tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647)

Browse Source 
* musa: fix build warning (unused parameter)

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* musa: upgrade MUSA SDK version to rc4.0.1

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* musa: use mudnn::Unary::IDENTITY op to accelerate D2D memory copy

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Update ggml/src/ggml-cuda/cpy.cu

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* musa: remove MUDNN_CHECK_GEN and use CUDA_CHECK_GEN instead in MUDNN_CHECK

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
R0CKSTAR
2025-05-21 09:58:49 +08:00
committed by GitHub
parent fb1cab201c
commit 33983057d0
10 changed files with 153 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
ggml/src/ggml-cuda/cpy.cu
View File

@ -1,5 +1,8 @@
#include "cpy.cuh"
#include "dequantize.cuh"
#ifdef GGML_USE_MUSA
#include "ggml-musa/mudnn.cuh"
#endif // GGML_USE_MUSA
typedef void (*cpy_kernel_t)(const char * cx, char * cdst);
@ -597,7 +600,14 @@ void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, gg
#endif
if (src0->type == src1->type && ggml_is_contiguous(src0) && ggml_is_contiguous(src1)) {
GGML_ASSERT(ggml_nbytes(src0) == ggml_nbytes(src1));
CUDA_CHECK(cudaMemcpyAsync(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream));
#ifdef GGML_USE_MUSA
if (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16) {
CUDA_CHECK(mudnnMemcpyAsync(ctx, src1, src0));
} else
#endif // GGML_USE_MUSA
{
CUDA_CHECK(cudaMemcpyAsync(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream));
}
} else if (src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_F32) {
ggml_cpy_f32_f32_cuda (src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, main_stream, dest_ptrs_d, graph_cpynode_index);
} else if (src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_BF16) {