diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index d597786854..9c101b7562 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1558,63 +1558,63 @@ {"batchId": "22985c0652314c9da91d705e62b9a761", "completedAt": "2026-09-20T06:22:58.008314+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:15:57.087133+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2117d361eefc46dbb71f012a4474709c", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-20T06:28:09.515696+00:00", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation"} {"batchId": "22985c0652314c9da91d705e62b9a761", "completedAt": "2026-09-20T06:22:58.008383+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:15:57.088163+00:00", "framework": "vllm", "intentId": "5df2b8a3a7eb43258594502d581688f9", "lastModified": "2026-08-24T20:23:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T06:28:09.515202+00:00", "repoId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4972230", "taskType": "text-generation"} {"batchId": "22985c0652314c9da91d705e62b9a761", "completedAt": "2026-09-20T06:22:58.008418+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:15:57.088814+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c74f257fec524656aa4afd0e30062bcf", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "reason": null, "reconciledAt": "2026-09-20T06:28:09.516394+00:00", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "4972231", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606287+00:00", "framework": "vllm_tokenizer_patch", "intentId": "98479c38517546c8a635976dd2fa021b", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606395+00:00", "framework": "vllm_tokenizer_patch", "intentId": "776921d6cd814bf886369627552a214a", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606450+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6aa30e63610047d1acf8812d50d0b4ec", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606501+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e6a328df6d74804b2fdc05a8a6cb69c", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606551+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c83d16a8743b47e4a3ece68a5152fe7d", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606595+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec41ff2069eb4885876ecf465a687fbc", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606639+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5a229942665943feb9f34c3d48075e39", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606691+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4c74780633db43b3ad416958ea296a9d", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606741+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2f64d9c30a19478182db3af85019c198", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606791+00:00", "framework": "vllm_tokenizer_patch", "intentId": "005e0fddd75048bc9892ff09581f61bd", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606865+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3a23954bc0244af48ec261ab0ddd5e92", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606916+00:00", "framework": "vllm_tokenizer_patch", "intentId": "252307a729a34349b9ff6c77ac9bfd60", "lastModified": "2026-09-04T14:33:33+00:00", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "repoId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606965+00:00", "framework": "vllm_tokenizer_patch", "intentId": "edc2c6944ada46879eb127eb824b3ffb", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607005+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bcd0e942b58249dfb3670237048f02bc", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607044+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a8a3b819abd44d6899228f75612399aa", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607082+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c09b580138ab4f3dbc5830150e031732", "lastModified": "2026-08-24T19:54:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607119+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a6583e355fc74e14955eb0fb8d8e3db6", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607158+00:00", "framework": "vllm_tokenizer_patch", "intentId": "92bd51395ffc44209ea0d73fdcb05768", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607196+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b81775bbfaf54fbd8f5dbaa554360e07", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607233+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4abb9ffd304a4767a807003a8321c64d", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607270+00:00", "framework": "vllm_tokenizer_patch", "intentId": "953ad3b8a1a14ee09fb065c65742841c", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607324+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5625853f83f544b9b5c69a4a068a2a30", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607362+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4bf0969610444603aaff42df49e84736", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607400+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6af243c8d55444eda2f9a687fe999309", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607437+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a5ffa2e57d0e47da940794f83aa169e0", "lastModified": "2026-08-24T20:02:14+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607475+00:00", "framework": "vllm-mlu", "intentId": "415221d94f704418b4cc161f3287f9dc", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607543+00:00", "framework": "vllm-mlu", "intentId": "e0d69886155b4d16b616f9ea9c7a274f", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607608+00:00", "framework": "vllm", "intentId": "00442d6e83854341a55249679a8b18c1", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607672+00:00", "framework": "vllm", "intentId": "718aff5da8524dea989526c40d96f37c", "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": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607727+00:00", "framework": "vllm", "intentId": "d49ac806d3a344419e6a9d1e77c0af71", "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": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607796+00:00", "framework": "vllm", "intentId": "98f39bcd92e14f04af75182c0c789737", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607849+00:00", "framework": "vllm", "intentId": "ca5bfefc64874bbb89cd21f3e918036e", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607904+00:00", "framework": "vllm", "intentId": "2a7b33fd83684c879ccea1d5cf6808f5", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607959+00:00", "framework": "vllm", "intentId": "ebd307cf8fb14d66876ef23a07df3002", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608013+00:00", "framework": "vllm", "intentId": "b658a95984f94a9498624d378b7ddb0c", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608067+00:00", "framework": "vllm", "intentId": "91f14ae565294f4aac74df5763a46157", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608122+00:00", "framework": "vllm", "intentId": "3405facadbfb41ddb0b1c7fe28d2f255", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608176+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d2ee90d68cc4384945e1c25e576f602", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608224+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a245d849d2d34cf09cb0fbc0b58da908", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608280+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b0b8abfad4c0457e8df2ad3c45f644ea", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608323+00:00", "framework": "vllm_fix_tokenizer", "intentId": "14bc227dda5f4a5c9e0fa764d8bc703c", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608366+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c7d8c0c578a640378a5413bd140e9828", "lastModified": "2026-09-01T03:45:04+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608408+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a6c1dcc8e17a498aa40824d95ee496a0", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608451+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3cf875d64c7345818de6b62744f01ada", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608493+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec807bee1a21408b80a22aa7c9fa72f8", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608536+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2bb4b17a92154ecf85204d2e277ca3d8", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608579+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6b83bb74f762404793e9340df370b253", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608622+00:00", "framework": "transformers", "intentId": "157f21960675442cb4aea545b8ad7b66", "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": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608716+00:00", "framework": "transformers", "intentId": "f89567880d1f448abda551db598f0b7a", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608779+00:00", "framework": "transformers", "intentId": "0ac1ee3b28f443d2a924496c0d3ace20", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608841+00:00", "framework": "transformers", "intentId": "ea8643156cb9445e87c3dbd30e20f353", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608903+00:00", "framework": "transformers", "intentId": "dae4cc90cbbd4f089d24955408443a9e", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608968+00:00", "framework": "transformers", "intentId": "cb33956791c347d3bf060cbb058d2dbc", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.609047+00:00", "framework": "transformers", "intentId": "3e485287fe3b49a585c9df29603f0aba", "lastModified": "2026-09-11T12:06:58+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.609109+00:00", "framework": "transformers", "intentId": "e335ee4374454e2789517a5ed14d09d6", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.609171+00:00", "framework": "transformers", "intentId": "c1c432d10dda4b1b872938f6a8e78f9c", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "60a50a77283e4c7896fd913b214d3112", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.609232+00:00", "framework": "transformers", "intentId": "0cca18cf4cf8490d88818323f92a1638", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906729+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606395+00:00", "framework": "vllm_tokenizer_patch", "intentId": "776921d6cd814bf886369627552a214a", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4972399", "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906769+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607044+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a8a3b819abd44d6899228f75612399aa", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "reason": null, "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4972417", "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906800+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607543+00:00", "framework": "vllm-mlu", "intentId": "e0d69886155b4d16b616f9ea9c7a274f", "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": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972418", "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906813+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607849+00:00", "framework": "vllm", "intentId": "ca5bfefc64874bbb89cd21f3e918036e", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "reason": null, "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906878+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.609232+00:00", "framework": "transformers", "intentId": "0cca18cf4cf8490d88818323f92a1638", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906875+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.609171+00:00", "framework": "transformers", "intentId": "c1c432d10dda4b1b872938f6a8e78f9c", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906873+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.609109+00:00", "framework": "transformers", "intentId": "e335ee4374454e2789517a5ed14d09d6", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906871+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.609047+00:00", "framework": "transformers", "intentId": "3e485287fe3b49a585c9df29603f0aba", "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906868+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608968+00:00", "framework": "transformers", "intentId": "cb33956791c347d3bf060cbb058d2dbc", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906866+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608903+00:00", "framework": "transformers", "intentId": "dae4cc90cbbd4f089d24955408443a9e", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906863+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608841+00:00", "framework": "transformers", "intentId": "ea8643156cb9445e87c3dbd30e20f353", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906861+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608779+00:00", "framework": "transformers", "intentId": "0ac1ee3b28f443d2a924496c0d3ace20", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906858+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608716+00:00", "framework": "transformers", "intentId": "f89567880d1f448abda551db598f0b7a", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906856+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608622+00:00", "framework": "transformers", "intentId": "157f21960675442cb4aea545b8ad7b66", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906853+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608579+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6b83bb74f762404793e9340df370b253", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906850+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608536+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2bb4b17a92154ecf85204d2e277ca3d8", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906847+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608493+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec807bee1a21408b80a22aa7c9fa72f8", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906844+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608451+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3cf875d64c7345818de6b62744f01ada", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906841+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608408+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a6c1dcc8e17a498aa40824d95ee496a0", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906838+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608366+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c7d8c0c578a640378a5413bd140e9828", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906835+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608323+00:00", "framework": "vllm_fix_tokenizer", "intentId": "14bc227dda5f4a5c9e0fa764d8bc703c", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906833+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608280+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b0b8abfad4c0457e8df2ad3c45f644ea", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906830+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608224+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a245d849d2d34cf09cb0fbc0b58da908", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906828+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608176+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d2ee90d68cc4384945e1c25e576f602", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906825+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608122+00:00", "framework": "vllm", "intentId": "3405facadbfb41ddb0b1c7fe28d2f255", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906822+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608067+00:00", "framework": "vllm", "intentId": "91f14ae565294f4aac74df5763a46157", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906820+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.608013+00:00", "framework": "vllm", "intentId": "b658a95984f94a9498624d378b7ddb0c", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906818+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607959+00:00", "framework": "vllm", "intentId": "ebd307cf8fb14d66876ef23a07df3002", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906815+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607904+00:00", "framework": "vllm", "intentId": "2a7b33fd83684c879ccea1d5cf6808f5", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906810+00:00", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607796+00:00", "framework": "vllm", "intentId": "98f39bcd92e14f04af75182c0c789737", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906808+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607727+00:00", "framework": "vllm", "intentId": "d49ac806d3a344419e6a9d1e77c0af71", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906805+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607672+00:00", "framework": "vllm", "intentId": "718aff5da8524dea989526c40d96f37c", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906803+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607608+00:00", "framework": "vllm", "intentId": "00442d6e83854341a55249679a8b18c1", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906798+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607475+00:00", "framework": "vllm-mlu", "intentId": "415221d94f704418b4cc161f3287f9dc", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906795+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607437+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a5ffa2e57d0e47da940794f83aa169e0", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906792+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607400+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6af243c8d55444eda2f9a687fe999309", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906790+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607362+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4bf0969610444603aaff42df49e84736", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906787+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607324+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5625853f83f544b9b5c69a4a068a2a30", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906785+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607270+00:00", "framework": "vllm_tokenizer_patch", "intentId": "953ad3b8a1a14ee09fb065c65742841c", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906782+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607233+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4abb9ffd304a4767a807003a8321c64d", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906780+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607196+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b81775bbfaf54fbd8f5dbaa554360e07", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906777+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607158+00:00", "framework": "vllm_tokenizer_patch", "intentId": "92bd51395ffc44209ea0d73fdcb05768", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906774+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607119+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a6583e355fc74e14955eb0fb8d8e3db6", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906772+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607082+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c09b580138ab4f3dbc5830150e031732", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906767+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.607005+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bcd0e942b58249dfb3670237048f02bc", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906764+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606965+00:00", "framework": "vllm_tokenizer_patch", "intentId": "edc2c6944ada46879eb127eb824b3ffb", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906761+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606916+00:00", "framework": "vllm_tokenizer_patch", "intentId": "252307a729a34349b9ff6c77ac9bfd60", "repoId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906758+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606865+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3a23954bc0244af48ec261ab0ddd5e92", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906756+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606791+00:00", "framework": "vllm_tokenizer_patch", "intentId": "005e0fddd75048bc9892ff09581f61bd", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906753+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606741+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2f64d9c30a19478182db3af85019c198", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906750+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606691+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4c74780633db43b3ad416958ea296a9d", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906748+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606639+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5a229942665943feb9f34c3d48075e39", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906745+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606595+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ec41ff2069eb4885876ecf465a687fbc", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906741+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606551+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c83d16a8743b47e4a3ece68a5152fe7d", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906737+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606501+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e6a328df6d74804b2fdc05a8a6cb69c", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906733+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606450+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6aa30e63610047d1acf8812d50d0b4ec", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "60a50a77283e4c7896fd913b214d3112", "completedAt": "2026-09-20T06:38:28.906715+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:31:44.606287+00:00", "framework": "vllm_tokenizer_patch", "intentId": "98479c38517546c8a635976dd2fa021b", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "e1b8d0f2a3d8428ead394386943ec4f5", "completedAt": "2026-09-20T06:26:24.015199+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:22:58.850672+00:00", "framework": "vllm", "intentId": "bee2c33e984543c28c8f3bfcbe2c00aa", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "e1b8d0f2a3d8428ead394386943ec4f5", "completedAt": "2026-09-20T06:26:24.015196+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:22:58.850609+00:00", "framework": "vllm", "intentId": "a9e176741cc949f39f28f0a2e59495fb", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "e1b8d0f2a3d8428ead394386943ec4f5", "completedAt": "2026-09-20T06:26:24.015193+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:22:58.850551+00:00", "framework": "vllm", "intentId": "e7a98c66d687412bb0e504eb3f80e78c", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} @@ -1862,56 +1862,3 @@ {"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:52:06.188983+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021749+00:00", "framework": "vllm", "intentId": "f31d9385d9284f9eb1aacbbea4d7a7b7", "repoId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "failed", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712834", "taskType": "text-generation"} {"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.019563+00:00", "framework": "vllm-mlu", "intentId": "93d41e6d138a4e949042087e533cdc9a", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "failed", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712800", "taskType": "text-generation"} {"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.020055+00:00", "framework": "vllm-mlu", "intentId": "3b0a6b2fd4c2450ebdfa9f5fea35a64e", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "failed", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712799", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.020117+00:00", "framework": "vllm-mlu", "intentId": "789ad60d319c4550b6f8d275df42b642", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "failed", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712801", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021255+00:00", "framework": "vllm", "intentId": "03d03ad1c6c34a29bf229ab22ab77d05", "repoId": "ornith-ai/Ornith-1.5-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "failed", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712832", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021313+00:00", "framework": "vllm", "intentId": "b8e24cd3a8c2447cb5979dd7cc7df0af", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712828", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021368+00:00", "framework": "vllm", "intentId": "ffeec8adadd7411cb4fa8a299224d9e6", "repoId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712823", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021478+00:00", "framework": "vllm", "intentId": "41cf42cf50c94c158c617fb240264cf0", "repoId": "empero-ai/Qwen3.8-9B-Distill", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712827", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021532+00:00", "framework": "vllm", "intentId": "040f531cfb9f4a1ba5dad83601afaec9", "repoId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712826", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021586+00:00", "framework": "vllm", "intentId": "a1e6d38884db4181b2c1d03823059312", "repoId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712830", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021641+00:00", "framework": "vllm", "intentId": "3578b21bd9d14b9a9e7c74fc2ade691a", "repoId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712829", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021695+00:00", "framework": "vllm", "intentId": "5df5ee94ba0941448a093d97a1ba4079", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712833", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021802+00:00", "framework": "vllm", "intentId": "0e23247dfbf644059904b1702130036a", "repoId": "empero-ai/Qwen3.8-4B-Distill", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712835", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021856+00:00", "framework": "vllm", "intentId": "10d1c4d259584b398ef709ab84824084", "repoId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712837", "taskType": "text-generation"} -{"batchId": "3a665fff32cd431dac134620648d6618", "completedAt": "2026-09-08T15:44:01.314865+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:46:06.021910+00:00", "framework": "vllm", "intentId": "91eb893dfa424fe9bfb7852d6bcc9b84", "repoId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "policy_cancelled", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation"} -{"batchId": "10f5a74bc93d4abfb75bb7685c67b38c", "completedAt": "2026-09-08T15:22:59.434461+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-04T21:32:44.453160+00:00", "framework": "vllm", "intentId": "57f7f1ecd5964d04af7f5ae8d374ff66", "repoId": "vastai-ais/GLM-OCR-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Mthreads_s4000", "taskId": "4634661", "taskType": "text-generation"} -{"batchId": "6380b42d1be24644bf4bd1f4ca84681c", "completedAt": "2026-09-08T14:28:49.850080+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-08T14:28:32.392879+00:00", "framework": "vllm_tokenizer_patch", "intentId": "432706e692664c9385287bfc5b4a0c0d", "repoId": "whq1111/M2RL-SFT", "safeConfigVector": {"gpuNum": 1}, "status": "failed", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "e6c68761e0174ed187ca143096e47468", "completedAt": "2026-09-08T13:28:12.296054+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-06T00:30:34.700742+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d0b00f5f7320407c95f6a0bea9e867c1", "repoId": "ornith-ai/Ornith-1.5-9B-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657910", "taskType": "text-generation"} -{"batchId": "9e587ab3e26e44c2a8c4cdf76d04a668", "completedAt": "2026-09-08T12:52:42.483951+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-04T04:29:14.034412+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d93832dca7c8400999029ebdc9a1336c", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611188", "taskType": "text-generation"} -{"batchId": "ed3dfa150bcc47ae8ca1119520c543f9", "completedAt": "2026-09-08T12:52:42.483951+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-04T13:43:29.875614+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1081a82b3bc449879f415e27c60fdba3", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4627497", "taskType": "text-generation"} -{"batchId": "ed3dfa150bcc47ae8ca1119520c543f9", "completedAt": "2026-09-08T12:52:42.483951+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-04T13:43:29.875769+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ad4f90962e98487c94b8cde2c2a1d925", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4627499", "taskType": "text-generation"} -{"batchId": "ed3dfa150bcc47ae8ca1119520c543f9", "completedAt": "2026-09-08T12:52:42.483951+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-04T13:43:29.875825+00:00", "framework": "vllm_fix_tokenizer", "intentId": "339831a6b60344bcaeadaf03c8103f1b", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4627498", "taskType": "text-generation"} -{"batchId": "e6c68761e0174ed187ca143096e47468", "completedAt": "2026-09-08T12:52:42.483951+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-06T00:30:34.700634+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b7eedfedada3442a98589ab40221e0b4", "repoId": "douyamv/Qwen3.8-27B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657895", "taskType": "text-generation"} -{"batchId": "e6c68761e0174ed187ca143096e47468", "completedAt": "2026-09-08T12:52:42.483951+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-06T00:30:34.701659+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7a6f8917e42244e4b89a1da1eacb7a4f", "repoId": "empero-ai/Qwen3.8-9B-Distill", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657913", "taskType": "text-generation"} -{"batchId": "9c5958c8c4834c069e33344ee747f0e2", "completedAt": "2026-09-08T11:25:41.817348+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-06T12:37:21.839011+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fefdd3aaca4e4dc38515d94e43f55e77", "repoId": "ZHTODD/llm-study-model", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Kunlunxin_p-800", "taskId": "4667092", "taskType": "text-generation"} -{"batchId": "100691b1dc0544c5aa018bdf892b98f9", "completedAt": "2026-09-08T10:26:28.594648+00:00", "configFingerprint": "34f970b6e01f1660bb20e6ced92e92ea2cde023b6fce68c2db3c60da86355277", "configSource": "modelhub_live", "createdAt": "2026-09-08T10:26:21.643059+00:00", "framework": "llamacpp", "intentId": "44a04e836f0449ddb73ead3eda1d4601", "repoId": "Mungert/s1-mini-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "506725fc9233489f937854d0af48a599", "completedAt": "2026-09-08T09:04:29.591621+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-08T09:04:10.802030+00:00", "framework": "vllm_tokenizer_patch", "intentId": "171469176beb4fc3940ebfc01e166c55", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1}, "status": "failed", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "ef85773cd8114d6880cf2b460703a109", "completedAt": "2026-09-08T07:15:24.611447+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-08T07:15:15.816226+00:00", "framework": "vllm", "intentId": "041a7cfafae449f7a171a3e1da305b6f", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "ef85773cd8114d6880cf2b460703a109", "completedAt": "2026-09-08T07:15:24.611444+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-08T07:15:15.816171+00:00", "framework": "vllm", "intentId": "10147b0ab6b3493fbbc50373d513df7e", "repoId": "nanbeige/Nanbeige4.2-3B", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "ef85773cd8114d6880cf2b460703a109", "completedAt": "2026-09-08T07:15:24.611440+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-08T07:15:15.816089+00:00", "framework": "vllm", "intentId": "4a24f9a865c14780a75fc8c360f19baf", "repoId": "OpenBMB/MiniCPM5-1B-Base", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "ef85773cd8114d6880cf2b460703a109", "completedAt": "2026-09-08T07:15:24.611436+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-08T07:15:15.816028+00:00", "framework": "vllm", "intentId": "7a39598f33ff422a9bf7f6d3d44fe7d4", "repoId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "ef85773cd8114d6880cf2b460703a109", "completedAt": "2026-09-08T07:15:24.611423+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-08T07:15:15.815910+00:00", "framework": "vllm", "intentId": "38d29881dd33492dac802fd2f1ec929e", "repoId": "OpenBMB/MiniCPM5-1B-MLX", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "92177bc2ceac4809a153985c4b3f2745", "completedAt": "2026-09-08T06:08:08.166724+00:00", "configFingerprint": "e9cd07e86276f5fee811fc4ddabd09a24003ccc7f2c5a7438fc0251496a96dd9", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:07:59.791038+00:00", "framework": "llamacpp", "intentId": "9f6fbf586a1b47efbeeb584ad750a10f", "repoId": "Mungert/s1-mini-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "e44d9b2beccc4c83938b82db7d0b2eb1", "completedAt": "2026-09-08T06:03:32.330103+00:00", "configFingerprint": "f79adc9ceb7c3c5ae9cbd3076751c0d7fa451eb2f81755c3467c7db567274aa3", "configSource": "modelhub_live", "createdAt": "2026-09-08T06:03:26.168951+00:00", "framework": "llamacpp", "intentId": "5e9cc3f50b9843a1872d3e801ae7cfb1", "repoId": "Mungert/s1-mini-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} -{"batchId": "8b622f21b1a04283ab6c2ccefd839c18", "completedAt": "2026-09-08T05:59:06.192410+00:00", "configFingerprint": "4aac302eaf4e6b649a18cf67238054066b364490c4c8db0009cb59f547dbb594", "configSource": "modelhub_live", "createdAt": "2026-09-08T05:58:57.823276+00:00", "framework": "llamacpp", "intentId": "bcfe7e8887a44465bf6da82205bcbbd6", "repoId": "Mungert/s1-mini-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "cadda9a7935640689bb0a87bbbb58b92", "completedAt": "2026-09-08T05:54:38.634116+00:00", "configFingerprint": "d83d625573987ebbd6e9cc5b86723b28e316275b88b9fe38063764f186db8a76", "configSource": "modelhub_live", "createdAt": "2026-09-08T05:54:32.000270+00:00", "framework": "llamacpp", "intentId": "7fafd7071b824ec2ac0d17a4e0be3955", "repoId": "Mungert/s1-mini-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "098529f68d314600854fc4043263aca1", "completedAt": "2026-09-08T01:20:49.384335+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-04T07:57:11.360092+00:00", "framework": "vllm", "intentId": "4330ade38dc04d7d93c53a46a0b7cbbc", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Mthreads_s4000", "taskId": "4622419", "taskType": "text-generation"} -{"batchId": "391cf91a900d46feab41966406e689e9", "completedAt": "2026-09-07T20:55:58.074822+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-06T02:28:43.196834+00:00", "framework": "vllm", "intentId": "221f65a0694843c798db3a8f7068f4c2", "repoId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659340", "taskType": "text-generation"} -{"batchId": "bde105281e84483a8d666d77df02b91e", "completedAt": "2026-09-07T20:55:58.074822+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-06T20:59:58.962914+00:00", "framework": "vllm", "intentId": "51a5ec1c46e14e0ba35b588cbeed6c32", "repoId": "mlx-community/Qwen3.8-27B-MTP-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678098", "taskType": "text-generation"} -{"batchId": "c74763998d684551b9d113d544073786", "completedAt": "2026-09-07T11:18:51.862534+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-05T16:20:37.326617+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8cbf20641a1641dabc3c3a14f17f37b9", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Vastai_va16", "taskId": "4651795", "taskType": "text-generation"} -{"batchId": "d1f0484873f54e6398d1628307e987a7", "completedAt": "2026-09-07T10:01:13.284901+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-05T16:23:34.606338+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b7b5ac48c7b54c84a03c6179abad34e0", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "Vastai_va16", "taskId": "4651830", "taskType": "text-generation"} -{"batchId": "c08d9fcca35c436faa0ad24c8d38f499", "completedAt": "2026-09-07T10:01:13.284901+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-05T16:30:07.592437+00:00", "framework": "vllm_fix_tokenizer", "intentId": "888f621634ed45d2b29d1de85ca06238", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Vastai_va16", "taskId": "4651930", "taskType": "text-generation"} -{"batchId": "d66607c3a0a04cbcaea46b7badb47bd5", "completedAt": "2026-09-07T07:47:47.313424+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-06T11:11:42.857097+00:00", "framework": "vllm", "intentId": "b49ab9d9fd6642e894cd964a71221c7f", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "MetaX_c-500", "taskId": "4666063", "taskType": "text-generation"} -{"batchId": "b5c64adfcc0c4f589b28509aa757b67d", "completedAt": "2026-09-07T06:13:51.774770+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-06T13:58:51.959421+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4c202532e551426fae7c8030f70396d5", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Kunlunxin_p-800", "taskId": "4667928", "taskType": "text-generation"} -{"batchId": "e5c99d9fc06b4810be0e75d00781f75f", "completedAt": "2026-09-07T05:35:28.244916+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-06T15:28:08.998895+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5f20c747f4d643f4bc9e071a95e54825", "repoId": "Aimiliya0011/lora_4090", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Kunlunxin_p-800", "taskId": "4669867", "taskType": "text-generation"} -{"batchId": "1622ad83ad3b45a18d141f84ef6b89cf", "completedAt": "2026-09-07T04:05:16.056495+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-06T10:24:49.294207+00:00", "framework": "vllm", "intentId": "34ff800c4fb84b87b8372834b3164b2d", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "MetaX_c-500", "taskId": "4665471", "taskType": "text-generation"} -{"batchId": "13ab0bcdc10243f797da99571e3b7b49", "completedAt": "2026-09-07T02:56:43.982886+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-06T15:05:38.419546+00:00", "framework": "vllm_fix_tokenizer", "intentId": "377e20fc995342219ea3e4024cedcbdb", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Kunlunxin_p-800", "taskId": "4669334", "taskType": "text-generation"} -{"batchId": "a260aa1631c34095a44e2bd41c2cef1c", "completedAt": "2026-09-06T23:17:09.169531+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-06T08:39:19.746365+00:00", "framework": "vllm", "intentId": "cf9a3aaaa114431a8283b97c7fcfef60", "repoId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "MetaX_c-500", "taskId": "4664213", "taskType": "text-generation"} -{"batchId": "1622ad83ad3b45a18d141f84ef6b89cf", "completedAt": "2026-09-06T23:17:09.169531+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-06T10:24:49.294376+00:00", "framework": "vllm", "intentId": "a2a6984ca25040a5bd781cbfd693f433", "repoId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "policy_cancelled", "targetGpu": "MetaX_c-500", "taskId": "4665473", "taskType": "text-generation"} -{"batchId": "1622ad83ad3b45a18d141f84ef6b89cf", "completedAt": "2026-09-06T22:56:41.472933+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-06T10:24:49.294316+00:00", "framework": "vllm", "intentId": "ded3579c42e04619be9de5ccdfee9746", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "MetaX_c-500", "taskId": "4665472", "taskType": "text-generation"} -{"batchId": "6e63e0a6e4d844daba876daee5abcf48", "completedAt": "2026-09-06T22:35:57.633492+00:00", "configFingerprint": "5dc29cb4673042e118df9721ee1fc20ce84e880992fba859071f1332bb52342f", "configSource": "modelhub_live", "createdAt": "2026-09-06T12:33:05.200153+00:00", "framework": "vllm", "intentId": "94e27f9d39224cb7a68fe8b07d85c93e", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "failed", "targetGpu": "MetaX_c-500", "taskId": "4667038", "taskType": "text-generation"} -{"batchId": "d4d6f4a97e574d62ab34bd9a729873fd", "completedAt": "2026-09-06T21:46:41.367467+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-06T21:46:27.473037+00:00", "framework": "vllm", "intentId": "9eb03c174c794803bb540fb604c40b71", "repoId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "e9727ffabf8149918a92d89f7472b45c", "completedAt": "2026-09-06T21:38:45.325225+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-06T21:38:25.130886+00:00", "framework": "vllm", "intentId": "4218fa2bc78141399966b6f23d8a10b3", "repoId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "e9727ffabf8149918a92d89f7472b45c", "completedAt": "2026-09-06T21:38:45.325212+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-06T21:38:25.130756+00:00", "framework": "vllm", "intentId": "e6a84dc1f550447ab77b57b02d964cc1", "repoId": "groxaxo/qwen36-reap-2k-mlx-q8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "4e68970711e84f6a961eef0639c843fb", "completedAt": "2026-09-06T21:26:08.116041+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-06T21:25:36.453385+00:00", "framework": "vllm", "intentId": "66198db39bf94d368faeed001e7e95cd", "repoId": "nanbeige/Nanbeige4.2-3B-Base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "4e68970711e84f6a961eef0639c843fb", "completedAt": "2026-09-06T21:26:08.116033+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-06T21:25:36.453234+00:00", "framework": "vllm", "intentId": "c0b5ea94355d496caf14b8baea317b0c", "repoId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index b7fd32a47a..29976f7bf4 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,22 +1,22 @@ { "acceptedByCategory": { - "unified_success_first": 1698 + "unified_success_first": 1702 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, "text-generation|Ascend_910-b3|vllm": 31, - "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 116, + "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 117, "text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|vllm": 18, - "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 107, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 108, "text-generation|Biren_166m|vllm": 71, "text-generation|Biren_166m|vllm_fix_tokenizer": 13, "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": 79, - "text-generation|Cambricon_mlu-370-x8|vllm": 47, + "text-generation|Cambricon_mlu-370-x8|vllm": 48, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 26, - "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 88, + "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 89, "text-generation|Iluvatar_bi-150|llamacpp": 16, "text-generation|Iluvatar_bi-150|transformers": 16, "text-generation|Iluvatar_bi-150|vllm": 7, @@ -36,8 +36,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 107 }, - "acceptedSinceRefresh": 1698, - "acceptedTotal": 1698, - "generatedAt": "2026-09-20T06:26:23.955757+00:00", + "acceptedSinceRefresh": 1702, + "acceptedTotal": 1702, + "generatedAt": "2026-09-20T06:38:28.854198+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 97803f0f29..dfa2749d09 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1046,3 +1046,7 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T05:16:13.330122+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971312", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T05:16:13.358703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971314", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "modelId": "BAAI/RoboBrain2.5-8B-MT", "submitTime": "2026-09-20T05:16:13.351034+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T06:31:52.552038+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972399", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "submitTime": "2026-09-20T06:32:07.434077+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4972417", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} +{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T06:33:31.623471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972418", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "submitTime": "2026-09-20T06:34:00.535697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 45cef2a271..79c9dbb842 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "a43deb60b6f751b76576986b5c89b51a2b8d469239d82ff9136f564b25b03b2c", ".modelhub_state/recent_outcomes.jsonl": "4b7938bcc5b2b904aebaad1319021584da98a5d1dd5fda519e187df40272316c", ".modelhub_state/recovery_active_tasks.jsonl": "e19776b902ed1dcfb58ebd2dec2025a695b171cc8d19c0d3e8878e1031b01060", - ".modelhub_state/recovery_intents.jsonl": "5c4a13893e0eefbbdfd05b1fe84a5a32b028a0d431ce6bf957d8b40bcb0ac56a", - ".modelhub_state/routing_intelligence.json": "8e0609a74a7466a598d6b8f136d81b1a2c1f7544bb45469ff9641437f4d9f88f", + ".modelhub_state/recovery_intents.jsonl": "8e32b4559e7f6359bbb7ecef28acfaa47005e477ce1edb0d3cec8cc18103314e", + ".modelhub_state/routing_intelligence.json": "3d7116d677e924fdfae91624d9d04570b139e9338815db4adfd03e7b7d376ead", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "704ade86aceff2bb859bedc29e978448d95a36974801c27221c7dfb415541103", - "outcomes/submissions.jsonl": "d1a84ffbb62b1b1238a8d148183fddb0f0a0f048c5ba7e7c9bc65af1dc7e9b0b" + "ledger/submissions.jsonl": "b8f0a462ba022f48d4b3e26bf27e6e7c58e0e85084944fb8b67149612f455c48", + "outcomes/submissions.jsonl": "df498b2e8e4e8986b4f7244ad014808c44b087a01fc79e8942b5654a15506a3d" }, - "generation": 10318, - "phase": "intent", + "generation": 10319, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T06:31:44.726010+00:00", + "updatedAt": "2026-09-20T06:38:29.027116+00:00", "writerId": "fc715c06e24c4db2ae3e425e435db996" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 9317a6f3a1..406bdccaf8 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1078,3 +1078,7 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T06:17:57.834294+00:00", "targetGpu": "Biren_166m", "taskId": "4972230", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:19:35.394755+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4972231", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "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": 2033824885}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:31:52.552038+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972399", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:32:07.434077+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4972417", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T06:33:31.623471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972418", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:34:00.535697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "taskType": "text-generation", "verifyResult": null}