root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

ggml : fix warnings under MSVC (#1908)

Browse Source
This commit is contained in:
Howard Su 2023-06-17 23:46:15 +08:00 committed by GitHub
parent 0711a5f6dc
commit 3d59ec5935
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml-cuda.cu
View File

@ -13,6 +13,10 @@
#include "ggml-cuda.h" #include "ggml-cuda.h"
#include "ggml.h" #include "ggml.h"
#if defined(_MSC_VER)
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
static_assert(sizeof(half) == sizeof(ggml_fp16_t), "wrong fp16 size"); static_assert(sizeof(half) == sizeof(ggml_fp16_t), "wrong fp16 size");
#define CUDA_CHECK(err) \ #define CUDA_CHECK(err) \

4
ggml-opencl.cpp
View File

@ -15,6 +15,10 @@
#include "ggml.h" #include "ggml.h"
#if defined(_MSC_VER)
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
#define CL_DMMV_BLOCK_SIZE 32 #define CL_DMMV_BLOCK_SIZE 32
#define MULTILINE_QUOTE(...) #__VA_ARGS__ #define MULTILINE_QUOTE(...) #__VA_ARGS__

2
llama.cpp
View File

@ -1253,7 +1253,7 @@ static void llama_model_load_internal(
vram_scratch = n_batch * MB; vram_scratch = n_batch * MB;
ggml_cuda_set_scratch_size(vram_scratch); ggml_cuda_set_scratch_size(vram_scratch);
if (n_gpu_layers > 0) { if (n_gpu_layers > 0) {
fprintf(stderr, "%s: allocating batch_size x 1 MB = %ld MB VRAM for the scratch buffer\n", fprintf(stderr, "%s: allocating batch_size x 1 MB = %zd MB VRAM for the scratch buffer\n",
__func__, vram_scratch / MB); __func__, vram_scratch / MB);
} }
} }