fix(Dockerfile): use cmd single line

Dockerfile

@@ -16,23 +16,20 @@ FROM docker.io/vllm/vllm-openai:v0.10.0
 
 EXPOSE 7860
 
-ENTRYPOINT ["vllm", "serve"]
-
-CMD [
-  "--model", "meta-llama/Llama-3.2-3B-Instruct",
-  "--task", "generate",
-  "--revision", "0cb88a4f764b7a12671c53f0838cd831a0843b95",
-  "--code-revision", "0cb88a4f764b7a12671c53f0838cd831a0843b95",
-  "--tokenizer-revision", "0cb88a4f764b7a12671c53f0838cd831a0843b95",
-  "--seed", "42",
-  "--host", "0.0.0.0",
-  "--port", "7860",
-  "--max-num-batched-tokens", "32768",
-  "--max-model-len", "32768",
-  "--dtype", "float16",
-  "--enforce-eager",
-  "--gpu-memory-utilization", "0.9",
-  "--enable-prefix-caching",
-  "--disable-log-requests",
-  "--trust-remote-code"
-]
+CMD vllm serve \
+  --model "meta-llama/Llama-3.2-3B-Instruct" \
+  --task generate \
+  --revision "0cb88a4f764b7a12671c53f0838cd831a0843b95" \
+  --code-revision "0cb88a4f764b7a12671c53f0838cd831a0843b95" \
+  --tokenizer-revision "0cb88a4f764b7a12671c53f0838cd831a0843b95" \
+  --seed 42 \
+  --host 0.0.0.0 \
+  --port 7860 \
+  --max-num-batched-tokens 32768 \
+  --max-model-len 32768 \
+  --dtype float16 \
+  --enforce-eager \
+  --gpu-memory-utilization 0.9 \
+  --enable-prefix-caching \
+  --disable-log-requests \
+  --trust-remote-code