build: smarter docker parallelism (#14653)

Our Dockerfile leverages parallel stages for more efficient builds.  However,
our old parallel settings were naive and lead to under/over utilization
depending on the capabilities of your build system.

This change switches to using Ninja for all our docker cmake builds to leverage
its smarter parallel logic.  We tell Ninja to target a load of nproc so each of
the build stages will share the load on the system aiming for full CPU use
without oversaturation.

The GPU parallelism settings are also adjusted to 4 to avoid a long-tail for
the last few GPU targets as they work through the long list of GPU
architectures.

This also fixes the Dockerfile to move Vulkan install to just the stage that
needs it instead of blocking most other GPU installs.  This should speed up CI
which always has a clean build cache.

scripts/env.sh

@@ -16,7 +16,6 @@ OLLAMA_COMMON_BUILD_ARGS="--build-arg=VERSION \
     --build-arg=OLLAMA_FAST_BUILD \
     --build-arg=CUSTOM_CPU_FLAGS \
     --build-arg=GPU_RUNNER_CPU_FLAGS \
-    --build-arg=PARALLEL \
     --build-arg=AMDGPU_TARGETS"
 
 echo "Building Ollama"