[Infra] Dockerfile.non_root: add BuildKit uv cache mount

Mount /app/.cache/uv as a BuildKit type=cache on both 'uv sync' steps.
The cache persists across builds on the same builder (and, when used
with type=gha in CI, across CI runs) so repeat builds don't re-download
every wheel.

Side-effect: because the cache lives outside the image layer, the
~742MB of downloaded wheel archives that were previously baked into
/app/.cache/uv drop out of the final image. Compressed image size
goes from ~5.0GB to ~3.7GB, and the 'USER nobody' prisma-generate
layer is 1.7GB vs 2.4GB.

Warm-build timing: a uv-sync-invalidating edit now takes ~1m30s vs
~2m39s without the cache mount, on this dev VM.

API parity and UI visual regression continue to match baseline.
Trivy HIGH/CRITICAL: 6 at baseline -> 2 now, no new CVEs.

Co-authored-by: yuneng-jiang <yuneng-berri@users.noreply.github.com>

docker/Dockerfile.non_root

@@ -41,7 +41,8 @@ COPY enterprise/pyproject.toml enterprise/
 COPY litellm-proxy-extras/pyproject.toml litellm-proxy-extras/
 
 # Install third-party dependencies (cached unless pyproject.toml/uv.lock change)
-RUN uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
+RUN --mount=type=cache,target=/app/.cache/uv,id=litellm-uv-cache \
+    uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
     --extra proxy \
     --extra proxy-runtime \
     --extra extra_proxy \
@@ -71,7 +72,8 @@ RUN mkdir -p /var/lib/litellm/ui /var/lib/litellm/assets && \
       done && \
       touch .litellm_ui_ready )
 
-RUN if [ "$PROXY_EXTRAS_SOURCE" = "published" ]; then \
+RUN --mount=type=cache,target=/app/.cache/uv,id=litellm-uv-cache \
+    if [ "$PROXY_EXTRAS_SOURCE" = "published" ]; then \
       uv sync --frozen --no-default-groups --no-editable \
         --extra proxy \
         --extra proxy-runtime \