From 6506086360e726f6f62c1b024c139152895180c8 Mon Sep 17 00:00:00 2001
From: paopaotang <1834563329@qq.com>
Date: Tue, 20 Oct 2026 13:49:57 +0800
Subject: [PATCH] add main.py

---
 main.py | 32 ++------------------------------
 1 file changed, 2 insertions(+), 30 deletions(-)

diff --git a/main.py b/main.py
index ce171d6..68fa9a8 100644
--- a/main.py
+++ b/main.py
@@ -21,39 +21,11 @@ TASK_TYPE = "text-generation"
 
 TASKS = [
     {
-        "label": "OSP-1.4B-100B-Muon-Only",
-        "model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Muon-Only",
-        "gpu": "MetaX_c-500",
-        "framework": "vllm_tokenizer_patch",
-        "config": "nv_framework: vllm_fix_tokenizer\nframework: vllm_tokenizer_patch\nstorage: gpfs\nmax_tokens: 1024\nmax_model_len: 2048\napi: completion\nsut_config:\n    gpu_num: 1\n    values:\n        command: ['/opt/conda/bin/vllm', 'serve', '/model', '--port', '8000', '--served-model-name', 'llm',  '--max-model-len', '2048', '--gpu-memory-utilization', '0.9',  '--enforce-eager', '--trust-remote-code' ,'-tp', '1' ]\nref_config:\n    gpu_num: 1\n    values:\n        command: ['/opt/entrypoint.sh', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '2048', '--enforce-eager', '--trust-remote-code', '-tp', '1']"
-    },
-    {
-        "label": "OSP-1.4B-100B-Muon-SSNorm",
-        "model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Muon-SSNorm",
+        "label": "OSP-1.4B-100B-Shampoo-SSNorm-EmbProj",
+        "model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm-EmbProj",
         "gpu": "Kunlunxin_p-800",
         "framework": "vllm_fix_tokenizer",
         "config": "framework: vllm_fix_tokenizer\nlang: en\nmax_model_len: 2048\nsut_config:\n  gpu_num: 1\n  values:\n    command:\n    - /opt/entrypoint.sh    - /model\n    - --port\n    - '80'\n    - --served-model-name\n    - llm\n    - --max-model-len\n    - '2048'\n    - --enforce-eager\n    - --trust-remote-code\n    - -tp\n    - '1'\nref_config:\n  gpu_num: 1\n  values:\n    command:\n    - /opt/entrypoint.sh    - /model\n    - --port\n    - '80'\n    - --served-model-name\n    - llm\n    - --max-model-len\n    - '2048'\n    - --enforce-eager\n    - --trust-remote-code\n    - -tp\n    - '1'"
-    },
-    {
-        "label": "OSP-1.4B-100B-Shampoo-SSNorm",
-        "model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm",
-        "gpu": "Cambricon_mlu-370-x8",
-        "framework": "vllm-mlu",
-        "config": "framework: vllm-mlu\nnv_framework: vllm_fix_tokenizer\napi: completion\nlang: en\ntemperature: 0.4\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n  gpu_num: 1\n  values:\n    env:\n    - name: MAX_MODEL_LEN\n      value: 2048\n    - name: VLLM_ALLOW_LONG_MAX_MODEL_LEN\n      value: '1'\n    command:\n    - vllm\n    - serve\n    - /model\n    - --port\n    - '8000'\n    - --served-model-name\n    - llm\n    - --max-model-len\n    - '2048'\n    - --trust-remote-code\n    - --dtype\n    - float16\nref_config:\n  cpu_num: 2\n  gpu_num: 1\n  values:\n    env:\n    - name: MAX_MODEL_LEN\n      value: 2048\n    - name: VLLM_ALLOW_LONG_MAX_MODEL_LEN\n      value: '1'\n    command:\n    - /opt/entrypoint.sh\n    - /model\n    - --port\n    - '80'\n    - --served-model-name\n    - llm\n    - --max-model-len\n    - '2048'\n    - --trust-remote-code\n    - --dtype\n    - float16\n"
-    },
-    {
-        "label": "OSP-1.4B-100B-Muon-EmbProj",
-        "model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Muon-EmbProj",
-        "gpu": "Biren_166m",
-        "framework": "vllm_fix_tokenizer",
-        "config": "framework: vllm_fix_tokenizer\nlang: en\nmax_model_len: 2048\nsut_config:\n  gpu_num: 1\n  values:\n    command:\n    - /opt/entrypoint.sh    - /model\n    - --port\n    - '80'\n    - --served-model-name\n    - llm\n    - --max-model-len\n    - '2048'\n    - --enforce-eager\n    - --trust-remote-code\n    - -tp\n    - '1'\nref_config:\n  gpu_num: 1\n  values:\n    command:\n    - /opt/entrypoint.sh    - /model\n    - --port\n    - '80'\n    - --served-model-name\n    - llm\n    - --max-model-len\n    - '2048'\n    - --enforce-eager\n    - --trust-remote-code\n    - -tp\n    - '1'"
-    },
-    {
-        "label": "OSP-1.4B-1T-Muon-SSNorm-EmbProj",
-        "model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-1T-Muon-SSNorm-EmbProj",
-        "gpu": "Sunrise_pt-200-x1",
-        "framework": "vllm_fix_tokenizer",
-        "config": "framework: vllm_fix_tokenizer\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: zh\nmax_model_len: 2048\nsut_config:\n  gpu_num: 1\n  values:\n    command:\n    - /opt/entrypoint.sh\n    - /model\n    - --port\n    - '8000'\n    - --served-model-name\n    - llm\n    - --max-model-len\n    - '2048'\n    - --gpu-memory-utilization\n    - '0.9'\n    - --enforce-eager\n    - --trust-remote-code\nref_config:\n  gpu_num: 1\n  values:\n    command:\n    - /opt/entrypoint.sh\n    - /model\n    - --port\n    - '8000'\n    - --served-model-name\n    - llm\n    - --max-model-len\n    - '2048'\n    - --dtype\n    - float16\n    - --gpu-memory-utilization\n    - '0.95'\n    - -tp\n    - '1'\n    - --enforce-eager\n    - --trust-remote-code\n"
     }
 ]