Merge pull request #28840 from nklskyoy:key-value-cache

FP32 KV Cache #28840

OpenCV Extra: https://github.com/opencv/opencv_extra/pull/1348

## This PR introduces basic (Paged ) KV-Cache to use on CPU

### Summary:
1. To ensure proper gemm-prepacking,
1.1. The Page Size of Key Cache is currently hardcoded as `FAST_GEMM_F32_NR`(which is 8, 12 or 16 depending on CPU architecture)  
1.2. The Page Size of Values Cache is hardcoded as `FAST_GEMM_F32_PACKED_STRIDE_K`
2. there are two phases supported - prefill & generate. 
2.1. prefill grows cache by `N` tokens and is allowed **only** for empty cache
2.2. generate grows cache by 1 token. 
2.3. **Improtant**: it is currently not allowed to grow non-empty cache by more than one token at a time (thisbehaviour is sufficient for normal LLM querying, but should be extended if we want to implement speculative decoding)

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake

modules/dnn/include/opencv2/dnn/all_layers.hpp

@@ -1876,6 +1876,8 @@ CV__DNN_INLINE_NS_BEGIN
 
     class CV_EXPORTS AttentionOnnxAiLayer : public Layer {
      public:
+        int kv_num_heads;
+
         static Ptr<AttentionOnnxAiLayer> create(const LayerParams &params);
     };
 

modules/dnn/include/opencv2/dnn/dnn.hpp

@@ -1027,6 +1027,14 @@ CV__DNN_INLINE_NS_BEGIN
          */
         CV_WRAP int64 getPerfProfile(CV_OUT std::vector<double>& timings);
 
+        /** @brief Enables KV-Cache for all AttentionOnnxI layers */
+        CV_WRAP void enableKVCache();
+
+        /** @brief Disables KV-Cache for all AttentionOnnxI layers */
+        CV_WRAP void disableKVCache();
+
+        /** @brief Resets KV-Cache for all AttentionOnnxI layers */
+        CV_WRAP void resetKVCache();
         /** @brief Returns profiling data captured during the last forward pass.
          *
          * Entries are sorted by time in descending order. Empty vectors are returned
@@ -1065,6 +1073,7 @@ CV__DNN_INLINE_NS_BEGIN
                               bool comma=true, bool dump_details=false) const;
         std::ostream& dumpDim(std::ostream& strm, int value) const;
 
+
         struct Impl;
         inline Impl* getImpl() const { return impl.get(); }
         inline Impl& getImplRef() const { CV_DbgAssert(impl); return *impl.get(); }