Add AMD support via ort alternative to trt

src/inference/similarity.hpp

@@ -0,0 +1,35 @@
+#pragma once
+#include <memory>
+#include <vector>
+
+// ── ISimilarityEngine ─────────────────────────────────────────────────────────
+// Backend-agnostic gallery similarity engine for the identity matcher.
+//
+// The full reference gallery (n_gallery × 512 L2-normalised embeddings) is
+// uploaded to the GPU once at construction and stays resident. Per frame, the
+// small query matrix (n_faces × 512) is uploaded and a single SGEMM produces the
+// similarity matrix S (n_gallery × n_faces, column-major) — i.e. S[g + f*n_gal]
+// is cosine_similarity(gallery[g], query[f]).
+//
+// The GPU math backend (cuBLAS/CUDA or rocBLAS/HIP) is selected at compile time
+// by CMake (SAE_GEMM_BACKEND); backends/gemm_backend.cpp provides
+// make_similarity_engine(). The core matcher node sees only this interface and
+// holds no CUDA/HIP/BLAS headers.
+
+struct ISimilarityEngine {
+    virtual ~ISimilarityEngine() = default;
+
+    // Largest n_faces accepted by compute() per call (bounds GPU buffer sizes).
+    virtual int max_faces() const = 0;
+
+    // Compute similarities for n_faces query embeddings.
+    // query_row_major: n_faces × 512, row fi at query + fi*512.
+    // Returns a pointer to host memory holding S column-major: the gallery
+    // similarities for face fi start at result + fi*n_gallery. The pointer is
+    // owned by the engine and valid until the next compute() call.
+    virtual const float* compute(const float* query_row_major, int n_faces) = 0;
+};
+
+// gallery_row_major: n_gallery × 512, embedding i at gallery + i*512.
+std::unique_ptr<ISimilarityEngine> make_similarity_engine(
+    const float* gallery_row_major, int n_gallery, int max_faces);