Refactor Dockerfile: unify CUDA logic and reduce image size by ~2.6 GB (#3749)

Signed-off-by: Kebe <mail@kebe7jun.com>

docker/Dockerfile

@@ -30,44 +30,19 @@ ARG CUDA_VERSION
 RUN python3 -m pip install --upgrade pip setuptools wheel html5lib six \
     && git clone --depth=1 https://github.com/sgl-project/sglang.git \
     && if [ "$CUDA_VERSION" = "12.1.1" ]; then \
-         python3 -m pip install torch --index-url https://download.pytorch.org/whl/cu121; \
+         export CUINDEX=121; \
        elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
-         python3 -m pip install torch --index-url https://download.pytorch.org/whl/cu124; \
+         export CUINDEX=124; \
        elif [ "$CUDA_VERSION" = "12.5.1" ]; then \
-         python3 -m pip install torch --index-url https://download.pytorch.org/whl/cu124; \
+         export CUINDEX=124; \
        elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
-         python3 -m pip install torch --index-url https://download.pytorch.org/whl/cu118; \
-         python3 -m pip install sgl-kernel -i https://docs.sglang.ai/whl/cu118; \
+         export CUINDEX=118; \
+         python3 -m pip install --no-cache-dir sgl-kernel -i https://docs.sglang.ai/whl/cu118; \
        else \
          echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
        fi \
+    && python3 -m pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cu${CUINDEX} \
     && cd sglang \
-    && if [ "$BUILD_TYPE" = "srt" ]; then \
-         if [ "$CUDA_VERSION" = "12.1.1" ]; then \
-           python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu121/torch2.5/flashinfer-python; \
-         elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
-           python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python; \
-         elif [ "$CUDA_VERSION" = "12.5.1" ]; then \
-           python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python; \
-         elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
-           python3 -m pip --no-cache-dir install -e "python[srt]" --find-links https://flashinfer.ai/whl/cu118/torch2.5/flashinfer-python; \
-           python3 -m pip install sgl-kernel -i https://docs.sglang.ai/whl/cu118; \
-         else \
-           echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
-         fi; \
-       else \
-         if [ "$CUDA_VERSION" = "12.1.1" ]; then \
-           python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu121/torch2.5/flashinfer-python; \
-         elif [ "$CUDA_VERSION" = "12.4.1" ]; then \
-           python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python; \
-         elif [ "$CUDA_VERSION" = "12.5.1" ]; then \
-           python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python; \
-         elif [ "$CUDA_VERSION" = "11.8.0" ]; then \
-           python3 -m pip --no-cache-dir install -e "python[all]" --find-links https://flashinfer.ai/whl/cu118/torch2.5/flashinfer-python; \
-           python3 -m pip install sgl-kernel -i https://docs.sglang.ai/whl/cu118; \
-         else \
-           echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1; \
-         fi; \
-       fi
+    && python3 -m pip --no-cache-dir install -e "python[${BUILD_TYPE}]" --find-links https://flashinfer.ai/whl/cu${CUINDEX}/torch2.5/flashinfer-python
 
 ENV DEBIAN_FRONTEND=interactive