Fix ROCm backend (target MIGraphX EP) and add CUDA support

ROCm silently fell back to CPU: the code targeted ONNX Runtime's classic
ROCMExecutionProvider, but distro ROCm-enabled ONNX Runtime builds (e.g.
Arch's onnxruntime-rocm) are commonly compiled with --use_migraphx instead,
and registration failures were invisible since breadmill never installed a
tracing subscriber. Switches the rocm feature to target MIGraphX, adds a
default tracing subscriber so EP registration success/failure is always
visible, and fixes a real crash where MIGraphX's output sequence padding
could index the attention mask out of bounds during mean-pooling.

Also adds a CUDA backend (--cuda / backend = "cuda") mirroring the same
ort execution-provider pattern, for NVIDIA hardware.

Version bump: 0.1.0 -> 0.2.0.

breadsearch-shared/src/lib.rs

@@ -129,7 +129,7 @@ pub struct ModelConfig {
     pub name: String,
     #[serde(default = "default_dim")]
     pub dim: usize,
-    /// Compute backend: "cpu" or "npu" (VitisAI/XDNA).
+    /// Compute backend: "cpu", "npu" (VitisAI/XDNA), "rocm" (MIGraphX/AMD GPU), or "cuda" (NVIDIA GPU).
     #[serde(default = "default_backend")]
     pub backend: String,
 }