Update README.md

README.md

@@ -21,8 +21,23 @@ base_model_relation: quantized
   ```
   CONTEXT_LENGTH=32768
 
-  vllm serve     QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix     --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix     --enable-expert-parallel     --swap-space 16     --max-num-seqs 512     --max-model-len $CONTEXT_LENGTH     --max-seq-len-to-capture $CONTEXT_LENGTH     --gpu-memory-utilization 0.9     --tensor-parallel-size 8     --trust-remote-code     --disable-log-requests     --host 0.0.0.0     --port 8000
-  ```
+CONTEXT_LENGTH=32768
+
+VLLM_USE_MODELSCOPE=true vllm serve \
+    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
+    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
+    --enable-expert-parallel \
+    --swap-space 16 \
+    --max-num-seqs 512 \
+    --max-model-len $CONTEXT_LENGTH \
+    --max-seq-len-to-capture $CONTEXT_LENGTH \
+    --gpu-memory-utilization 0.9 \
+    --tensor-parallel-size 8 \
+    --trust-remote-code \
+    --disable-log-requests \
+    --host 0.0.0.0 \
+    --port 8000
+```
 
   ### 【Dependencies】
   ```