Modify some mistakes in README.md

README.md

@@ -17,10 +17,9 @@ Qwen3-Omni 是一款原生的端到端全模态基座模型，具备对文本、
 | :------: |:-----------------------------------------:|
 | DTK |               26.04                |
 | python |          3.10.12               |
-| transformers |                5.2.0.dev0                 |
-| vllm |       0.15.1+das.opt1.alpha.dtk2604       |
-| triton | 3.3.0+das.opt2.dtk2604 |
-| torch | 2.9.0+das.opt1.dtk2604 |
+| transformers |       4.57.6           |
+| vllm |  0.15.1+das.opt1.alpha.dtk2604.20260220.g2799735a   |
+| torch | 2.9.0+das.opt1.dtk2604.20260206.g275d08c2 |
 
 推荐使用镜像: harbor.sourcefind.cn:5443/dcu/admin/base/custom:vllm0.15.1-ubuntu22.04-dtk26.04-0130-py3.10-20260220
 
@@ -48,6 +47,7 @@ docker run -it \
 ```
 pip uninstall vllm numpy
 pip install vllm-0.15.1+das.opt1.alpha.dtk2604-cp310-cp310-linux_x86_64.whl
+pip install pycountry
 pip install numpy==1.26.1
 ```
 
@@ -66,7 +66,7 @@ pip install numpy==1.26.1
 
 vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct \
     --trust-remote-code \
-    --tensor-parallel-size 4 \
+    --tensor-parallel-size 2 \
     --dtype bfloat16 
 
 ## client访问