perf: cache CPU position embeddings across DiT runners (#2211)

src/core/pe_cache.cpp

@@ -0,0 +1,30 @@
+#include "core/pe_cache.h"
+
+namespace sd {
+    PECacheKey& PECacheKey::add_shape(const ggml_tensor* tensor) {
+        add(tensor != nullptr);
+        if (tensor != nullptr) {
+            for (int i = 0; i < GGML_MAX_DIMS; ++i) {
+                add(tensor->ne[i]);
+            }
+        }
+        return *this;
+    }
+
+    PECacheKey& PECacheKey::add_shapes(const std::vector<ggml_tensor*>& tensors) {
+        add(tensors.size());
+        for (const auto* tensor : tensors) {
+            add_shape(tensor);
+        }
+        return *this;
+    }
+
+    const Tensor<float>& PECache::get_or_create(const PECacheKey& key, const std::function<Tensor<float>()>& build) {
+        auto entry = entries_.find(key.name());
+        if (entry != entries_.end() && entry->second.key == key) {
+            return entry->second.value;
+        }
+        auto value = build();
+        return entries_.insert_or_assign(key.name(), Entry{key, std::move(value)}).first->second.value;
+    }
+}