docker/unified: add uv via pip install (#681)

Install uv after the cpp tool binaries are copied and before the
llama-swap binary, enabling `uv run` usage for Python-based inference
backends like vLLM.

- add python3-pip to runtime apt installs
- add `pip install uv --break-system-packages` after cpp installs

fixes #628

Co-authored-by: Claude <noreply@anthropic.com>

docker/unified/Dockerfile

@@ -149,7 +149,7 @@ ARG IK_LLAMA_COMMIT_HASH=unknown
 ARG RUN_UID=0
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    python3-numpy python3-sentencepiece \
+    python3-numpy python3-sentencepiece python3-pip \
     && rm -rf /var/lib/apt/lists/*
 
 # Create non-root user when RUN_UID != 0
@@ -180,6 +180,9 @@ COPY --from=llama-build /install/bin/llama-cli /usr/local/bin/
 # Copy ik-llama-server (CUDA only; empty copy for vulkan)
 COPY --from=ik-llama-build /install/bin/ /usr/local/bin/
 
+# Install uv
+RUN pip install uv --break-system-packages
+
 # Copy llama-swap binary
 COPY --from=llama-swap-download /install/bin/llama-swap /usr/local/bin/
 COPY --from=llama-swap-download /install/llama-swap-version /tmp/