Merge pull request #622 from akemimadoka/fix-msvc

Fix missing macro definition for KTRANSFORMERS_USE_CUDA and <chrono> includes on MSVC

ktransformers/ktransformers_ext/CMakeLists.txt

@@ -209,6 +209,7 @@ add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/../../third_party/llama.cpp ${CMAKE
 include_directories(${CMAKE_CURRENT_SOURCE_DIR}/../../third_party)
 if (WIN32)
     include_directories("$ENV{CUDA_PATH}/include")
+    add_compile_definitions(KTRANSFORMERS_USE_CUDA=1)
 elseif (UNIX)
     if (KTRANSFORMERS_USE_CUDA)
         find_package(CUDA REQUIRED)

ktransformers/ktransformers_ext/operators/kvcache/kvcache_attn.cpp

@@ -10,6 +10,8 @@
 
 #include "kvcache.h"
 
+#include <chrono>
+
 void KVCache::attention_kvhead_(const uint16_t *q_in_data, ggml_fp16_t *output,
                                 float *attn_lse, int batch_size,
                                 Backend *backend) {

ktransformers/ktransformers_ext/operators/kvcache/kvcache_load_dump.cpp

@@ -9,6 +9,9 @@
  **/
 
 #include "kvcache.h"
+
+#include <chrono>
+
 void KVCache::load_kvcache(std::string tensor_file_path, Backend *backend) {
     // Timer start
     auto start = std::chrono::high_resolution_clock::now();

ktransformers/ktransformers_ext/operators/kvcache/kvcache_read_write.cpp

@@ -10,6 +10,8 @@
 
 #include "kvcache.h"
 
+#include <chrono>
+
 void KVCache::get_anchor_one_block(ggml_fp16_t *anchor, int layer_id,
                                    int block_idx, Backend *backend) {
     // Timer start

ktransformers/ktransformers_ext/operators/kvcache/kvcache_utils.cpp

@@ -10,6 +10,8 @@
 
 #include "kvcache.h"
 
+#include <chrono>
+
 std::string ggml_type_to_string(ggml_type type) {
     switch (type) {
     case GGML_TYPE_F32: