updata

README.md

@@ -117,8 +117,7 @@ ray start --address='x.x.x.x:6379' --num-gpus=8 --num-cpus=32
 vllm serve /path/to/Baichuan-M3-235B 
     --host x.x.x.x --port 8000  
     --distributed-executor-backend ray 
-    --tensor-parallel-size 8   
-    --pipeline-parallel-size 2  
+    --tensor-parallel-size 16 
     --gpu-memory-utilization 0.9 
     --served-model-name baichuan-m3 
     --reasoning-parser deepseek_r1
@@ -149,12 +148,13 @@ curl http://localhost:8000/v1/chat/completions   \
 ### transformers
 #### 单机推理
 ```bash
+python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-model_path = "/path/to/Baichuan-M3-235B"
 import os
 import torch
 os.environ['TRANSFORMERS_OFFLINE'] = '1'
 os.environ['MODELSCOPE_OFFLINE'] = '1'
+model_path = "/path/to/Baichuan-M3-235B"
 model = AutoModelForCausalLM.from_pretrained(
   model_path, 
   trust_remote_code=True,