feat: add ROCm (AMD GPU) and Intel GPU support (v0.2.12)

New image variants:
- :rocm  — InsightFace via ROCmExecutionProvider, SigLIP via PyTorch ROCm 6.3
- :intel — InsightFace via OpenVINOExecutionProvider (onnxruntime-openvino);
           Intel GPU compute runtime auto-installed from Intel graphics repo;
           OPENVINO_DEVICE=GPU opts into Arc/iGPU inference (default: CPU)

Also adds:
- pyproject-rocm.toml + uv-rocm.lock, pyproject-intel.toml + uv-intel.lock
- compose.yml device passthrough snippets for AMD and Intel
- CI: build-rocm and build-intel jobs in docker-publish.yml; all four
  variants built and tagged in release.yml
- README reworked: cleaner structure, GPU variant quick-start examples,
  OPENVINO_DEVICE env var documented
- CHANGELOG entry and version bump to 0.2.12

Fix: IntPrompt in dict literal was eagerly evaluated in the no-embedding
fallback path of _get_strategy_choice, prompting users for a custom count
regardless of which strategy they picked.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

winnow/jobs.py

@@ -58,8 +58,11 @@ def _get_strategy_choice(has_embedding: bool, entity_type: str) -> tuple[int | s
     rprint("  [bold]4.[/bold] Skip")
 
     choice = Prompt.ask("Choice", choices=["1", "2", "3", "4"], default="1")
-    limits = {"1": 30, "2": 100, "3": IntPrompt.ask("Enter number of images", default=30)}
-    return limits.get(choice, 0), "time" if choice != "4" else "skip"
+    if choice == "4":
+        return 0, "skip"
+    if choice == "3":
+        return IntPrompt.ask("Enter number of images", default=30), "time"
+    return {"1": 30, "2": 100}.get(choice, 30), "time"
 
 
 def _resolve_strategy(strategy: str, has_embedding: bool) -> tuple[int | str, str]: