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

state: generation 11053 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 01:17:18 +00:00
parent 178bbd87fa
commit b8a8918ea6
5 changed files with 81 additions and 130 deletions
Download Patch File Download Diff File Expand all files Collapse all files

176
.modelhub_state/recovery_intents.jsonl
View File

@@ -1882,66 +1882,66 @@
{"batchId": "801c58a410704e9f9dd21ff480faeae0", "completedAt": "2026-09-21T00:40:32.435004+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:36:42.801279+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fd92d1143c9c435cb04e1bd29d07c1cb", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T01:06:58.655035+00:00", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4990464", "taskType": "text-generation"}
{"batchId": "bfa8ed2fa7ec4618ab6db0c51699fd3e", "completedAt": "2026-09-21T00:41:04.872858+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:40:56.683923+00:00", "framework": "vllm-customized", "intentId": "eaae0dbf87bd408297fdfa4ceb9d0b6a", "lastModified": "2026-09-20T14:38:08+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "reason": null, "reconciledAt": "2026-09-21T01:06:58.654503+00:00", "repoId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990527", "taskType": "text-generation"}
{"batchId": "c1b3225b91e248cdb0d432a15809d8bd", "completedAt": "2026-09-21T01:01:39.006186+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:51:37.609781+00:00", "framework": "vllm-mlu", "intentId": "e61b5eb79d79449b94b1c7e6b6df13ee", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-21T01:06:58.655500+00:00", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734193+00:00", "framework": "vllm-mlu", "intentId": "ed678d511eca4246af651f3f2294418c", "lastModified": "2026-08-24T19:36:40+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734335+00:00", "framework": "vllm-mlu", "intentId": "e5b77fc77bff4a2ba99764a6a9666dfd", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734404+00:00", "framework": "vllm", "intentId": "0a2b8bee680f4d089856640e66603c03", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734466+00:00", "framework": "vllm", "intentId": "f8f7c19c340e425db09e4a8a3075407b", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734525+00:00", "framework": "vllm_fix_tokenizer", "intentId": "22a504f40f464defb415b1ab1d95d883", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fec9220dc12043cf9f6b2db3c0d45022", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734613+00:00", "framework": "vllm_fix_tokenizer", "intentId": "63a7f0d974604244bdf5948e23394da1", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734657+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5572f6ca884e47739141284fe6081b21", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734720+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e7be4b63f6c04cc49c0c1ad88d48ddc5", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734763+00:00", "framework": "vllm_fix_tokenizer", "intentId": "182b0b1503574e07ad3002a845e6dbf6", "lastModified": "2026-08-24T19:54:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734807+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aa4a83af0a034a2da90d23761ee79612", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734850+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9c1cc43d6ea4880a6f37a354fb912c6", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734893+00:00", "framework": "vllm_fix_tokenizer", "intentId": "146085a645454f94ba17a092500081c1", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b6bbef3120454144a22fc97f515a87d2", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734979+00:00", "framework": "vllm_fix_tokenizer", "intentId": "21aad501e2e4402da99190927fc52977", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735022+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e04592c5360443029a1eae04c7556a7c", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735065+00:00", "framework": "vllm_fix_tokenizer", "intentId": "64dc1527999f462e8a30c87f8b3ced65", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735107+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc215648713a449992e961f4d4dc88f1", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735150+00:00", "framework": "vllm_fix_tokenizer", "intentId": "edb421aa761743c0900265b91d9c43e7", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735193+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0ac0061725e74f11b0d620f74b306710", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735236+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ba0b273e7e864df8bd1b1280b9411652", "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": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735279+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dc43e678c8f6458ead1358ae2ad06e83", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735322+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04342fdc2209408188f755cc04116626", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735365+00:00", "framework": "vllm_fix_tokenizer", "intentId": "007f231871cf4b269c3e0850d0354735", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735408+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6c8ac6210032421f9156927e11487c44", "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": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735451+00:00", "framework": "vllm_fix_tokenizer", "intentId": "96474af7e05547d0a15efc730d104bc6", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735494+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9cd897e76fa049af80664ba04f63b6c3", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735537+00:00", "framework": "vllm_fix_tokenizer", "intentId": "932ee6e5868f45f386d6936b3cf74ddf", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735580+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cf7ec8f561de46e2a322926d72f61291", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735622+00:00", "framework": "vllm_fix_tokenizer", "intentId": "09c04fec92874045add8d92039c35121", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735670+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cbb76375731b4c94b752b0844381ea29", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735713+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dbe913de0054427684a3490c0e7a75ec", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735755+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea3c9d8ea0234a4db9b6ff5fc5187cee", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735797+00:00", "framework": "vllm_fix_tokenizer", "intentId": "18bc41075cd949aa880a3c47b9e32e36", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735840+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cba64e2474b34c088e54d6cad357a44e", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735883+00:00", "framework": "vllm_fix_tokenizer", "intentId": "699409f98c734bac8b6ffdb9e83ec7b4", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735925+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3986a290319048dd9ab31d2fb9b15d09", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735967+00:00", "framework": "vllm_fix_tokenizer", "intentId": "852e7704a6b6450bb63d6ee1f91dbbe9", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736010+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dea8b2ffd192453285486048f9d042d3", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736052+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a45e8049651544c2bbe87932222589d5", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736095+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6136c597502f4af5af517020f6f4d3db", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736137+00:00", "framework": "vllm_fix_tokenizer", "intentId": "451e4445478548fd89a971b588d6dada", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736180+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7876960e4fae45d9a7db3b1cee683695", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736222+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a35acfe3c8344574aee8e7624b0bb0e0", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736264+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cb0e3df69bc44fc2a273a138d58e45a1", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736307+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ab9dce96b5bf440794922595dc34c3f5", "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": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736350+00:00", "framework": "vllm", "intentId": "00a0c8773b3646be9f4e1cc011c4cac9", "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": "Iluvatar_mrv-100", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736399+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8a7eed7219db46e69c61c9be724a6343", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736441+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a060610a7737468b9c44d40d712b575e", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736483+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a9b4f3250a0a4e5e812f3dd3f6c1913f", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736526+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4607201015384e039b0f75ff91584eab", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "34d173e59db24680a68d3a177668c80f", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2035e12bf4bb4179985e56fd10d59249", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736654+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f47a9516503541e581c855a0e21617d9", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736701+00:00", "framework": "vllm", "intentId": "93233ee2b6e945b3be73ca7755e45d82", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736750+00:00", "framework": "vllm", "intentId": "bf2c6591046a462f836e1cd25d98fe73", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736798+00:00", "framework": "vllm", "intentId": "ccb31c440fc84ce2a28f0bba9fada351", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736846+00:00", "framework": "vllm", "intentId": "194d974a154446358b1fda0c440dd6e8", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736893+00:00", "framework": "vllm", "intentId": "5900b6da1ef44bdebc555ea4ad037950", "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": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736940+00:00", "framework": "vllm", "intentId": "1916c1551b6d41419ba32c2dbfb750eb", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117242+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734335+00:00", "framework": "vllm-mlu", "intentId": "e5b77fc77bff4a2ba99764a6a9666dfd", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "reason": null, "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990878", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117262+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734657+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5572f6ca884e47739141284fe6081b21", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "reason": null, "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4990879", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117281+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b6bbef3120454144a22fc97f515a87d2", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4990910", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117326+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735580+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cf7ec8f561de46e2a322926d72f61291", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "reason": null, "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4990935", "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117413+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736940+00:00", "framework": "vllm", "intentId": "1916c1551b6d41419ba32c2dbfb750eb", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117410+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736893+00:00", "framework": "vllm", "intentId": "5900b6da1ef44bdebc555ea4ad037950", "repoId": "neuralmagic/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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117407+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736846+00:00", "framework": "vllm", "intentId": "194d974a154446358b1fda0c440dd6e8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117405+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736798+00:00", "framework": "vllm", "intentId": "ccb31c440fc84ce2a28f0bba9fada351", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117402+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736750+00:00", "framework": "vllm", "intentId": "bf2c6591046a462f836e1cd25d98fe73", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117399+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736701+00:00", "framework": "vllm", "intentId": "93233ee2b6e945b3be73ca7755e45d82", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117396+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736654+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f47a9516503541e581c855a0e21617d9", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117393+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2035e12bf4bb4179985e56fd10d59249", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117390+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "34d173e59db24680a68d3a177668c80f", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117388+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736526+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4607201015384e039b0f75ff91584eab", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117386+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736483+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a9b4f3250a0a4e5e812f3dd3f6c1913f", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117383+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736441+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a060610a7737468b9c44d40d712b575e", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117380+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736399+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8a7eed7219db46e69c61c9be724a6343", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117377+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736350+00:00", "framework": "vllm", "intentId": "00a0c8773b3646be9f4e1cc011c4cac9", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117374+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736307+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ab9dce96b5bf440794922595dc34c3f5", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117371+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736264+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cb0e3df69bc44fc2a273a138d58e45a1", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117368+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736222+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a35acfe3c8344574aee8e7624b0bb0e0", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117366+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736180+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7876960e4fae45d9a7db3b1cee683695", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117362+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736137+00:00", "framework": "vllm_fix_tokenizer", "intentId": "451e4445478548fd89a971b588d6dada", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117359+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736095+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6136c597502f4af5af517020f6f4d3db", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117356+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736052+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a45e8049651544c2bbe87932222589d5", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117353+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736010+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dea8b2ffd192453285486048f9d042d3", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117351+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735967+00:00", "framework": "vllm_fix_tokenizer", "intentId": "852e7704a6b6450bb63d6ee1f91dbbe9", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117348+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735925+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3986a290319048dd9ab31d2fb9b15d09", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117345+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735883+00:00", "framework": "vllm_fix_tokenizer", "intentId": "699409f98c734bac8b6ffdb9e83ec7b4", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117342+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735840+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cba64e2474b34c088e54d6cad357a44e", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117340+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735797+00:00", "framework": "vllm_fix_tokenizer", "intentId": "18bc41075cd949aa880a3c47b9e32e36", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117337+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735755+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea3c9d8ea0234a4db9b6ff5fc5187cee", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117334+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735713+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dbe913de0054427684a3490c0e7a75ec", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117331+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735670+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cbb76375731b4c94b752b0844381ea29", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117329+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735622+00:00", "framework": "vllm_fix_tokenizer", "intentId": "09c04fec92874045add8d92039c35121", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117323+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735537+00:00", "framework": "vllm_fix_tokenizer", "intentId": "932ee6e5868f45f386d6936b3cf74ddf", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117320+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735494+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9cd897e76fa049af80664ba04f63b6c3", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117317+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735451+00:00", "framework": "vllm_fix_tokenizer", "intentId": "96474af7e05547d0a15efc730d104bc6", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117315+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735408+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6c8ac6210032421f9156927e11487c44", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117312+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735365+00:00", "framework": "vllm_fix_tokenizer", "intentId": "007f231871cf4b269c3e0850d0354735", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117309+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735322+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04342fdc2209408188f755cc04116626", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117306+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735279+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dc43e678c8f6458ead1358ae2ad06e83", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117302+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735236+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ba0b273e7e864df8bd1b1280b9411652", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117299+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735193+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0ac0061725e74f11b0d620f74b306710", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117296+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735150+00:00", "framework": "vllm_fix_tokenizer", "intentId": "edb421aa761743c0900265b91d9c43e7", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117293+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735107+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc215648713a449992e961f4d4dc88f1", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117289+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735065+00:00", "framework": "vllm_fix_tokenizer", "intentId": "64dc1527999f462e8a30c87f8b3ced65", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117286+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735022+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e04592c5360443029a1eae04c7556a7c", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117283+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734979+00:00", "framework": "vllm_fix_tokenizer", "intentId": "21aad501e2e4402da99190927fc52977", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117277+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734893+00:00", "framework": "vllm_fix_tokenizer", "intentId": "146085a645454f94ba17a092500081c1", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117274+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734850+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9c1cc43d6ea4880a6f37a354fb912c6", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117271+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734807+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aa4a83af0a034a2da90d23761ee79612", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117268+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734763+00:00", "framework": "vllm_fix_tokenizer", "intentId": "182b0b1503574e07ad3002a845e6dbf6", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117265+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734720+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e7be4b63f6c04cc49c0c1ad88d48ddc5", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117260+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734613+00:00", "framework": "vllm_fix_tokenizer", "intentId": "63a7f0d974604244bdf5948e23394da1", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117256+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fec9220dc12043cf9f6b2db3c0d45022", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117253+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734525+00:00", "framework": "vllm_fix_tokenizer", "intentId": "22a504f40f464defb415b1ab1d95d883", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117250+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734466+00:00", "framework": "vllm", "intentId": "f8f7c19c340e425db09e4a8a3075407b", "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": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117246+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734404+00:00", "framework": "vllm", "intentId": "0a2b8bee680f4d089856640e66603c03", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117219+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734193+00:00", "framework": "vllm-mlu", "intentId": "ed678d511eca4246af651f3f2294418c", "repoId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "3b83c690a91847a68bb5b29252f7659a", "completedAt": "2026-09-21T01:06:56.187826+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:01:39.842511+00:00", "framework": "vllm", "intentId": "28aea81c34d44aa2a3f8df6fbf96e365", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "3b83c690a91847a68bb5b29252f7659a", "completedAt": "2026-09-21T01:06:56.187823+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:01:39.842452+00:00", "framework": "vllm-customized", "intentId": "a4d810bd8fe14f08b685f5515a18762a", "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": "3b83c690a91847a68bb5b29252f7659a", "completedAt": "2026-09-21T01:06:56.187820+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:01:39.842394+00:00", "framework": "vllm-customized", "intentId": "3ccde998b3554890952f63a472f335ab", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
@@ -2186,59 +2186,3 @@
{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837021+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900646+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a1b4187df0c74cbe9b8d9a7544880d64", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837018+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900603+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aad74f15aefa49fcb4d7a7ac710b8763", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837016+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900561+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3dec5f6f751c4883a515106d9195e5d3", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837013+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900518+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b068274054ce474e9ec0fb307af6ae19", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837010+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900476+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ae1fb51f8d484a92ab28b81180f5c173", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837007+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900433+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1bf1487516bc4fdf8c2b8efca4832cbb", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837003+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900391+00:00", "framework": "vllm_fix_tokenizer", "intentId": "659cc2c028734b9db64dcf94833036c8", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837000+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900342+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1626b51d2b5a40019dbf9282cdf42ee1", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.836997+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900299+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3c2b422e33aa41aa9d535b9713b36745", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.836995+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900257+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4a2777953e894bdfb7821efa043c7a24", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.836991+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900215+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1d4e99f59312417588c2552b07422495", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.836989+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900172+00:00", "framework": "vllm_fix_tokenizer", "intentId": "56ddd6920e7b43d1aed0652ea2dce568", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.836985+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900130+00:00", "framework": "vllm_fix_tokenizer", "intentId": "688b9568f2ec4b9bac57d5f18c1f3341", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.836979+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900044+00:00", "framework": "vllm_fix_tokenizer", "intentId": "71b344243ec642c19fd1f87af8862e66", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.836976+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900001+00:00", "framework": "vllm_fix_tokenizer", "intentId": "827c812b51b6490b93f34240f05c9a95", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.836970+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.899956+00:00", "framework": "vllm_fix_tokenizer", "intentId": "708305f16a124ede9b7fd12c140e0187", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675571+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.661561+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6daddb306e7144059cc3d1257e41d70d", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675568+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.661467+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5865a857f588409dae392a9e1f28dd43", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675565+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.661375+00:00", "framework": "vllm_fix_tokenizer", "intentId": "86ac00e960ca4568ae44af17127a95e9", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675562+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.661320+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c081874e727d4a2e87fecca49c4878e6", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675558+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.661264+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9c424784375d4fd5b0e31d55c925d7f7", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675556+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.661207+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d5609cdb2fba4c06acf22391a2e7346b", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675552+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.661164+00:00", "framework": "vllm", "intentId": "b750971c42d24718b2f7f1cf59ea7de9", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675545+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.661037+00:00", "framework": "vllm", "intentId": "741111875e674f4eb11c19ebb850ed47", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675542+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660995+00:00", "framework": "vllm", "intentId": "54129bb8787049beb10a81f9e0d70c5e", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675539+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660953+00:00", "framework": "vllm", "intentId": "6eb7a0b274df4dceba02fbcbb1330fdc", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675536+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660910+00:00", "framework": "vllm", "intentId": "4b3a90319864419ba3a5a619130f4b58", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675534+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660868+00:00", "framework": "vllm", "intentId": "120ae8a705254bf58e5000f3259feea1", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675531+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660823+00:00", "framework": "vllm", "intentId": "dea100e5a68b489c875c93a761128349", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675528+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660764+00:00", "framework": "vllm-customized", "intentId": "d67ec3fc075c495596837fb03f472192", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675525+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660706+00:00", "framework": "vllm-customized", "intentId": "b811f3a0f57b4c6f8c474b417642f48e", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675522+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660636+00:00", "framework": "vllm-customized", "intentId": "d4ce123654d4478eba043bfbbca7f840", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675519+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660577+00:00", "framework": "vllm-customized", "intentId": "c8231e646b5748e4a140533022e57c21", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675516+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660517+00:00", "framework": "vllm-customized", "intentId": "6ec0427a4e4d46f8ae4c3dd3094fa63a", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675513+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660476+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f0cac0de3d404ce483766c98ce54bf8b", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675510+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660435+00:00", "framework": "vllm_tokenizer_patch", "intentId": "442ae9170b3546fabd91837d26d0cf63", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675507+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660390+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f91d2803c6384d69ae60f8b9baee4d9d", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675504+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660339+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1fd1f433d718403f8f7b3d4feb2cfcae", "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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675499+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660226+00:00", "framework": "vllm", "intentId": "d8d2f242217941c8a332c3434913d2c9", "repoId": "RedHatAI/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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675496+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660177+00:00", "framework": "vllm", "intentId": "46f359b785944cd49ed53499ac0333fe", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675493+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660126+00:00", "framework": "vllm", "intentId": "bcc83cb4d2384d8b8e6e82446805a64f", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675489+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660082+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f52531faf2f747be86bb34976f74a7fa", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675486+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.660039+00:00", "framework": "vllm_fix_tokenizer", "intentId": "45c4c2359ceb44d39789065a55800137", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675484+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.659995+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f7da4624f765431088e1f915d726db94", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675481+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.659950+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a688f4ab6cd447dd8cf3bb4fc52c3204", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675477+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.659903+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8572e6e63a9c4fa68460f838b3f78033", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675474+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.659848+00:00", "framework": "vllm", "intentId": "7e7bfbe10c524744baa9c5767ff84a91", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675472+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.659792+00:00", "framework": "vllm", "intentId": "68c86cddb3df4995925704ab498a9753", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675468+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.659730+00:00", "framework": "vllm", "intentId": "49439ff874924145805bb7fb634c2a68", "repoId": "neuralmagic/starcoder2-7b-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": "13501ade864c4f78b3d6836d640ec04c", "completedAt": "2026-09-21T00:06:32.675445+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:01:51.659597+00:00", "framework": "vllm", "intentId": "16cd37ffe5094a4ba1f6c0542d86d029", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "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", "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", "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", "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", "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", "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", "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", "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", "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"}

12
.modelhub_state/routing_intelligence.json
View File

@@ -1,6 +1,6 @@
{
"acceptedByCategory": {
"unified_success_first": 2022
"unified_success_first": 2026
},
"acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17,
@@ -10,13 +10,13 @@
"text-generation|Ascend_910-b4|vllm": 22,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 130,
"text-generation|Biren_166m|vllm": 81,
"text-generation|Biren_166m|vllm_fix_tokenizer": 71,
"text-generation|Biren_166m|vllm_fix_tokenizer": 74,
"text-generation|Cambricon_mlu-370-x4|vllm": 53,
"text-generation|Cambricon_mlu-370-x4|vllm-customized": 4,
"text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82,
"text-generation|Cambricon_mlu-370-x8|vllm": 55,
"text-generation|Cambricon_mlu-370-x8|vllm-customized": 40,
"text-generation|Cambricon_mlu-370-x8|vllm-mlu": 93,
"text-generation|Cambricon_mlu-370-x8|vllm-mlu": 94,
"text-generation|Iluvatar_bi-100|transformers": 20,
"text-generation|Iluvatar_bi-150|llamacpp": 16,
"text-generation|Iluvatar_bi-150|transformers": 30,
@@ -38,8 +38,8 @@
"text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 118
},
"acceptedSinceRefresh": 2022,
"acceptedTotal": 2022,
"generatedAt": "2026-09-21T01:06:56.083859+00:00",
"acceptedSinceRefresh": 2026,
"acceptedTotal": 2026,
"generatedAt": "2026-09-21T01:17:18.051736+00:00",
"version": 1
}

5
ledger/submissions.jsonl
View File

@@ -1006,7 +1006,6 @@
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "submitTime": "2026-09-21T00:36:43.644698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4990464", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-21T00:41:04.760036+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990527", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-21T00:51:43.688289+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:57:37.806607+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970326", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-20T03:57:37.934664+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970335", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-20T03:58:35.458351+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970351", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-20T03:58:41.304973+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970364", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
@@ -1158,3 +1157,7 @@
{"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/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-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "modelId": "RedHatAI/starcoder2-15b-FP8", "submitTime": "2026-09-21T01:10:00.817297+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990878", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-21T01:10:00.835785+00:00", "targetGpu": "Biren_166m", "taskId": "4990879", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "submitTime": "2026-09-21T01:10:01.025615+00:00", "targetGpu": "Biren_166m", "taskId": "4990910", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "submitTime": "2026-09-21T01:11:59.475916+00:00", "targetGpu": "Biren_166m", "taskId": "4990935", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}

14
manifest.json
View File

@@ -9,16 +9,16 @@
".modelhub_state/queue_cleanup_latest.json": "87ea93bf42a8a1e24e156ef53e31bb1f4495dd95733206eb0979243c703bdc7f",
".modelhub_state/recent_outcomes.jsonl": "bfffd6af93a9d04b368110149eca10ab996989d09685a15b5c02f02824787e9b",
".modelhub_state/recovery_active_tasks.jsonl": "47a448855a5cf5902e5effcee152eb9a864fea15488a4004b1350ef23b18b082",
".modelhub_state/recovery_intents.jsonl": "787ea42c8be47ddf418aa124eef210f3113540aa8c2d11fa7599c01003beb9a3",
".modelhub_state/routing_intelligence.json": "9ada660d091d25cfcc04e175e2bd58581091b0f81e817e15d2e21513a5e1bd2e",
".modelhub_state/recovery_intents.jsonl": "bc95c9876fa06e22e8d223b08a4f3b6c358864a5af54bccc79dfde0558e9caea",
".modelhub_state/routing_intelligence.json": "7eb4badffe639ab62245ebeca66ebfd381b6f4ab910458ac0ef6f058152cab30",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "ee7c9afd034f784e704c348f7318ec955184ce3f65ac6d83eb605634c1db0590",
"outcomes/submissions.jsonl": "a9644aca9522e7754709882092751233d071181131f9bc6821f08ae2a553ac4b"
"ledger/submissions.jsonl": "3787bf8090cef9d15c9f9c0f69a6870580ca22eb1b1cd3625d3b1c9bc66a449d",
"outcomes/submissions.jsonl": "3b3e2edba320e23090862f04bfc0729f19db94075763b82398691c80097cb4e8"
},
"generation": 11052,
"phase": "intent",
"generation": 11053,
"phase": "result",
"schemaVersion": 1,
"updatedAt": "2026-09-21T01:09:52.880628+00:00",
"updatedAt": "2026-09-21T01:17:18.262256+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996"
}

4
outcomes/submissions.jsonl
View File

@@ -1116,3 +1116,7 @@
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:36:43.644698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4990464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:41:04.760036+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990527", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:51:43.688289+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "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": 16568142065}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:00.817297+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990878", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020564058}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:00.835785+00:00", "targetGpu": "Biren_166m", "taskId": "4990879", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:01.025615+00:00", "targetGpu": "Biren_166m", "taskId": "4990910", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:11:59.475916+00:00", "targetGpu": "Biren_166m", "taskId": "4990935", "taskType": "text-generation", "verifyResult": null}