From d62cda6c4b909b82b259d82c0703aa1460e44467 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 11:07:39 +0000 Subject: [PATCH] state: generation 11409 (result) --- .modelhub_state/recovery_intents.jsonl | 179 ++++++++-------------- .modelhub_state/routing_intelligence.json | 14 +- ledger/submissions.jsonl | 4 + manifest.json | 14 +- outcomes/submissions.jsonl | 4 + 5 files changed, 83 insertions(+), 132 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 3643bfae01..05c28ce8c0 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2051,67 +2051,67 @@ {"batchId": "5e7798d2f7dc4de98461e952a03abd04", "completedAt": "2026-09-21T10:54:40.108956+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T10:48:51.274039+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5530b98b1bbe439080077c3a149dd89d", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-21T10:57:32.120761+00:00", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999447", "taskType": "text-generation"} {"batchId": "5e7798d2f7dc4de98461e952a03abd04", "completedAt": "2026-09-21T10:54:40.108959+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T10:48:51.274093+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f2d1a2950c274fdfba0355aabbcafcee", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "reason": null, "reconciledAt": "2026-09-21T10:57:32.120538+00:00", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999409", "taskType": "text-generation"} {"batchId": "5e7798d2f7dc4de98461e952a03abd04", "completedAt": "2026-09-21T10:54:40.108961+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T10:48:51.274147+00:00", "framework": "vllm_fix_tokenizer", "intentId": "22abe624b1b94df1909815fc00083ad4", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "reason": null, "reconciledAt": "2026-09-21T10:57:32.120955+00:00", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999410", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733078+00:00", "framework": "vllm-mlu", "intentId": "1fbbb247f18c4fb3a2ba57faba837573", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733197+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bf767cd287ca4ea88be99228d8005402", "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": "Vastai_va16", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733246+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f9f53af5454d4c8f9ba826dd6e6b8756", "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": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733287+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d191b1f474444923a7a5a9a07fc4b833", "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": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733325+00:00", "framework": "vllm_tokenizer_patch", "intentId": "560ff8ad169e4ab3b773eb825eb96035", "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": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733363+00:00", "framework": "vllm_tokenizer_patch", "intentId": "72319e5740944060ba6d89bcee51e7a2", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733401+00:00", "framework": "vllm_tokenizer_patch", "intentId": "77a4fd8c8dc64e4687ea69b8b733cb74", "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": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733438+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d947e1ae1e234147a0cc49b9eca7395c", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733489+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ab68332de817416c895f3631ee57ac35", "lastModified": "2026-08-24T19:38:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733539+00:00", "framework": "vllm_tokenizer_patch", "intentId": "564657b0d9964d18aad15091a7260f69", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733589+00:00", "framework": "vllm_tokenizer_patch", "intentId": "05c0934f01df480493fe72401f2c9453", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733638+00:00", "framework": "vllm", "intentId": "6107ca16ccf34990b5ab5ff425585031", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733707+00:00", "framework": "vllm", "intentId": "ed7b0ca706424f41b7111b2810b584e6", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733765+00:00", "framework": "vllm", "intentId": "daf756216a5c428296217b0fc8872cbc", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733821+00:00", "framework": "vllm", "intentId": "6b992b33ffe2401e97eade83babd3ffd", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733878+00:00", "framework": "vllm", "intentId": "5b1fe9a336ca460ebca4ba476005f342", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733934+00:00", "framework": "vllm", "intentId": "9c48723f3af64a16bc21a10a674c7ac3", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733997+00:00", "framework": "vllm", "intentId": "84019d77b109445e8870f30546d71a4e", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734054+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "496259bbb6874467a05a451f8885393d", "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": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734099+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d04157a575746dfbb12619a3ce16eee", "lastModified": "2026-08-31T03:35:12+00:00", "modelAddress": "https://modelscope.cn/models/logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734142+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a22c4d58314c4e3a93b9095a94e739ae", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734184+00:00", "framework": "vllm-patch-tokenizer", "intentId": "378a1f93b554458d805639b88b7644d1", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734226+00:00", "framework": "vllm-patch-tokenizer", "intentId": "bfb1f4ae5976408da1bbc3eaadac633d", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734268+00:00", "framework": "vllm-patch-tokenizer", "intentId": "43395e632c02417d87fcf4ac4f0bf2e0", "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": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734310+00:00", "framework": "vllm-patch-tokenizer", "intentId": "271e2afc6e924dd38e3b1f967c26b7cd", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734352+00:00", "framework": "vllm-patch-tokenizer", "intentId": "440f08a201634631b1d8955f3a4dc4f8", "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": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734393+00:00", "framework": "vllm-patch-tokenizer", "intentId": "014d54a094aa4ebcb8edb9208aabad1f", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734435+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ca32931de1804719b683f75a42019fb8", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734477+00:00", "framework": "vllm-patch-tokenizer", "intentId": "525854d503644a0185b8398d159ac2fc", "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": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734518+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3118ea4e3eda43f594959fdbdc463158", "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": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734559+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e5dc2158fc184b9499211b2afae4698f", "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": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734601+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a7ba437dd7b348d8a41bc3ea45d29641", "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": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734642+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b16aa077415a478389c45750fce40491", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734689+00:00", "framework": "vllm", "intentId": "e8163bebf7c04b06a532eaab75f0faff", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734737+00:00", "framework": "vllm", "intentId": "ffbb2bdbdbd842fe956020144d24b640", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734785+00:00", "framework": "vllm", "intentId": "e1068fe5fada4003b1fe399f10b290cb", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734831+00:00", "framework": "vllm", "intentId": "7d44dd3da4864a7eab1c0bf4f07b0ace", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734878+00:00", "framework": "vllm-customized", "intentId": "f2e04a38b9024bb984f0f4cdb0cb217f", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734936+00:00", "framework": "vllm-customized", "intentId": "2a0aef07c16c4aebb42c815e095dd859", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734994+00:00", "framework": "vllm-customized", "intentId": "905f653cb4a3480c9cb4385ce3fdbf83", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735050+00:00", "framework": "vllm-customized", "intentId": "c5c44a916b3b46e89f77d0fcff769d37", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735107+00:00", "framework": "vllm-customized", "intentId": "311602b38cbb42f0b2ecb12aa3424a04", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735164+00:00", "framework": "vllm-customized", "intentId": "3936ae3a96ca4bffa6d076a3b38ee9f6", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735221+00:00", "framework": "vllm-customized", "intentId": "431dd66a0cd743c4822466d82d3b50aa", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735278+00:00", "framework": "vllm-customized", "intentId": "ffcfd2633a8c41e4b2ced1df2987f7fb", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735335+00:00", "framework": "vllm-customized", "intentId": "949e7178218e4159a2c1c0b3c3a7f437", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735392+00:00", "framework": "vllm-customized", "intentId": "f2e6db39dc5b4817a2b14c23d4c7698c", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735448+00:00", "framework": "vllm-customized", "intentId": "38ae4bee43be47ba8907e5fca7c8fdd6", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735505+00:00", "framework": "vllm-customized", "intentId": "e5b3bddaa9554029ab5efdca327b1f6e", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735562+00:00", "framework": "vllm-customized", "intentId": "8ec0a9716e6b4f91ac1213ebd03a47d2", "lastModified": "2026-08-24T20:30:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735620+00:00", "framework": "vllm-customized", "intentId": "2243bef0d98c49019c7d882700cf9f16", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735767+00:00", "framework": "vllm-customized", "intentId": "7fbfb0a8dff24678876acef4527ba30f", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735825+00:00", "framework": "vllm-customized", "intentId": "a0e95778c4534d499c15d1a76cbc78ed", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735883+00:00", "framework": "vllm-customized", "intentId": "bd1c398873344faf98225b511d03dbf5", "lastModified": "2026-08-24T20:33:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735940+00:00", "framework": "vllm-customized", "intentId": "cd35a4e52a7a48c183a0cd6acb53e1b0", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735997+00:00", "framework": "vllm-customized", "intentId": "57c38f12537c468781d9ba381a5bf43b", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736054+00:00", "framework": "vllm-customized", "intentId": "30e8dc09e9c846e78a282727a9474533", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736111+00:00", "framework": "vllm-customized", "intentId": "3ae01647af3c4ecca8790433e46f0b7b", "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": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736168+00:00", "framework": "vllm-customized", "intentId": "27281b3a11af4be6ad30b5c8ee8c0457", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736225+00:00", "framework": "vllm-customized", "intentId": "51e7617f249341c49618d2fe44cc65ca", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "bc617924808a4a0d95a19562eb38a56a", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736282+00:00", "framework": "vllm-customized", "intentId": "bf76773e57904346840d0bb2b89475d7", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263056+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733246+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f9f53af5454d4c8f9ba826dd6e6b8756", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "reason": null, "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4999568", "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263069+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733401+00:00", "framework": "vllm_tokenizer_patch", "intentId": "77a4fd8c8dc64e4687ea69b8b733cb74", "lastModified": "2026-09-08T15:40:32+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "reason": null, "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4999567", "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263078+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733539+00:00", "framework": "vllm_tokenizer_patch", "intentId": "564657b0d9964d18aad15091a7260f69", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "reason": null, "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4999569", "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263102+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733997+00:00", "framework": "vllm", "intentId": "84019d77b109445e8870f30546d71a4e", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "reason": null, "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4999589", "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263227+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736282+00:00", "framework": "vllm-customized", "intentId": "bf76773e57904346840d0bb2b89475d7", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263224+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736225+00:00", "framework": "vllm-customized", "intentId": "51e7617f249341c49618d2fe44cc65ca", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263222+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736168+00:00", "framework": "vllm-customized", "intentId": "27281b3a11af4be6ad30b5c8ee8c0457", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263218+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736111+00:00", "framework": "vllm-customized", "intentId": "3ae01647af3c4ecca8790433e46f0b7b", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263215+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.736054+00:00", "framework": "vllm-customized", "intentId": "30e8dc09e9c846e78a282727a9474533", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263212+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735997+00:00", "framework": "vllm-customized", "intentId": "57c38f12537c468781d9ba381a5bf43b", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263209+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735940+00:00", "framework": "vllm-customized", "intentId": "cd35a4e52a7a48c183a0cd6acb53e1b0", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263206+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735883+00:00", "framework": "vllm-customized", "intentId": "bd1c398873344faf98225b511d03dbf5", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263204+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735825+00:00", "framework": "vllm-customized", "intentId": "a0e95778c4534d499c15d1a76cbc78ed", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263202+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735767+00:00", "framework": "vllm-customized", "intentId": "7fbfb0a8dff24678876acef4527ba30f", "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": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263199+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735620+00:00", "framework": "vllm-customized", "intentId": "2243bef0d98c49019c7d882700cf9f16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263196+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735562+00:00", "framework": "vllm-customized", "intentId": "8ec0a9716e6b4f91ac1213ebd03a47d2", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263193+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735505+00:00", "framework": "vllm-customized", "intentId": "e5b3bddaa9554029ab5efdca327b1f6e", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263190+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735448+00:00", "framework": "vllm-customized", "intentId": "38ae4bee43be47ba8907e5fca7c8fdd6", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263187+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735392+00:00", "framework": "vllm-customized", "intentId": "f2e6db39dc5b4817a2b14c23d4c7698c", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263184+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735335+00:00", "framework": "vllm-customized", "intentId": "949e7178218e4159a2c1c0b3c3a7f437", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263181+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735278+00:00", "framework": "vllm-customized", "intentId": "ffcfd2633a8c41e4b2ced1df2987f7fb", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263179+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735221+00:00", "framework": "vllm-customized", "intentId": "431dd66a0cd743c4822466d82d3b50aa", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263176+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735164+00:00", "framework": "vllm-customized", "intentId": "3936ae3a96ca4bffa6d076a3b38ee9f6", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263173+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735107+00:00", "framework": "vllm-customized", "intentId": "311602b38cbb42f0b2ecb12aa3424a04", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263170+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.735050+00:00", "framework": "vllm-customized", "intentId": "c5c44a916b3b46e89f77d0fcff769d37", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263167+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734994+00:00", "framework": "vllm-customized", "intentId": "905f653cb4a3480c9cb4385ce3fdbf83", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263165+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734936+00:00", "framework": "vllm-customized", "intentId": "2a0aef07c16c4aebb42c815e095dd859", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263162+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734878+00:00", "framework": "vllm-customized", "intentId": "f2e04a38b9024bb984f0f4cdb0cb217f", "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": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263159+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734831+00:00", "framework": "vllm", "intentId": "7d44dd3da4864a7eab1c0bf4f07b0ace", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263156+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734785+00:00", "framework": "vllm", "intentId": "e1068fe5fada4003b1fe399f10b290cb", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263153+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734737+00:00", "framework": "vllm", "intentId": "ffbb2bdbdbd842fe956020144d24b640", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263150+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734689+00:00", "framework": "vllm", "intentId": "e8163bebf7c04b06a532eaab75f0faff", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263146+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734642+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b16aa077415a478389c45750fce40491", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263143+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734601+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a7ba437dd7b348d8a41bc3ea45d29641", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263140+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734559+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e5dc2158fc184b9499211b2afae4698f", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263137+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734518+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3118ea4e3eda43f594959fdbdc463158", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263134+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734477+00:00", "framework": "vllm-patch-tokenizer", "intentId": "525854d503644a0185b8398d159ac2fc", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263131+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734435+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ca32931de1804719b683f75a42019fb8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263128+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734393+00:00", "framework": "vllm-patch-tokenizer", "intentId": "014d54a094aa4ebcb8edb9208aabad1f", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263125+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734352+00:00", "framework": "vllm-patch-tokenizer", "intentId": "440f08a201634631b1d8955f3a4dc4f8", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263123+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734310+00:00", "framework": "vllm-patch-tokenizer", "intentId": "271e2afc6e924dd38e3b1f967c26b7cd", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263120+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734268+00:00", "framework": "vllm-patch-tokenizer", "intentId": "43395e632c02417d87fcf4ac4f0bf2e0", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263117+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734226+00:00", "framework": "vllm-patch-tokenizer", "intentId": "bfb1f4ae5976408da1bbc3eaadac633d", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263114+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734184+00:00", "framework": "vllm-patch-tokenizer", "intentId": "378a1f93b554458d805639b88b7644d1", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263111+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734142+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a22c4d58314c4e3a93b9095a94e739ae", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263108+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734099+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d04157a575746dfbb12619a3ce16eee", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263105+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.734054+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "496259bbb6874467a05a451f8885393d", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263099+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733934+00:00", "framework": "vllm", "intentId": "9c48723f3af64a16bc21a10a674c7ac3", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263096+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733878+00:00", "framework": "vllm", "intentId": "5b1fe9a336ca460ebca4ba476005f342", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263093+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733821+00:00", "framework": "vllm", "intentId": "6b992b33ffe2401e97eade83babd3ffd", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263090+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733765+00:00", "framework": "vllm", "intentId": "daf756216a5c428296217b0fc8872cbc", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263087+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733707+00:00", "framework": "vllm", "intentId": "ed7b0ca706424f41b7111b2810b584e6", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263084+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733638+00:00", "framework": "vllm", "intentId": "6107ca16ccf34990b5ab5ff425585031", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263080+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733589+00:00", "framework": "vllm_tokenizer_patch", "intentId": "05c0934f01df480493fe72401f2c9453", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263075+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733489+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ab68332de817416c895f3631ee57ac35", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263072+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733438+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d947e1ae1e234147a0cc49b9eca7395c", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263066+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733363+00:00", "framework": "vllm_tokenizer_patch", "intentId": "72319e5740944060ba6d89bcee51e7a2", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263063+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733325+00:00", "framework": "vllm_tokenizer_patch", "intentId": "560ff8ad169e4ab3b773eb825eb96035", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263059+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733287+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d191b1f474444923a7a5a9a07fc4b833", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263052+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733197+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bf767cd287ca4ea88be99228d8005402", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} +{"batchId": "bc617924808a4a0d95a19562eb38a56a", "completedAt": "2026-09-21T11:07:39.263031+00:00", "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configSource": "modelhub_live", "createdAt": "2026-09-21T11:00:15.733078+00:00", "framework": "vllm-mlu", "intentId": "1fbbb247f18c4fb3a2ba57faba837573", "repoId": "RedHatAI/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": "5e7798d2f7dc4de98461e952a03abd04", "completedAt": "2026-09-21T10:54:40.108951+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T10:48:51.273932+00:00", "framework": "vllm_fix_tokenizer", "intentId": "398dff4c8fac4929ba6911256eb8e233", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "5e7798d2f7dc4de98461e952a03abd04", "completedAt": "2026-09-21T10:54:40.108948+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T10:48:51.273879+00:00", "framework": "vllm_fix_tokenizer", "intentId": "63db1fe1ad2b45d08c88b832033718d4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "5e7798d2f7dc4de98461e952a03abd04", "completedAt": "2026-09-21T10:54:40.108945+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T10:48:51.273825+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5850dbb0b6ce4bfcbb3b6265fe21d1cf", "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"} @@ -2355,60 +2355,3 @@ {"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457746+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406437+00:00", "framework": "vllm", "intentId": "07de76243403465b87bacb2086432b7f", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457743+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406380+00:00", "framework": "vllm", "intentId": "1b78d944f725418daf5bcec8551ecc90", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457740+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406323+00:00", "framework": "vllm", "intentId": "a69fb60c277943b38e8050c0eb51d03d", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457737+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406264+00:00", "framework": "vllm", "intentId": "b5ce0ba9a5864d9ba0b29cb98cc09a77", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457734+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406206+00:00", "framework": "vllm", "intentId": "422577bbcd4743b794cf9bbffe126847", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457732+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "df129b71d9e14cd98eea089522c93b2a", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457729+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406108+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd84a896be6b45898ddba8100c5ea33b", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457726+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406060+00:00", "framework": "vllm_tokenizer_patch", "intentId": "40d9cc0cf50641d2a9654c20aa664d88", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457724+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.406011+00:00", "framework": "vllm_tokenizer_patch", "intentId": "eefd3a5f51be4e8385770954926fa8da", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457721+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405962+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0eb9f93fecb9480fa3f8caf5358a1efd", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457719+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405912+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ff896332209949a3ac302a16043982b6", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457716+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405862+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6bcdbe8bbe2144e0b2bb4a7f1a193c94", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457713+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405812+00:00", "framework": "vllm_tokenizer_patch", "intentId": "34d3c311b17d48cc8912f2f01d78adb5", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457710+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405761+00:00", "framework": "vllm_tokenizer_patch", "intentId": "93e0534d8c434f6790a09895d6e7a917", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457708+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405693+00:00", "framework": "vllm-mlu", "intentId": "51dcf583c46347c6b2295f452831376c", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457705+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405648+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d5e4b7e6f5a341ad9c9dba1f613b82c6", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457700+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405573+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c9a16d207004451fb055563caadb84b5", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457697+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405536+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b96adae0f42842b3a34a0f37da5404da", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457695+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405499+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7f46c7c42a754ffb9ccd691492ecd09e", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457692+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405461+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6fcca3c3e2d84c4095741a8740bb7708", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457689+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405424+00:00", "framework": "vllm_tokenizer_patch", "intentId": "22f497e788354b23bb8752facbfdf367", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457686+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405385+00:00", "framework": "vllm_tokenizer_patch", "intentId": "563464de09344181bee8d51442eff825", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457683+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405348+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d196ab3bd96e4844b8cb13932690f57a", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457680+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405310+00:00", "framework": "vllm_tokenizer_patch", "intentId": "12ee9796822a41559fc3c1cc750e1234", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457678+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405271+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8cd49b3c9db04ab28d00ee5f21b17df4", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457675+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405233+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ff81358ca734b47a106e836a1f71148", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457663+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405157+00:00", "framework": "vllm_tokenizer_patch", "intentId": "24a4f25199eb4f4191b2744b7b6ae51a", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457660+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405116+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9925633a3f5a40dd9ac32e9e63e08df4", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457656+00:00", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405068+00:00", "framework": "vllm", "intentId": "af1e89d4d49d49ab91aec36c57ca06c7", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457653+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.405023+00:00", "framework": "vllm_fix_tokenizer", "intentId": "614f77bf98b748889af7b244a754a662", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "dd83c476d83041e4b6540de3761eab4e", "completedAt": "2026-09-21T09:49:02.457645+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:40:25.404968+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2bf1e4842577432db303ba91c2e705ae", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979823+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524650+00:00", "framework": "vllm", "intentId": "70181d484e034c4c99bce93d2c9afa9a", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979820+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524590+00:00", "framework": "vllm", "intentId": "745a98c92bf14f7884ff416219393fa7", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979817+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524530+00:00", "framework": "vllm", "intentId": "c97311b9308d4a6d98baffab6c5c7ea5", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979815+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524478+00:00", "framework": "vllm", "intentId": "dc9f025cb23940e1910a9eefb056457e", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979812+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524426+00:00", "framework": "vllm", "intentId": "ab782ed7bb1a4db4b2b5c4402b826836", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979809+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524372+00:00", "framework": "vllm", "intentId": "0199f6066f214f9c9f75fc957f2147f0", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979807+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524319+00:00", "framework": "vllm", "intentId": "4acf18cd62c24463abaf227d2c04a91a", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979804+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524259+00:00", "framework": "vllm", "intentId": "366c5bbfb8c54c9aa0ed568639ee1142", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979800+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524198+00:00", "framework": "vllm", "intentId": "cd45367a55ac415fb412c54cc8b2ec16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979798+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524137+00:00", "framework": "vllm", "intentId": "1a70007892c14a929e7397241436fd81", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979794+00:00", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524081+00:00", "framework": "vllm-customized", "intentId": "3ba89368d4944beb96d0b0f9875631b9", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979791+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.524023+00:00", "framework": "vllm-customized", "intentId": "fb3b946cf8dc43ffaba0ceabfa5e0062", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979788+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523961+00:00", "framework": "vllm-customized", "intentId": "61d1cf1d968b41818d67cb788b90efc0", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979785+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523901+00:00", "framework": "vllm-customized", "intentId": "f5f22c1756c945638214402c5730a07f", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979782+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523841+00:00", "framework": "vllm-customized", "intentId": "a921a4b7ee3b493cb2a4559a0f2a3fa3", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979779+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523781+00:00", "framework": "vllm-customized", "intentId": "bb7796c6e1874a2ca618896ea27082ed", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979776+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523720+00:00", "framework": "vllm-customized", "intentId": "b1261286760647f9890b9267503847e6", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979773+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523644+00:00", "framework": "vllm-customized", "intentId": "219baf2c7d4f427cae62456875260f46", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979770+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523583+00:00", "framework": "vllm-customized", "intentId": "3bd72e2d26c4486a9f4cb364363fafa3", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979768+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523522+00:00", "framework": "vllm-customized", "intentId": "4bf9c304090244ee877d71a0d6fa1dcf", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979765+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523462+00:00", "framework": "vllm-customized", "intentId": "0381777b3b3c4cab9ec010a64d366376", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979762+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523402+00:00", "framework": "vllm-customized", "intentId": "caab8efb3fe849f4b081d9f529f9d599", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979759+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523341+00:00", "framework": "vllm-customized", "intentId": "6be6ef1d532141ab9c97950b6a5b0af0", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979756+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523281+00:00", "framework": "vllm-customized", "intentId": "4f42e158e45b4cae8f1a4a1ec1e925c8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979753+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523220+00:00", "framework": "vllm-customized", "intentId": "b4deec666c4b4c2b9acdb56114381e8e", "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": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979750+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523159+00:00", "framework": "vllm-customized", "intentId": "86c03d58b583434f8b261f425afd4070", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979747+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523099+00:00", "framework": "vllm-customized", "intentId": "1997b490a82647458851152193c0c9e6", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979744+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.523038+00:00", "framework": "vllm-customized", "intentId": "449fcb43f47542769463315a0c06fcc0", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "f8cd5025838c46b5b6bdaa1f722188a8", "completedAt": "2026-09-21T09:32:40.979741+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:28:00.522976+00:00", "framework": "vllm-customized", "intentId": "0ca1582dee2b482e91d222ac0d3b45ac", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index a8cbabe790..b9597f4241 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,11 +1,11 @@ { "acceptedByCategory": { - "unified_success_first": 2190 + "unified_success_first": 2194 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|vllm": 38, - "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 152, + "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 154, "text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|vllm": 26, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 140, @@ -25,9 +25,9 @@ "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 40, "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 3, "text-generation|Iluvatar_mrv-100|vllm": 62, - "text-generation|Kunlunxin_p-800|vllm": 49, + "text-generation|Kunlunxin_p-800|vllm": 50, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 183, - "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 76, + "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 77, "text-generation|MetaX_c-500|vllm": 104, "text-generation|Mthreads_s4000|llamacpp": 17, "text-generation|Mthreads_s4000|vllm": 103, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 125 }, - "acceptedSinceRefresh": 2190, - "acceptedTotal": 2190, - "generatedAt": "2026-09-21T10:54:40.047249+00:00", + "acceptedSinceRefresh": 2194, + "acceptedTotal": 2194, + "generatedAt": "2026-09-21T11:07:39.201842+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 34720b8faf..c5147880c9 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1184,3 +1184,7 @@ {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "submitTime": "2026-09-21T08:39:42.289781+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997241", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"} {"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "modelId": "RedHatAI/starcoder2-15b-FP8", "submitTime": "2026-09-21T09:05:59.142974+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997663", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "modelId": "neuralmagic/starcoder2-3b-FP8", "submitTime": "2026-09-21T11:00:23.700518+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4999568", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-21T11:00:23.698765+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4999567", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "modelId": "sapientinc/HRM-Text-1B", "submitTime": "2026-09-21T11:00:23.702706+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4999569", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-21T11:00:43.861933+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4999589", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"} diff --git a/manifest.json b/manifest.json index 91426423b0..7541cac1d6 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "f4afc5dbbf57b883780778e798518d72ad1770b7d52c2f9efa7ac7bca07813f7", ".modelhub_state/recent_outcomes.jsonl": "a8ed55186bd94df8df243a3fd82531cf20d4f31ed783e09e68ef5fe9491b176c", ".modelhub_state/recovery_active_tasks.jsonl": "293ff7583f3455818bcc033b35e19cbc72462d001f47ab44b2824589641bfd0a", - ".modelhub_state/recovery_intents.jsonl": "53285abeba7fe2044bb5c7e4e3cf3245e3dcad19a09192be92ee6ad477dceeea", - ".modelhub_state/routing_intelligence.json": "7c36192e1564323afc6c72f3aee5addec37cbd3f3e486969bf4c80a4bf0e936b", + ".modelhub_state/recovery_intents.jsonl": "e7f2970f84690f54f2f0ed8df1fe4b2adf6381b9619b5447f868b05053f1f201", + ".modelhub_state/routing_intelligence.json": "e41c8911c02c44a5db61e2022d9f9ed72bd814f09ed41a1696bee9084c4230f1", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "8f0129323bf2dcb55447484c1069d92e69397d6324848a3c5cb6f8df9390cb7a", - "outcomes/submissions.jsonl": "157177fcaff3c674179d8e93dfacacb9d960592ac57bf91a6dccbd1b592e96f2" + "ledger/submissions.jsonl": "10cef048d4f807cb371167d5c7c62a7f14bba8eb9d3b73a7c637595969e21b5a", + "outcomes/submissions.jsonl": "cc02e6bd5176e4d86ec50dd7b30e8a8c720f301bbf15af5bde155493eb55e7a9" }, - "generation": 11408, - "phase": "intent", + "generation": 11409, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T11:00:15.882645+00:00", + "updatedAt": "2026-09-21T11:07:39.408227+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index d39b126f2b..76623ffce6 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1119,3 +1119,7 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T10:52:10.635641+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999447", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663548868}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T10:52:20.595972+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999409", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345693224}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T10:52:20.710547+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999410", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786187, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "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": 3487786187}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:00:23.700518+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4999568", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:00:23.698765+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4999567", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:00:23.702706+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4999569", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:00:43.861933+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4999589", "taskType": "text-generation", "verifyResult": null}