RYDE-WORK/ktransformers
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/ktransformers.git synced 2026-02-02 04:28:01 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
akemimadoka 2025-02-24 01:37:50 +08:00
parent eb039b723d
commit 706e69f4fc
5 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ktransformers/ktransformers_ext/CMakeLists.txt
View File

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

2
ktransformers/ktransformers_ext/operators/kvcache/kvcache_attn.cpp
View File

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

3
ktransformers/ktransformers_ext/operators/kvcache/kvcache_load_dump.cpp
View File

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

2
ktransformers/ktransformers_ext/operators/kvcache/kvcache_read_write.cpp
View File

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

2
ktransformers/ktransformers_ext/operators/kvcache/kvcache_utils.cpp
View File

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