bada731ae47b4e2d803d201a98641600", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294963+00:00", "framework": "vllm_fix_tokenizer", "intentId": "98674de3a84e4875bbcee75cb814f924", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409734+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296152+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0882d47574aa4075a09379a6a0066c89", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295007+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dcff6ec795a7423a87b958598038cedc", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409731+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296109+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d558c910009f4f4f9ea9ebf2f5f4181c", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295050+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fff835541a1c46069555bd9dc77d3a6c", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409728+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296066+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8502f2d12c4d49768a5fcd7be1e7be55", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295092+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bcff22fcbd3c49979186dc7cd34eaf93", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409725+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296023+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4a1a2c60ec0b41968ca511b503af33d5", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295135+00:00", "framework": "vllm_fix_tokenizer", "intentId": "28011675e6e34597a74ea1a0b9c3cf72", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409722+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295974+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cac9ca57673e4017ba1e442c1565d0e6", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295178+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d85206797e9a4273bd8da8fe93297269", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409719+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295932+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bbf3ab55840643fb873741d3961b7397", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295220+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f78b8098e2534563b962393b1f9cf4a0", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409716+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295889+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e050d192abf7476eb418bb02651d7cd7", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295263+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2b9b772a9ee74507ac1cdcb6b20cb4fb", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409713+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295847+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4ac97825b51b4e1ab98e25a0510561e9", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295312+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4087c9d7e8f946d09adb9f84e808fb08", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409709+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295804+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aa71ad5e95664622a8f7d9d826176af5", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295355+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2e747a2394014a689d7140d2762b417c", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409706+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295762+00:00", "framework": "vllm_fix_tokenizer", "intentId": "346ad53078c44d13955e5877b02c8053", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295398+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2a55049c232f4fd183009fb150880f4a", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409703+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295718+00:00", "framework": "vllm_fix_tokenizer", "intentId": "25851070e3ff4a6f945ff4ee4543f59d", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295441+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e5c06290e3f34c23a53b8999d97bae07", "lastModified": "2026-08-31T14:36:00+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409700+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295660+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3505e12306a6417680be096d9fd0651e", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295484+00:00", "framework": "vllm_fix_tokenizer", "intentId": "09b07c0f3cba4246aba122f9cc7e8249", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409696+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4a07e1345aa84d0eae8806da0b74a8e7", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295527+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b2b3d17571a740dca82a0feaffd2c281", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409694+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "05ebf8de1e0b44fcb2526bab5b8967ae", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "05ebf8de1e0b44fcb2526bab5b8967ae", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409691+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295527+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b2b3d17571a740dca82a0feaffd2c281", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4a07e1345aa84d0eae8806da0b74a8e7", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409688+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295484+00:00", "framework": "vllm_fix_tokenizer", "intentId": "09b07c0f3cba4246aba122f9cc7e8249", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295660+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3505e12306a6417680be096d9fd0651e", "lastModified": "2026-08-24T20:02:14+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409686+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295441+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e5c06290e3f34c23a53b8999d97bae07", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295718+00:00", "framework": "vllm_fix_tokenizer", "intentId": "25851070e3ff4a6f945ff4ee4543f59d", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409682+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295398+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2a55049c232f4fd183009fb150880f4a", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295762+00:00", "framework": "vllm_fix_tokenizer", "intentId": "346ad53078c44d13955e5877b02c8053", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409679+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295355+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2e747a2394014a689d7140d2762b417c", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295804+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aa71ad5e95664622a8f7d9d826176af5", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409663+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295312+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4087c9d7e8f946d09adb9f84e808fb08", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295847+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4ac97825b51b4e1ab98e25a0510561e9", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409660+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295263+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2b9b772a9ee74507ac1cdcb6b20cb4fb", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295889+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e050d192abf7476eb418bb02651d7cd7", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409657+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295220+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f78b8098e2534563b962393b1f9cf4a0", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295932+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bbf3ab55840643fb873741d3961b7397", "lastModified": "2026-08-26T13:13:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409653+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295178+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d85206797e9a4273bd8da8fe93297269", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295974+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cac9ca57673e4017ba1e442c1565d0e6", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409651+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295135+00:00", "framework": "vllm_fix_tokenizer", "intentId": "28011675e6e34597a74ea1a0b9c3cf72", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296023+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4a1a2c60ec0b41968ca511b503af33d5", "lastModified": "2026-09-03T06:52:45+00:00", "modelAddress": "https://modelscope.cn/models/bharatgenai/Param2-17B-A2.4B-Thinking", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409645+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295050+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fff835541a1c46069555bd9dc77d3a6c", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296066+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8502f2d12c4d49768a5fcd7be1e7be55", "lastModified": "2026-08-28T09:38:42+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409642+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.295007+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dcff6ec795a7423a87b958598038cedc", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296109+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d558c910009f4f4f9ea9ebf2f5f4181c", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409639+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294963+00:00", "framework": "vllm_fix_tokenizer", "intentId": "98674de3a84e4875bbcee75cb814f924", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296152+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0882d47574aa4075a09379a6a0066c89", "lastModified": "2026-09-08T15:40:32+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409636+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294920+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d91e6a316a84fa39de96952d299222a", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296194+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bada731ae47b4e2d803d201a98641600", "lastModified": "2026-08-26T20:08:51+00:00", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409633+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294856+00:00", "framework": "vllm", "intentId": "34bfcce23a9a434e89b878e07ef02c8b", "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": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296237+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e84f83c6bfb346f8a4597276f1c459f7", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409630+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294799+00:00", "framework": "vllm", "intentId": "832cd72d07624c4a951b2bf96a702d77", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296279+00:00", "framework": "vllm_fix_tokenizer", "intentId": "59bc6044d8c24e158e7acb44040f7903", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409627+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294742+00:00", "framework": "vllm", "intentId": "d03c5ebcc6ba4faba602b61e2389698c", "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": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296322+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b914f5f7694a47e7ae2913044883a2f1", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409620+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294621+00:00", "framework": "vllm", "intentId": "9640d0ea4b28474fba9a46c1c4ead978", "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": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296364+00:00", "framework": "vllm_fix_tokenizer", "intentId": "755e1ed8540c476e93c7418137ff8170", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409617+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294556+00:00", "framework": "vllm", "intentId": "be89658e3e3a469f8e08ef8dd7dbf2a1", "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": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296413+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d9a37536fdd6461395a5c54977e69fd5", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409614+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294499+00:00", "framework": "vllm", "intentId": "73fe840d5aed420f8f367913b98be1e4", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296456+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bd53b609ee574f2285f1a618108a259b", "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": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409611+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294441+00:00", "framework": "vllm", "intentId": "673b972157504ac8a2b8d3912392e41b", "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": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296498+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9eb00e868b154d959ea66f454d7b7116", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409608+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294384+00:00", "framework": "vllm", "intentId": "d82ba6abfa1d4d46becebfc0d4c64ee8", "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": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296541+00:00", "framework": "vllm", "intentId": "7c4c025ff23f43e693a0ddf9ad64a41a", "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": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409605+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294325+00:00", "framework": "vllm", "intentId": "1a8b50128aac4685879530f3c1b7f87a", "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": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296597+00:00", "framework": "vllm", "intentId": "7a8bc032929c49778a43693675f38792", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409601+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294266+00:00", "framework": "vllm", "intentId": "c585753ca22d4de0aa7506f5b8368380", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296651+00:00", "framework": "vllm", "intentId": "69ae61e8595a48abb9600a2cb3a58cd2", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409592+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294155+00:00", "framework": "vllm_fix_tokenizer", "intentId": "383d6398a9c241b89a5fc07dbce3275b", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "0175127faec64360a6228d6ecb7d78c2", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.296716+00:00", "framework": "vllm", "intentId": "770fe7e54c19496782bf93e98a91d514", "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": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} {"batchId": "0175127faec64360a6228d6ecb7d78c2", "completedAt": "2026-09-21T00:01:50.409564+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:55:28.294034+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cccd1c22862d4c338cdc7697b93410bf", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778811+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625471+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b8196779bbc54c5bbb81b09c273ee2d8", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778811+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625471+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b8196779bbc54c5bbb81b09c273ee2d8", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778808+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c7c0d6c8881547889f550e1bdcd822a1", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778808+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c7c0d6c8881547889f550e1bdcd822a1", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778806+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625361+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ef8a7a87f66242bb985c1b1f6ed9a9d2", "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": "0d50ffe368744e9dbfa0d829d9cce7f6", "completedAt": "2026-09-20T23:23:25.778806+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T23:18:40.625361+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ef8a7a87f66242bb985c1b1f6ed9a9d2", "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"}
@@ -2166,54 +2166,3 @@
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227798+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572877+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3c6d840046034efb91d8a4d399840cd0", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227798+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572877+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3c6d840046034efb91d8a4d399840cd0", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227795+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572801+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f57e12c2e7874a9ca299d1a71c7b8136", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227795+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572801+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f57e12c2e7874a9ca299d1a71c7b8136", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227793+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572725+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2e1045afb6c24dff9a2c0ae54778a911", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227793+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572725+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2e1045afb6c24dff9a2c0ae54778a911", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227790+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572641+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b228725fe20a418aa477a1f547548de5", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227787+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572565+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5de6f58110d34692aa3a9939e35594ee", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227784+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572460+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0f4a5616db2e43bf8f0ab560fc43f1c1", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227781+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572384+00:00", "framework": "vllm_fix_tokenizer", "intentId": "71c7ee413baa4164b6c860276f7e6d88", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227778+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572307+00:00", "framework": "vllm_fix_tokenizer", "intentId": "06b8dca798aa49e69ec7ffde32b5179c", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227776+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572230+00:00", "framework": "vllm_fix_tokenizer", "intentId": "101a3b1653634fc0bfc411872eb5c772", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227773+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572154+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3bed056b221646d298a1d1acd1c8d693", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227770+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572078+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8f52e8792a4240d0b5e9451c956b6d13", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227767+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572002+00:00", "framework": "vllm_fix_tokenizer", "intentId": "18eee6aa3a0a4f639e13f7fd82b195a7", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227765+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571925+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7cd832a8bff449ce9d271f617c2f00f7", "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227762+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571849+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e209051f0cf34cb7832bde96a049c29e", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227759+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571773+00:00", "framework": "vllm_fix_tokenizer", "intentId": "beba8a02a4c74fdd826aed861f2c6d15", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227756+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571696+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ca2484634874410b8bec28b7e2ea1026", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227752+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e0c6c5b21636468bb141cccbd1b834a7", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227749+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571534+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9ffedea7bc044fe99e29884589b1707f", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227743+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571354+00:00", "framework": "vllm", "intentId": "786a70da19a840ec8e24a287d9941dca", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227740+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571247+00:00", "framework": "vllm", "intentId": "9a0918825a15471ca078af3e2eec427c", "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": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227736+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571127+00:00", "framework": "vllm-mlu", "intentId": "a5018ac5d0ca4543b695b01e0d6c420c", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227733+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571059+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cf9260fa2e774625ba58295aacde97d1", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227730+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.570992+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5b8e5f37e4f543ea87ffe23b38a65bd7", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227726+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.570920+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c946c063861d4c4e9da8c5d8e348f6bc", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "67a81b105def48f8a969ca85668e5231", "completedAt": "2026-09-20T22:07:18.227702+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.570798+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b9057a72a819402a83f389f215adaf5c", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268918+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670785+00:00", "framework": "vllm_fix_tokenizer", "intentId": "157e9942a18f48e483882f1df3f63e0c", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268915+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670730+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2dc6833c4bbf4be9befa6f9639bfe7c8", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268913+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670676+00:00", "framework": "vllm_fix_tokenizer", "intentId": "480abb8f7bd342c096c3270e01d123d9", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268910+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670616+00:00", "framework": "vllm_fix_tokenizer", "intentId": "88020c9c009c446cbe3f99175326dd21", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268908+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670561+00:00", "framework": "vllm_fix_tokenizer", "intentId": "db54ab67e90a42238fa327636765be61", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268905+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670506+00:00", "framework": "vllm_fix_tokenizer", "intentId": "87adf1c068e1427e999df87913f6ad20", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268902+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670446+00:00", "framework": "vllm", "intentId": "510b5ba064dd4c14a4c66f61cc4406b2", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268900+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670405+00:00", "framework": "vllm", "intentId": "903a9ffd010d4b0b81f0f542dee99d14", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268897+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670364+00:00", "framework": "vllm", "intentId": "73adbbe22b9d404a812954e6f9b90f5e", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268895+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670322+00:00", "framework": "vllm", "intentId": "62af446385af437bbcc11631117ed627", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268892+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670280+00:00", "framework": "vllm", "intentId": "e5dac5e544684cca9640d925ee9c483d", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268890+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670238+00:00", "framework": "vllm", "intentId": "820bf822f585495f9bb142dd49078188", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268887+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670197+00:00", "framework": "vllm", "intentId": "399f1f50a6164a4d9858bd20eb590893", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268885+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670153+00:00", "framework": "vllm", "intentId": "7964337ba4224402afae338ce2510649", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268882+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670094+00:00", "framework": "vllm-customized", "intentId": "115583d3a1f64641a0a4c49fc9652697", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268880+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670036+00:00", "framework": "vllm-customized", "intentId": "6200decf7d6a4ebd9cae3676a38483fd", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268877+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669976+00:00", "framework": "vllm-customized", "intentId": "805cfdbb7a194db0baba90c76aa7e17b", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268875+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669914+00:00", "framework": "vllm-customized", "intentId": "98cc5f07ca284f6eb32786f08476fb97", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268872+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669874+00:00", "framework": "vllm_tokenizer_patch", "intentId": "112b8f3b4b82414a8d015d9905ebf95f", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268870+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669821+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e3bd527e32354b8d9cded9cd4045e3b0", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268867+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669773+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d38a42a2683643a7a2e50a26054ef8e9", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268865+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669250+00:00", "framework": "vllm_tokenizer_patch", "intentId": "142d9f8cc2714bb8bfbf35cfbf4b69b7", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268862+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669203+00:00", "framework": "vllm", "intentId": "372a63fa80744a8d87fbd647196064a0", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268859+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669155+00:00", "framework": "vllm", "intentId": "f4bba108470e47eb86ded0a35c622397", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268857+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669107+00:00", "framework": "vllm", "intentId": "fe1702c2369749498d97a99dd5049fc3", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268854+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669058+00:00", "framework": "vllm", "intentId": "68cb4f7c5678457fa55f477d873722da", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268851+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.669007+00:00", "framework": "vllm", "intentId": "b503dad8c3594cc2ba18a1771d119ec3", "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": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268848+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.668964+00:00", "framework": "vllm-patch-tokenizer", "intentId": "642a85c817c9496e932a123a61295e70", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268845+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.668921+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c1397c7149a9456ca0d19a92af7c3422", "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"}

14
.modelhub_state/routing_intelligence.json
View File

@@ -1,6 +1,6 @@
{ {
"acceptedByCategory": { "acceptedByCategory": {
"unified_success_first": 2002 "unified_success_first": 2006
}, },
"acceptedByRoute": { "acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|llamacpp": 17,
@@ -9,8 +9,8 @@
"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": 130, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 130,
"text-generation|Biren_166m|vllm": 79, "text-generation|Biren_166m|vllm": 80,
"text-generation|Biren_166m|vllm_fix_tokenizer": 66, "text-generation|Biren_166m|vllm_fix_tokenizer": 67,
"text-generation|Cambricon_mlu-370-x4|vllm": 52, "text-generation|Cambricon_mlu-370-x4|vllm": 52,
"text-generation|Cambricon_mlu-370-x4|vllm-customized": 4, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 4,
"text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82,
@@ -25,7 +25,7 @@
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 40, "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 40,
"text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 3, "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 3,
"text-generation|Iluvatar_mrv-100|vllm": 61, "text-generation|Iluvatar_mrv-100|vllm": 61,
"text-generation|Kunlunxin_p-800|vllm": 31, "text-generation|Kunlunxin_p-800|vllm": 33,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 175, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 175,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 70, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 70,
"text-generation|MetaX_c-500|vllm": 104, "text-generation|MetaX_c-500|vllm": 104,
@@ -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": 117 "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 117
}, },
"acceptedSinceRefresh": 2002, "acceptedSinceRefresh": 2006,
"acceptedTotal": 2002, "acceptedTotal": 2006,
"generatedAt": "2026-09-20T23:30:59.795279+00:00", "generatedAt": "2026-09-21T00:01:50.349279+00:00",
"version": 1 "version": 1
} }

4
ledger/submissions.jsonl
View File

@@ -1158,3 +1158,7 @@
{"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", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "modelId": "neuralmagic/starcoder2-7b-FP8", "submitTime": "2026-09-20T23:55:34.970259+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4989936", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "submitTime": "2026-09-20T23:55:34.974164+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4989937", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-20T23:56:08.554994+00:00", "targetGpu": "Biren_166m", "taskId": "4989961", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "submitTime": "2026-09-21T00:00:11.334848+00:00", "targetGpu": "Biren_166m", "taskId": "4989991", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}

14
manifest.json
View File

@@ -9,16 +9,16 @@
".modelhub_state/queue_cleanup_latest.json": "87ea93bf42a8a1e24e156ef53e31bb1f4495dd95733206eb0979243c703bdc7f", ".modelhub_state/queue_cleanup_latest.json": "87ea93bf42a8a1e24e156ef53e31bb1f4495dd95733206eb0979243c703bdc7f",
".modelhub_state/recent_outcomes.jsonl": "900cc07550df51641d2bd7f6e7f8621828949aa38cd74b0a1f62ad4d60f6f04d", ".modelhub_state/recent_outcomes.jsonl": "900cc07550df51641d2bd7f6e7f8621828949aa38cd74b0a1f62ad4d60f6f04d",
".modelhub_state/recovery_active_tasks.jsonl": "97144d81c10580cfbfbcb405474d13a320a4747c07aa5b7b95550a4af6760381", ".modelhub_state/recovery_active_tasks.jsonl": "97144d81c10580cfbfbcb405474d13a320a4747c07aa5b7b95550a4af6760381",
".modelhub_state/recovery_intents.jsonl": "bf3fe2a984dc410d7c35f4b4b9b9e813e0b15f69dc03b2d947fceecb7537629a", ".modelhub_state/recovery_intents.jsonl": "81135ea108c10ea62e1ef336d62598cad354fbf7f3a42b693009a45b15d122fa",
".modelhub_state/routing_intelligence.json": "a97e1db5fb63ba910836ca39ab15cc66005d8d28e72f7b2c1784e35a1cc82487", ".modelhub_state/routing_intelligence.json": "8402e0e6efdf98db55c03ef4a3c8b0502924be8480cf87934313de1da2e04cab",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "6aa1c28acef49127f98d12bc9bca8b2f2401f6300ff37fb5b69794a395d26d88", "ledger/submissions.jsonl": "9389bd824b91b6849dee8a2d10dbbf483bbd9284b056c376d3eb4316221da32c",
"outcomes/submissions.jsonl": "a00a0d7ae735cc76e095640a8c16e88944f1066d362299a2d18bf5d3bc1ab481" "outcomes/submissions.jsonl": "af26e7263d18f48effa8a8d7b5b7ff4d45c2c7e3882fa6aaabffd127f0349df3"
}, },
"generation": 11013, "generation": 11014,
"phase": "intent", "phase": "result",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-20T23:55:28.485663+00:00", "updatedAt": "2026-09-21T00:01:50.558837+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996" "writerId": "fc715c06e24c4db2ae3e425e435db996"
} }

4
outcomes/submissions.jsonl
View File

@@ -1108,3 +1108,7 @@
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:23:58.519510+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4989458", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:23:58.519510+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4989458", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:23:58.507376+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4989456", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:23:58.507376+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4989456", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:30:59.745247+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4989519", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:30:59.745247+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4989519", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858541078}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:55:34.970259+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4989936", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449433, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449433}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:55:34.974164+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4989937", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "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": 17788663867}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T23:56:08.554994+00:00", "targetGpu": "Biren_166m", "taskId": "4989961", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251901, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251901}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:00:11.334848+00:00", "targetGpu": "Biren_166m", "taskId": "4989991", "taskType": "text-generation", "verifyResult": null}