Create Dockerfile

Dockerfile

@@ -0,0 +1,19 @@
+FROM vllm/vllm-openai:latest
+
+ENV PORT=7860
+EXPOSE 7860
+
+ENV MODEL_NAME="Qwen/Qwen3.8-Flash-Next-FP8"
+
+ENTRYPOINT vllm serve ${MODEL_NAME} \
+    --host 0.0.0.0 \
+    --port 7860 \
+    --tensor-parallel-size 8 \
+    --gpu-memory-utilization 0.95 \
+    --max-model-len 262144 \
+    --enable-chunked-prefill \
+    --max-num-batched-tokens 32768 \
+    --swap-space 64 \
+    --speculative-config '{"method":"mtp","num_speculative_tokens":2}' \
+    --trust-remote-code \
+    --api-key ${API_KEY}