From 5b4b28f1cd584be053b2b034461dfbdcce4484b7 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sun, 20 Sep 2026 04:14:42 +0000 Subject: [PATCH] state: generation 10180 (result) --- .modelhub_state/recovery_intents.jsonl | 68 +++++++++++------------ .modelhub_state/routing_intelligence.json | 44 +++++++-------- ledger/submissions.jsonl | 34 ++++++++++++ manifest.json | 14 ++--- outcomes/submissions.jsonl | 34 ++++++++++++ 5 files changed, 131 insertions(+), 63 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 0079135c98..7ecba9ca8f 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1469,40 +1469,40 @@ {"batchId": "38cf9891ae7f43358a74f65a66a11939", "completedAt": "2026-09-20T04:10:03.220442+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:09:55.639471+00:00", "framework": "vllm", "intentId": "7c72bcb2a78b4b779f12c344daa9f57e", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "reason": null, "reconciledAt": "2026-09-20T04:11:14.264778+00:00", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "4970512", "taskType": "text-generation"} {"batchId": "4b2c1e75aad648a5b8353f8527bc1509", "completedAt": "2026-09-20T04:11:12.864451+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:11:04.927041+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4ad00cd3724f493ea541d5f441639476", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "reason": null, "reconciledAt": "2026-09-20T04:11:14.265257+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "4970526", "taskType": "text-generation"} {"batchId": "4b2c1e75aad648a5b8353f8527bc1509", "completedAt": "2026-09-20T04:11:12.864466+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:11:04.927176+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6172335afbf14bb088bdee43f944a59c", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "reason": null, "reconciledAt": "2026-09-20T04:11:14.264522+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4970527", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023508+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e5bb44d64e54a209e25ff21ee3ce566", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023625+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da1372df3b344dccaabbc5999e6967e8", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023687+00:00", "framework": "vllm_tokenizer_patch", "intentId": "894440f74c8d4e43b87337d70fdca6d0", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023736+00:00", "framework": "vllm-mlu", "intentId": "572b2bb7a27d450f8142ed59c8880c64", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023789+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ffcb7ff87bc740f09f403a2c9ca5f296", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023833+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b85af3d6cd8746f3a15cd847b02c4afb", "lastModified": "2026-08-24T20:10:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023875+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c6a26374779a44a089959c5adb6bbfb3", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023918+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0db0f3544e804c3dae2abbb15ef06bfd", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023961+00:00", "framework": "vllm_tokenizer_patch", "intentId": "18be3134e43e4a34b6b5c39fb1fddb76", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024010+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a2a1b1b05984448885a7b7c9cb980c4b", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024059+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4b8e42a7cfd7481baa28a88cfffbbbef", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024098+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bfbf2fb8dc0a4f84bedfa677948d703c", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024135+00:00", "framework": "vllm-mlu", "intentId": "60fb7dac0ced4c39963e1d4c31a33f21", "lastModified": "2026-08-24T20:26:05+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024200+00:00", "framework": "vllm-mlu", "intentId": "2e6a96f31ff24899abbbf59d9ddf37d4", "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}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024262+00:00", "framework": "vllm", "intentId": "29cab42e754f4dfc9f2b19a67fd195ad", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024320+00:00", "framework": "vllm", "intentId": "7fe562be76574cb4bea7fc2668703789", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024376+00:00", "framework": "vllm", "intentId": "bb296546f5664a14bf4f515714909827", "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": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024429+00:00", "framework": "vllm", "intentId": "8a45c7dc09814b0e8658eee43a62d770", "lastModified": "2026-08-24T20:31:44+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024478+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c9b4a1a871974b3faf903468341740f2", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024520+00:00", "framework": "transformers", "intentId": "fca5c13089a74b51848e88faacf9fe0c", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024582+00:00", "framework": "transformers", "intentId": "413f96377b7b4a80a12582d5a5b47494", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024643+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3c835f627cef4c8fb65af21a0c15bc58", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024690+00:00", "framework": "vllm", "intentId": "7dc54d2d28a74ba58db0f26b7268454d", "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}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024737+00:00", "framework": "vllm", "intentId": "525a93d1e4b041178c08580f0f04c099", "lastModified": "2026-08-24T20:23:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024784+00:00", "framework": "vllm", "intentId": "6520cf10f5cf4197b04c3f73fb1fce1f", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024831+00:00", "framework": "vllm", "intentId": "9ca119a3da8e44b1939b53fff4d1c4ae", "lastModified": "2026-08-24T20:15:51+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024878+00:00", "framework": "vllm-customized", "intentId": "dfbb12ee49de40e9b30bd86fbeee06b2", "lastModified": "2026-08-24T20:38:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024935+00:00", "framework": "vllm-customized", "intentId": "4f4250ebbd06445f9475710d7e2d933d", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024992+00:00", "framework": "vllm-customized", "intentId": "d3c85dd076124f78863ad6a123b6a965", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025049+00:00", "framework": "vllm-customized", "intentId": "b89880ab9eb6494d9ddbf8d90d41a638", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025105+00:00", "framework": "vllm", "intentId": "286db9dcbe66488cae8010c65b910dad", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025161+00:00", "framework": "vllm", "intentId": "29149886f8014827b92665ec994be4e9", "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": "MetaX_c-500", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025212+00:00", "framework": "vllm", "intentId": "202e2dbad9b347c6aa3d4eeca390af43", "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": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025268+00:00", "framework": "vllm", "intentId": "1641bf865cc34a68a685e8b6d0f57bc3", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214643+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023508+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e5bb44d64e54a209e25ff21ee3ce566", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4970572", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214663+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023625+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da1372df3b344dccaabbc5999e6967e8", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "reason": null, "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4970575", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214680+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023687+00:00", "framework": "vllm_tokenizer_patch", "intentId": "894440f74c8d4e43b87337d70fdca6d0", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "reason": null, "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4970569", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214684+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023736+00:00", "framework": "vllm-mlu", "intentId": "572b2bb7a27d450f8142ed59c8880c64", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970576", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214688+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023789+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ffcb7ff87bc740f09f403a2c9ca5f296", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Vastai_va16", "taskId": "4970571", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214692+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023833+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b85af3d6cd8746f3a15cd847b02c4afb", "lastModified": "2026-08-24T20:10:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214695+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023875+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c6a26374779a44a089959c5adb6bbfb3", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970577", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214698+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023918+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0db0f3544e804c3dae2abbb15ef06bfd", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970573", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214701+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.023961+00:00", "framework": "vllm_tokenizer_patch", "intentId": "18be3134e43e4a34b6b5c39fb1fddb76", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "reason": null, "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970567", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214704+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024010+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a2a1b1b05984448885a7b7c9cb980c4b", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "reason": null, "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970578", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214707+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024059+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4b8e42a7cfd7481baa28a88cfffbbbef", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4970574", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214710+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024098+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bfbf2fb8dc0a4f84bedfa677948d703c", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4970570", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214712+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024135+00:00", "framework": "vllm-mlu", "intentId": "60fb7dac0ced4c39963e1d4c31a33f21", "lastModified": "2026-08-24T20:26:05+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970582", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214715+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024200+00:00", "framework": "vllm-mlu", "intentId": "2e6a96f31ff24899abbbf59d9ddf37d4", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970585", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214718+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024262+00:00", "framework": "vllm", "intentId": "29cab42e754f4dfc9f2b19a67fd195ad", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "reason": null, "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970589", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214721+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024320+00:00", "framework": "vllm", "intentId": "7fe562be76574cb4bea7fc2668703789", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970579", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214724+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024376+00:00", "framework": "vllm", "intentId": "bb296546f5664a14bf4f515714909827", "lastModified": "2026-08-24T20:30:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "reason": null, "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970583", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214727+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024429+00:00", "framework": "vllm", "intentId": "8a45c7dc09814b0e8658eee43a62d770", "lastModified": "2026-08-24T20:31:44+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970586", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214730+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024478+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c9b4a1a871974b3faf903468341740f2", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "reason": null, "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970587", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214733+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024520+00:00", "framework": "transformers", "intentId": "fca5c13089a74b51848e88faacf9fe0c", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970590", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214736+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024582+00:00", "framework": "transformers", "intentId": "413f96377b7b4a80a12582d5a5b47494", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970580", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214739+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024643+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3c835f627cef4c8fb65af21a0c15bc58", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "reason": null, "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970581", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214741+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024690+00:00", "framework": "vllm", "intentId": "7dc54d2d28a74ba58db0f26b7268454d", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "reason": null, "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970584", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214744+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024737+00:00", "framework": "vllm", "intentId": "525a93d1e4b041178c08580f0f04c099", "lastModified": "2026-08-24T20:23:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970588", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214747+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024784+00:00", "framework": "vllm", "intentId": "6520cf10f5cf4197b04c3f73fb1fce1f", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "reason": null, "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970591", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214750+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024831+00:00", "framework": "vllm", "intentId": "9ca119a3da8e44b1939b53fff4d1c4ae", "lastModified": "2026-08-24T20:15:51+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970594", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214753+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024878+00:00", "framework": "vllm-customized", "intentId": "dfbb12ee49de40e9b30bd86fbeee06b2", "lastModified": "2026-08-24T20:38:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970598", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214756+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024935+00:00", "framework": "vllm-customized", "intentId": "4f4250ebbd06445f9475710d7e2d933d", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970592", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214759+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.024992+00:00", "framework": "vllm-customized", "intentId": "d3c85dd076124f78863ad6a123b6a965", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970595", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214761+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025049+00:00", "framework": "vllm-customized", "intentId": "b89880ab9eb6494d9ddbf8d90d41a638", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970596", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214764+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025105+00:00", "framework": "vllm", "intentId": "286db9dcbe66488cae8010c65b910dad", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "reason": null, "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214767+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025161+00:00", "framework": "vllm", "intentId": "29149886f8014827b92665ec994be4e9", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "MetaX_c-500", "taskId": "4970593", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214771+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025212+00:00", "framework": "vllm", "intentId": "202e2dbad9b347c6aa3d4eeca390af43", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4970599", "taskType": "text-generation"} +{"batchId": "76464b8d79c74b00bbd4e97d75b26a1f", "completedAt": "2026-09-20T04:14:42.214774+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:14:33.025268+00:00", "framework": "vllm", "intentId": "1641bf865cc34a68a685e8b6d0f57bc3", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4970597", "taskType": "text-generation"} {"batchId": "a0638aa6b9d441fc8127d1ff98b0380e", "completedAt": "2026-09-20T02:22:36.529135+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-10T13:27:22.633245+00:00", "framework": "vllm", "intentId": "8986a9476a034876a874432fe981a93c", "repoId": "laion/swesmith-nl2bash-stack-bugsseq", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "success", "targetGpu": "Biren_166m", "taskId": "4760700", "taskType": "text-generation"} {"batchId": "3601d2529e2f4dbab4abc91721a031a6", "completedAt": "2026-09-20T01:08:42.115049+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-19T12:27:15.291074+00:00", "framework": "vllm_tokenizer_patch", "intentId": "56909ec2a21e4e3f9e0a55deb70d46c0", "repoId": "Arain119/Sophia", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Ascend_910-b3", "taskId": "4956471", "taskType": "text-generation"} {"batchId": "17f9bc75c9254b23a97517096a945dfd", "completedAt": "2026-09-20T00:27:18.357432+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-09T17:53:27.791335+00:00", "framework": "vllm-mlu", "intentId": "e8b41bd8a15a4f4ab9051c3e998dfc85", "repoId": "laion/swesmith-nl2bash-stack-bugsseq", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "success", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4744096", "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index bd5452de94..e0400c01e8 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,43 +1,43 @@ { "acceptedByCategory": { - "unified_success_first": 1609 + "unified_success_first": 1643 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|vllm": 31, - "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 114, + "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 116, "text-generation|Ascend_910-b4|llamacpp": 13, - "text-generation|Ascend_910-b4|vllm": 16, - "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 101, + "text-generation|Ascend_910-b4|vllm": 18, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 104, "text-generation|Biren_166m|vllm": 69, "text-generation|Biren_166m|vllm_fix_tokenizer": 13, - "text-generation|Cambricon_mlu-370-x4|vllm": 44, + "text-generation|Cambricon_mlu-370-x4|vllm": 48, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 2, - "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 77, - "text-generation|Cambricon_mlu-370-x8|vllm": 39, - "text-generation|Cambricon_mlu-370-x8|vllm-customized": 18, - "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 82, + "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 78, + "text-generation|Cambricon_mlu-370-x8|vllm": 41, + "text-generation|Cambricon_mlu-370-x8|vllm-customized": 22, + "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 84, "text-generation|Iluvatar_bi-150|llamacpp": 16, - "text-generation|Iluvatar_bi-150|transformers": 3, + "text-generation|Iluvatar_bi-150|transformers": 5, "text-generation|Iluvatar_bi-150|vllm": 6, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 95, - "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 21, - "text-generation|Iluvatar_mrv-100|vllm": 60, - "text-generation|Kunlunxin_p-800|vllm": 2, - "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 159, - "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 51, - "text-generation|MetaX_c-500|vllm": 103, + "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 22, + "text-generation|Iluvatar_mrv-100|vllm": 61, + "text-generation|Kunlunxin_p-800|vllm": 3, + "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 162, + "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 53, + "text-generation|MetaX_c-500|vllm": 104, "text-generation|Mthreads_s4000|llamacpp": 17, - "text-generation|Mthreads_s4000|vllm": 97, + "text-generation|Mthreads_s4000|vllm": 98, "text-generation|Sunrise_pt-200-x1|vllm": 62, "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 62, - "text-generation|Vastai_va16|vllm_fix_tokenizer": 70, + "text-generation|Vastai_va16|vllm_fix_tokenizer": 71, "text-generation|hygon_k100-ai|llamacpp": 18, "text-generation|hygon_k100-ai|vllm": 26, - "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 105 + "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 106 }, - "acceptedSinceRefresh": 1609, - "acceptedTotal": 1609, - "generatedAt": "2026-09-20T04:11:12.808603+00:00", + "acceptedSinceRefresh": 1643, + "acceptedTotal": 1643, + "generatedAt": "2026-09-20T04:14:42.158522+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 9a18ae5b5b..1b63e09457 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -970,3 +970,37 @@ {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "submitTime": "2026-09-20T03:57:37.834872+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970331", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "submitTime": "2026-09-20T03:57:37.837081+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970332", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "submitTime": "2026-09-20T03:57:37.819101+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970330", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "submitTime": "2026-09-20T04:14:34.851058+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970572", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "submitTime": "2026-09-20T04:14:34.909060+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970575", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "submitTime": "2026-09-20T04:14:34.794463+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970569", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "submitTime": "2026-09-20T04:14:34.933362+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970576", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "submitTime": "2026-09-20T04:14:34.792755+00:00", "targetGpu": "Vastai_va16", "taskId": "4970571", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "submitTime": "2026-09-20T04:14:34.915616+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970577", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"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": "2026-09-20T04:14:34.920885+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970573", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-20T04:14:34.845570+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970567", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-20T04:14:34.911597+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970578", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-20T04:14:34.922099+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970574", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T04:14:34.856488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970570", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T04:14:41.836936+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970582", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "submitTime": "2026-09-20T04:14:41.857836+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970585", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "modelId": "LiquidAI/LFM2.5-2.6B", "submitTime": "2026-09-20T04:14:41.844966+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970589", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "submitTime": "2026-09-20T04:14:41.811307+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970579", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "submitTime": "2026-09-20T04:14:41.850857+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970583", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T04:14:41.835776+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970586", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "modelId": "BAAI/AquilaMed-RL", "submitTime": "2026-09-20T04:14:41.855366+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970587", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} +{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "submitTime": "2026-09-20T04:14:41.846486+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970590", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} +{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "submitTime": "2026-09-20T04:14:41.848764+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970580", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} +{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "submitTime": "2026-09-20T04:14:41.838656+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970581", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "modelId": "neuralmagic/starcoder2-15b-FP8", "submitTime": "2026-09-20T04:14:41.835421+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970584", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T04:14:41.853833+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970588", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "modelId": "RedHatAI/starcoder2-15b-FP8", "submitTime": "2026-09-20T04:14:41.990095+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970591", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T04:14:42.084586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970594", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T04:14:42.070470+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970598", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "submitTime": "2026-09-20T04:14:42.077355+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970592", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "submitTime": "2026-09-20T04:14:42.081414+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970595", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "submitTime": "2026-09-20T04:14:42.074603+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970596", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "submitTime": "2026-09-20T04:14:42.093442+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "submitTime": "2026-09-20T04:14:42.066492+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970593", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-20T04:14:42.086692+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970599", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-20T04:14:42.090996+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970597", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"} diff --git a/manifest.json b/manifest.json index 0b3e468f37..29c0a37e1b 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "21a630cefff5c090992ca8360dafe8435b598ca2102f1b9990df6496329a9afe", ".modelhub_state/recent_outcomes.jsonl": "8b230beac27183f4f5f556eaa061dbc77bdcc47b761f379a572673e0fba55aaa", ".modelhub_state/recovery_active_tasks.jsonl": "1e46efe936ad9ca5d5f6038ff8383e9208c958b77e9c807a34380a69ff70dd2b", - ".modelhub_state/recovery_intents.jsonl": "2c12204dc10d52fcc667565165ca6c1bd30acd8273d4e9a1ce2d7b57a50b14f7", - ".modelhub_state/routing_intelligence.json": "f6ea35420c39809f9df76c2dfd16c8aa3b955d524f3cfe2e914041baad88f6b4", + ".modelhub_state/recovery_intents.jsonl": "f59a3d5b50e2ccec3556aede3ba9fccc9878b84eecd6047fc06f0db197524322", + ".modelhub_state/routing_intelligence.json": "fe6e841247cc57f9189123b338f3e1f5f96143421a0c883c6c2b861cea97cc47", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "33b2da3b3bb4e1624c437e31234f9af5f1a4076f097f8af0078aa9e8fce9e562", - "outcomes/submissions.jsonl": "0af3a9cd6d8c87042598a0540e301b95b09a293198f3c44f99b843d413a9ce2a" + "ledger/submissions.jsonl": "864993e6c8040cbad057a43c713dd3d8fe9a8bae3a19f4032555d3b40d2b4589", + "outcomes/submissions.jsonl": "75aa37ec0974ad91d11bee8be63c246c32fde872c76f502c1593a56e167edfab" }, - "generation": 10179, - "phase": "intent", + "generation": 10180, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T04:14:33.140575+00:00", + "updatedAt": "2026-09-20T04:14:42.384287+00:00", "writerId": "f67e4ec113c04968a9d9484fb8e36bd4" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 8b1b3656bc..113e96c59f 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -994,3 +994,37 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:10:03.058495+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970512", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "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": 955857175}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:11:06.667095+00:00", "targetGpu": "Vastai_va16", "taskId": "4970526", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:11:06.683086+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970527", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626643, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626643}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.851058+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970572", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.909060+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970575", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860631926, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860631926}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.794463+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970569", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.933362+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970576", "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": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T04:14:34.792755+00:00", "targetGpu": "Vastai_va16", "taskId": "4970571", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251763}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.915616+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970577", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.920885+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970573", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.845570+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970567", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020563851}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.911597+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970578", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673858}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.922099+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970574", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:34.856488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970570", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720442075}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.836936+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970582", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.857836+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970585", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.844966+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970589", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.811307+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970579", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2263018168, "estimatedRequiredGiB": 2.532, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 2265562651, "modelscopeLicense": "llama2", "modelscopeParams": 3821079552, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2265562651}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.850857+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970583", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.835776+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970586", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.855366+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970587", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.846486+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970590", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.848764+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970580", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.838656+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970581", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142341, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142341}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.835421+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970584", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.853833+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970588", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142065}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:41.990095+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970591", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236688}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:42.084586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970594", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:42.070470+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970598", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:42.077355+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970592", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:42.081414+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970595", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T04:14:42.074603+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970596", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-20T04:14:42.093442+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:42.066492+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970593", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "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": 6768615496}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:42.086692+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970599", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663867}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:14:42.090996+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970597", "taskType": "text-generation", "verifyResult": null}