perf: reduce container sizes and build times

- miku-stt: switch PyTorch CUDA -> CPU-only (~2.5 GB savings)
  - Silero VAD already runs on CPU via ONNX (onnx=True), CUDA PyTorch was waste
  - faster-whisper/CTranslate2 uses CUDA directly, no PyTorch GPU needed
  - torch+torchaudio layer: 3.3 GB -> 796 MB; total image 9+ GB -> 6.83 GB
  - Tested: Silero VAD loads (ONNX), Whisper loads on cuda, server ready

- llama-swap-rocm: add root .dockerignore to fix 31 GB build context
  - Dockerfile clones all sources from git, never COPYs from context
  - 19 GB of GGUF model files were being transferred on every build
  - Now excludes everything (*), near-zero context transfer

- anime-face-detector: add .dockerignore to exclude accumulated outputs
  - api/outputs/ (56 accumulated detection files) no longer baked into image
  - api/__pycache__/ and images/ also excluded

- .gitignore: remove .dockerignore exclusion so these files are tracked

.dockerignore

@@ -0,0 +1,10 @@
+# .dockerignore for llama-swap-rocm (build context is project root)
+# The Dockerfile.llamaswap-rocm doesn't COPY anything from the build context —
+# everything is git-cloned in multi-stage builds. Exclude everything to avoid
+# sending ~31 GB of unnecessary build context (models, backups, etc.)
+
+# Exclude everything by default
+*
+
+# Only include what the Dockerfile actually needs (nothing from context currently)
+# If the Dockerfile changes to COPY files, add exceptions here with !filename