From 18e77102c9f34596dbe5e1b1ccba5b99ac0c197e Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sun, 20 Sep 2026 08:42:28 +0000 Subject: [PATCH] state: generation 10399 (result) --- .modelhub_state/recovery_intents.jsonl | 174 ++++++++-------------- .modelhub_state/routing_intelligence.json | 14 +- ledger/submissions.jsonl | 3 + manifest.json | 14 +- outcomes/submissions.jsonl | 3 + 5 files changed, 79 insertions(+), 129 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 9f036e03d9..21637df5b1 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1570,65 +1570,65 @@ {"batchId": "2f600fb86246427297a6ae08fe11fd12", "completedAt": "2026-09-20T07:42:18.408352+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:34:58.562414+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e7c51a01d0fc446a9541691286ab36b6", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-20T08:31:39.817799+00:00", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4973190", "taskType": "text-generation"} {"batchId": "f2d85c6f60334a4a89250cfd1042f86f", "completedAt": "2026-09-20T08:20:23.421828+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:13:26.730810+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6580905d5ba4492fadb9b0e1a4212eca", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "reason": null, "reconciledAt": "2026-09-20T08:31:39.816199+00:00", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4973783", "taskType": "text-generation"} {"batchId": "f2d85c6f60334a4a89250cfd1042f86f", "completedAt": "2026-09-20T08:20:23.421834+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:13:26.730899+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ebc93f749dbc4291844e557a622f1a8a", "lastModified": "2026-09-11T15:31:18+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "reconciledAt": "2026-09-20T08:31:39.818065+00:00", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4973784", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380303+00:00", "framework": "vllm_tokenizer_patch", "intentId": "62c16e6e832f429092fac58cd3a66901", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380461+00:00", "framework": "vllm_tokenizer_patch", "intentId": "720132407b5244cc9c46f0b8e1706c10", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380550+00:00", "framework": "vllm_tokenizer_patch", "intentId": "20f4159abc9442e7aaf947a51f998093", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380634+00:00", "framework": "vllm_tokenizer_patch", "intentId": "889823153b1f44dcbfcd38ffa69c91bd", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380715+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4ad56ef13cce45d988e431789f139fe6", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380761+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1590e651723b4713af1135dffa895a06", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380805+00:00", "framework": "vllm_fix_tokenizer", "intentId": "407f9cd63b344450acccd9ef33722ac8", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380848+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e4ed693549244b54bd270e7154e1183d", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380892+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2728429a6de45988ce6d79cdb426933", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380935+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d18d874ce31d41109c6cf331d903473d", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380978+00:00", "framework": "vllm_fix_tokenizer", "intentId": "66c769bb63f94cddb2b4149cd71c2fab", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "ecd31d4ed4e0e92b9deabe3de0f18c75dc252004ba68826e4cfd561549549074", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381021+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fa0bbe708e944508bc9d72be173396c0", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381072+00:00", "framework": "vllm_tokenizer_patch", "intentId": "af83eaa538684d3296469d1b39ac8b39", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381122+00:00", "framework": "vllm_tokenizer_patch", "intentId": "047852a0e83c43fcafb5b2c4bcfd6c07", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381171+00:00", "framework": "vllm_tokenizer_patch", "intentId": "912930ecd6394c749940c41b7a71f7c0", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381220+00:00", "framework": "vllm_tokenizer_patch", "intentId": "caffa2e4e9024809bd14d2bb94336769", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381269+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a71068b876ea401db5c4a06265957bf2", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381318+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e3a4bbfe594d4ed0a1dcf311c8c9c6fa", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381367+00:00", "framework": "vllm_tokenizer_patch", "intentId": "53e599679f28480db70a4a59302ee373", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381416+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3b9cb98a3fd44131aa757fb35c4eeb95", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381465+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8dcbcbaa6cc84a7a914b681eaa3881dc", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381514+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0c0bf5b2867646c9898c0ce81b88d110", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381576+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ab3de7381521485fad9ebe303ffcac38", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381626+00:00", "framework": "vllm_tokenizer_patch", "intentId": "518f43878f3f4c0aa6cf250f6dfac0c7", "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": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381688+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7db1f81d2c6b439599f8c6dcec17ddf9", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381729+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7156d359ca19440ebad91204bb61bb9e", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8ffb7310924a424f80e32a3094eb8fdd", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381806+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4a2303a4d30b41ad9dae459bba1952fa", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381844+00:00", "framework": "vllm-mlu", "intentId": "2da57c44a1154b9e8ad923414bfecdb2", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381911+00:00", "framework": "vllm", "intentId": "472a1bacae7a45b390dfbd0f684180e3", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381969+00:00", "framework": "vllm", "intentId": "a3e7d35f75c747abb4c21c2e1f101d9b", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382023+00:00", "framework": "vllm", "intentId": "19188e9bd4b44dddb39261b5737a977e", "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": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382077+00:00", "framework": "vllm", "intentId": "504b59f10ccf4adaad038addd474fc6c", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382129+00:00", "framework": "vllm", "intentId": "81d2242c736b41dfb706fb0f09e65c8d", "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": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382182+00:00", "framework": "vllm", "intentId": "d7d3ce2a20b44b77b9b58a6f68187376", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382234+00:00", "framework": "vllm", "intentId": "61f6b8695f8343c3b5da8749eeb1989a", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382290+00:00", "framework": "vllm", "intentId": "ebc15a1639ca4e8ea54f202385b5a00f", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382345+00:00", "framework": "vllm", "intentId": "aa8696fc415945fb884ef63119a8e91e", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382399+00:00", "framework": "vllm", "intentId": "5322dccb9a98410380bf22aaa21ed0ae", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382454+00:00", "framework": "vllm", "intentId": "318cf8c1a1dc42968cfdc7b3d9cc9856", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382509+00:00", "framework": "vllm", "intentId": "70beb78ccc234410a9bc83012bbd9a3e", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382564+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a5991293b70e41eaac58e095528987c2", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382619+00:00", "framework": "vllm_fix_tokenizer", "intentId": "30ee789b7d8c43619b2c298b025ff926", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382695+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c4f0265021174875a2fbfab7eca31549", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382765+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6e2ca5aa20bb4edb85e87e0e4e99f1a5", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382836+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9dc33a714ef945beae273beeef858d1e", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382908+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2598caf0bfaf4a549b7ddea6838ec94f", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382952+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f3e4736fa2594fd69dcf40c90cbd662f", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382995+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c585bd8de2894a86b3326e34b8469255", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383039+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed4637bc15f641bd884c0c8d4bcda788", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383082+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d51d1c606be4353a6f462333a4da327", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383126+00:00", "framework": "transformers", "intentId": "2873c836e0d640639090b821fea58431", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383190+00:00", "framework": "transformers", "intentId": "0d6fa8bc878445738adf3015eabc5bec", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383254+00:00", "framework": "transformers", "intentId": "d9d6776b62c64e89a47f5bd312b7ca4b", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383316+00:00", "framework": "transformers", "intentId": "fb752e52d30e4c3ca397783630512aa7", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383378+00:00", "framework": "transformers", "intentId": "57391c3069e641ccb8184b983000dcbc", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383440+00:00", "framework": "transformers", "intentId": "6ba4a72ff5f7402aafb2b617a8f4ccb7", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383502+00:00", "framework": "transformers", "intentId": "42d07b7d21024026af52c892f6a7f5d8", "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": "944d8a9deaa044318bf23afca4cc654b", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383564+00:00", "framework": "transformers", "intentId": "b9b3ed70986c446e8bdd03c7af20d6b4", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162986+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380761+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1590e651723b4713af1135dffa895a06", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "reason": null, "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4974052", "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163028+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381367+00:00", "framework": "vllm_tokenizer_patch", "intentId": "53e599679f28480db70a4a59302ee373", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4974067", "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163080+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382234+00:00", "framework": "vllm", "intentId": "61f6b8695f8343c3b5da8749eeb1989a", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974086", "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163148+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383564+00:00", "framework": "transformers", "intentId": "b9b3ed70986c446e8bdd03c7af20d6b4", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163144+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383502+00:00", "framework": "transformers", "intentId": "42d07b7d21024026af52c892f6a7f5d8", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163142+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383440+00:00", "framework": "transformers", "intentId": "6ba4a72ff5f7402aafb2b617a8f4ccb7", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163139+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383378+00:00", "framework": "transformers", "intentId": "57391c3069e641ccb8184b983000dcbc", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163136+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383316+00:00", "framework": "transformers", "intentId": "fb752e52d30e4c3ca397783630512aa7", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163133+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383254+00:00", "framework": "transformers", "intentId": "d9d6776b62c64e89a47f5bd312b7ca4b", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163130+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383190+00:00", "framework": "transformers", "intentId": "0d6fa8bc878445738adf3015eabc5bec", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163127+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383126+00:00", "framework": "transformers", "intentId": "2873c836e0d640639090b821fea58431", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163125+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383082+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d51d1c606be4353a6f462333a4da327", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163122+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.383039+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed4637bc15f641bd884c0c8d4bcda788", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163119+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382995+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c585bd8de2894a86b3326e34b8469255", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163116+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382952+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f3e4736fa2594fd69dcf40c90cbd662f", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163114+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382908+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2598caf0bfaf4a549b7ddea6838ec94f", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163111+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382836+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9dc33a714ef945beae273beeef858d1e", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163108+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382765+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6e2ca5aa20bb4edb85e87e0e4e99f1a5", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163105+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382695+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c4f0265021174875a2fbfab7eca31549", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163102+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382619+00:00", "framework": "vllm_fix_tokenizer", "intentId": "30ee789b7d8c43619b2c298b025ff926", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163099+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382564+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a5991293b70e41eaac58e095528987c2", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163095+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382509+00:00", "framework": "vllm", "intentId": "70beb78ccc234410a9bc83012bbd9a3e", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163092+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382454+00:00", "framework": "vllm", "intentId": "318cf8c1a1dc42968cfdc7b3d9cc9856", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163089+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382399+00:00", "framework": "vllm", "intentId": "5322dccb9a98410380bf22aaa21ed0ae", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163086+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382345+00:00", "framework": "vllm", "intentId": "aa8696fc415945fb884ef63119a8e91e", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163083+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382290+00:00", "framework": "vllm", "intentId": "ebc15a1639ca4e8ea54f202385b5a00f", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163077+00:00", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382182+00:00", "framework": "vllm", "intentId": "d7d3ce2a20b44b77b9b58a6f68187376", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163074+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382129+00:00", "framework": "vllm", "intentId": "81d2242c736b41dfb706fb0f09e65c8d", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163071+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382077+00:00", "framework": "vllm", "intentId": "504b59f10ccf4adaad038addd474fc6c", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163069+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.382023+00:00", "framework": "vllm", "intentId": "19188e9bd4b44dddb39261b5737a977e", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163065+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381969+00:00", "framework": "vllm", "intentId": "a3e7d35f75c747abb4c21c2e1f101d9b", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163062+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381911+00:00", "framework": "vllm", "intentId": "472a1bacae7a45b390dfbd0f684180e3", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163059+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381844+00:00", "framework": "vllm-mlu", "intentId": "2da57c44a1154b9e8ad923414bfecdb2", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163056+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381806+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4a2303a4d30b41ad9dae459bba1952fa", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163052+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8ffb7310924a424f80e32a3094eb8fdd", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163049+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381729+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7156d359ca19440ebad91204bb61bb9e", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163046+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381688+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7db1f81d2c6b439599f8c6dcec17ddf9", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163043+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381626+00:00", "framework": "vllm_tokenizer_patch", "intentId": "518f43878f3f4c0aa6cf250f6dfac0c7", "repoId": "RedHatAI/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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163040+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381576+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ab3de7381521485fad9ebe303ffcac38", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163037+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381514+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0c0bf5b2867646c9898c0ce81b88d110", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163034+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381465+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8dcbcbaa6cc84a7a914b681eaa3881dc", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163031+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381416+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3b9cb98a3fd44131aa757fb35c4eeb95", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163024+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381318+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e3a4bbfe594d4ed0a1dcf311c8c9c6fa", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163022+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381269+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a71068b876ea401db5c4a06265957bf2", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163018+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381220+00:00", "framework": "vllm_tokenizer_patch", "intentId": "caffa2e4e9024809bd14d2bb94336769", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163016+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381171+00:00", "framework": "vllm_tokenizer_patch", "intentId": "912930ecd6394c749940c41b7a71f7c0", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163013+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381122+00:00", "framework": "vllm_tokenizer_patch", "intentId": "047852a0e83c43fcafb5b2c4bcfd6c07", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163009+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381072+00:00", "framework": "vllm_tokenizer_patch", "intentId": "af83eaa538684d3296469d1b39ac8b39", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163006+00:00", "configFingerprint": "ecd31d4ed4e0e92b9deabe3de0f18c75dc252004ba68826e4cfd561549549074", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.381021+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fa0bbe708e944508bc9d72be173396c0", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163003+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380978+00:00", "framework": "vllm_fix_tokenizer", "intentId": "66c769bb63f94cddb2b4149cd71c2fab", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.163000+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380935+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d18d874ce31d41109c6cf331d903473d", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162996+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380892+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2728429a6de45988ce6d79cdb426933", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162993+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380848+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e4ed693549244b54bd270e7154e1183d", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162990+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380805+00:00", "framework": "vllm_fix_tokenizer", "intentId": "407f9cd63b344450acccd9ef33722ac8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162983+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380715+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4ad56ef13cce45d988e431789f139fe6", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162979+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380634+00:00", "framework": "vllm_tokenizer_patch", "intentId": "889823153b1f44dcbfcd38ffa69c91bd", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162976+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380550+00:00", "framework": "vllm_tokenizer_patch", "intentId": "20f4159abc9442e7aaf947a51f998093", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162971+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380461+00:00", "framework": "vllm_tokenizer_patch", "intentId": "720132407b5244cc9c46f0b8e1706c10", "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": "944d8a9deaa044318bf23afca4cc654b", "completedAt": "2026-09-20T08:42:28.162947+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:35:16.380303+00:00", "framework": "vllm_tokenizer_patch", "intentId": "62c16e6e832f429092fac58cd3a66901", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "334884ad19f0430f80f30cd81bf275b5", "completedAt": "2026-09-20T08:23:13.372198+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:20:24.505561+00:00", "framework": "vllm", "intentId": "0e25903d62894310b2d71a63ce289c21", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "334884ad19f0430f80f30cd81bf275b5", "completedAt": "2026-09-20T08:23:13.372195+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:20:24.505516+00:00", "framework": "vllm", "intentId": "76a837003b2a48dfa14b88c6d87438de", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "334884ad19f0430f80f30cd81bf275b5", "completedAt": "2026-09-20T08:23:13.372192+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T08:20:24.505472+00:00", "framework": "vllm", "intentId": "dcb5c4e2018c41ffa41e6840361a5c29", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} @@ -1873,59 +1873,3 @@ {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851680+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.041001+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7320383e619f4900b91abcd0cb0c8162", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8059016df904d1cbb34b18372c8644d", "completedAt": "2026-09-20T07:25:58.851663+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T07:19:40.040945+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ce244ee0c764ef689587bc3f68ef896", "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": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432012+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.642022+00:00", "framework": "vllm", "intentId": "530a73b5bd6f4c5f98e1f04a2eed1768", "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": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432007+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641955+00:00", "framework": "vllm", "intentId": "e4c5b4949e2b41ce9854775a54fbd5f9", "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": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.432003+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641888+00:00", "framework": "vllm", "intentId": "492ba554c7054dffaaa97069a5ea24f7", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431999+00:00", "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641820+00:00", "framework": "vllm", "intentId": "4610622389594fea83a8372e5e4013b3", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431995+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641779+00:00", "framework": "vllm_tokenizer_patch", "intentId": "17246b28c43b42639cd4599603669d0c", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431991+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641731+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e260b63b28fd41e58cc03d887c35cb47", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431987+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641690+00:00", "framework": "vllm_tokenizer_patch", "intentId": "83c83c0780414cf78503b9d8b21e20dd", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431983+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641635+00:00", "framework": "vllm_tokenizer_patch", "intentId": "af280b59f7d2413d84523d344667de5c", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431979+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641586+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d294c1514dfd423689bf8fe13e186ffb", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431975+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641531+00:00", "framework": "vllm", "intentId": "bd5ec9c2125c45d9ba12bfeff203ff65", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431971+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641478+00:00", "framework": "vllm", "intentId": "84571ed8e0464a19ba371b4a58761ff3", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431967+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641426+00:00", "framework": "vllm", "intentId": "7c8973a3916e48b9864508dff31712d7", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431962+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641383+00:00", "framework": "vllm-patch-tokenizer", "intentId": "dd972d93f5df4497989302e6d69ef79e", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431959+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641339+00:00", "framework": "vllm-patch-tokenizer", "intentId": "df468a08cccb48b3b5206b7ab461f654", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431955+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641295+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f2e900e77e774d7690dd7ff164920a86", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431950+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641232+00:00", "framework": "transformers", "intentId": "d34472e1bb4b47e2ad75e1f6e7983817", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431946+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641169+00:00", "framework": "transformers", "intentId": "2d282ddecc2f4b7383862f82f4f127e4", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431942+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641106+00:00", "framework": "transformers", "intentId": "810956b0795e4d9ca887b7793e273180", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431938+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.641037+00:00", "framework": "transformers", "intentId": "d0f4e9c92389452b9d09dbb841002f89", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431934+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.640974+00:00", "framework": "transformers", "intentId": "be1e8c2ccaa1416b8273d5b707fe7a55", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431930+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.640912+00:00", "framework": "transformers", "intentId": "f8e572164c984409bead48ae9d3a1bda", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431926+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.640850+00:00", "framework": "transformers", "intentId": "f1283124205e4a7f803764c4eeb07651", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431922+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.640786+00:00", "framework": "transformers", "intentId": "6098ef308f12420b83d3a35bc48ffdec", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431917+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.640713+00:00", "framework": "transformers", "intentId": "570e6e596dd848aba479a4ef4da55d7f", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431911+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.640637+00:00", "framework": "transformers", "intentId": "7a921ea4705b4a6d9ff6d5d86ba2f7eb", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "34b3f3240268438fa30503f921cc7cc8", "completedAt": "2026-09-20T06:59:26.431891+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:56:16.640507+00:00", "framework": "transformers", "intentId": "6d778e23837d463ea3b5f39e01b0e0d8", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602286+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.625433+00:00", "framework": "transformers", "intentId": "c5074e3c4c87498b85fa509755842329", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602284+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.625365+00:00", "framework": "transformers", "intentId": "f9adf1722e9441b6a1b312a9e8aae5b1", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602281+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.625304+00:00", "framework": "transformers", "intentId": "89fca5e3393b43e0bd1f6a385b71df9f", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602279+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.625242+00:00", "framework": "transformers", "intentId": "32887fa2a9144e7da82421532d01916f", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602277+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.625180+00:00", "framework": "transformers", "intentId": "ecef71b7a2df4120aac7346cf14c0f8f", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602275+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.625119+00:00", "framework": "transformers", "intentId": "f35330f832f94e1dbdf9664b81214824", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602272+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.625057+00:00", "framework": "transformers", "intentId": "210c4dda8cde43b287900f1e02846867", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602269+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624990+00:00", "framework": "transformers", "intentId": "24f3b821d2df4477882d9f084605d84e", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602266+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624929+00:00", "framework": "transformers", "intentId": "7b813e60dd1e41e6979314c413118241", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602263+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624867+00:00", "framework": "transformers", "intentId": "fa76d2369f43449ba2fc27bdc16f9112", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602261+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624804+00:00", "framework": "transformers", "intentId": "2a658646e4cd4c70974728e27ea2ed24", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602259+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624741+00:00", "framework": "transformers", "intentId": "e699d9c95b5f4754a9725cd105924ba6", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602256+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624698+00:00", "framework": "vllm_fix_tokenizer", "intentId": "83e6a1bd13754b9480ef25f4fc659578", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602254+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624643+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ae273dbd07df4fb084781cbf8931dc8f", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602251+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624600+00:00", "framework": "vllm_fix_tokenizer", "intentId": "118e3dd64920497fa1c4e8de6eb37940", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602248+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624553+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3aef0f50fbe6443f9929ddace99da9bd", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602246+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624510+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1052896b4da946f1b4842705ed78adcf", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602243+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624467+00:00", "framework": "vllm_fix_tokenizer", "intentId": "302db5c295a04cb9b1e03097f5f95b18", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602240+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624425+00:00", "framework": "vllm_fix_tokenizer", "intentId": "83df2fbeaa1b4459b20a3b95d9ca3c3d", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602238+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624382+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e046ff39421b4d0498b9edf66f7dbd4c", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602235+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624339+00:00", "framework": "vllm_fix_tokenizer", "intentId": "677529c80bb64cfb81c4bff0504daa1d", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602232+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624295+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f6593437e3d141678828112ab8fbc646", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602230+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624234+00:00", "framework": "vllm", "intentId": "e4f1b3f3f4344c298cefd883d5e1de3e", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602228+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624180+00:00", "framework": "vllm", "intentId": "9ba2a23874384a56be4638ebb9dc086e", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602226+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624125+00:00", "framework": "vllm", "intentId": "aeb77f86e5654c11b1a824e46dc291fa", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602223+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624071+00:00", "framework": "vllm", "intentId": "0f1eee6c7b694312b80918ac0a8c00b7", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602221+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.624016+00:00", "framework": "vllm", "intentId": "53e62a1cafef4357bb4889547eb3d922", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602218+00:00", "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.623965+00:00", "framework": "vllm", "intentId": "a443005efc5b4776b41a55f9bcb2551f", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602216+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.623912+00:00", "framework": "vllm", "intentId": "6606f2635a0b46218211f6894500823d", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602213+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.623860+00:00", "framework": "vllm", "intentId": "c29335b63bc94a0ca9b52074c303dd9c", "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": "dc59e7dc9be04fb3a031c8ddf73ced17", "completedAt": "2026-09-20T06:56:15.602210+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T06:49:08.623806+00:00", "framework": "vllm", "intentId": "9a963540ddfa42199613df1702b54387", "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index d5ac08d2fc..f65cbffe5a 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1710 + "unified_success_first": 1713 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -14,7 +14,7 @@ "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": 80, - "text-generation|Cambricon_mlu-370-x8|vllm": 48, + "text-generation|Cambricon_mlu-370-x8|vllm": 49, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 26, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 89, "text-generation|Iluvatar_bi-150|llamacpp": 16, @@ -24,8 +24,8 @@ "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 32, "text-generation|Iluvatar_mrv-100|vllm": 61, "text-generation|Kunlunxin_p-800|vllm": 3, - "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 166, - "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 57, + "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 167, + "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 58, "text-generation|MetaX_c-500|vllm": 104, "text-generation|Mthreads_s4000|llamacpp": 17, "text-generation|Mthreads_s4000|vllm": 98, @@ -36,8 +36,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 107 }, - "acceptedSinceRefresh": 1710, - "acceptedTotal": 1710, - "generatedAt": "2026-09-20T08:23:13.311877+00:00", + "acceptedSinceRefresh": 1713, + "acceptedTotal": 1713, + "generatedAt": "2026-09-20T08:42:28.096409+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 79d1d6c9b7..32bcf9ebe2 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1052,3 +1052,6 @@ {"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_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "modelId": "inclusionAI/Ling-3.0-tiny", "submitTime": "2026-09-20T06:19:35.394755+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4972231", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "modelId": "LiquidAI/LFM2.5-8B-A1B", "submitTime": "2026-09-20T07:24:14.091402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4973030", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "submitTime": "2026-09-20T08:35:23.865977+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974052", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T08:36:06.135810+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974067", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-20T08:38:08.235641+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974086", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 1154866c9a..8aa827928b 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "a43deb60b6f751b76576986b5c89b51a2b8d469239d82ff9136f564b25b03b2c", ".modelhub_state/recent_outcomes.jsonl": "e4ec7fe7a933ada1495dda90138340a94157c38bdea2cbc2d2155d9b305ba72e", ".modelhub_state/recovery_active_tasks.jsonl": "ba993a4b636dd0a72eb29c2d4550942d1c146592c0c2807207d03b2880355bbb", - ".modelhub_state/recovery_intents.jsonl": "2257e0528eb06a55af7cf7fca78fe0b482be523543e83d6fd079b4c94b185bd6", - ".modelhub_state/routing_intelligence.json": "010a51428f05fdbd5668d304922f379c5690533e678aece411bee97754fb4c9a", + ".modelhub_state/recovery_intents.jsonl": "98113d16a18177f34fb07c27a2795ed73d8879f6ab24aa1187f2498eaaeac2a6", + ".modelhub_state/routing_intelligence.json": "e69dd1419d63e7eacb5c738cf882e312f2919111177d69194253e54ba7522515", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "0d42c01ce8e175a145f6185042c3344c7a25ef4025964e2ebcbc5c929309efc3", - "outcomes/submissions.jsonl": "1b746b58ecb3484781aa0fc1343d4f92801f7680a08479fca6a964eb74ebe328" + "ledger/submissions.jsonl": "13eab04b5b641f3793f79f65be21c51cd700061c19d2ddd584d2f7181393ab3c", + "outcomes/submissions.jsonl": "650d28883ad4ee4ce1ed93ec1e914af858e8aa5a08b088afba74a2939552c6a2" }, - "generation": 10398, - "phase": "intent", + "generation": 10399, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T08:35:16.563438+00:00", + "updatedAt": "2026-09-20T08:42:28.347663+00:00", "writerId": "fc715c06e24c4db2ae3e425e435db996" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 8460b552d2..a6ac9f2739 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1083,3 +1083,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T07:35:10.256551+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4973190", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663548868}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T08:13:33.948576+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4973783", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730845002, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730845002}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T08:13:33.946939+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4973784", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251901, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251901}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T08:35:23.865977+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974052", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T08:36:06.135810+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974067", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T08:38:08.235641+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974086", "taskType": "text-generation", "verifyResult": null}