CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-21 12:16:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

musa: upgrade musa sdk to rc4.2.0 (#14498)

Browse Source 
* musa: apply mublas API changes

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

* musa: update musa version to 4.2.0

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

* musa: restore MUSA graph settings in CMakeLists.txt

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

* musa: disable mudnnMemcpyAsync by default

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

* musa: switch back to non-mudnn images

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

* minor changes

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

* musa: restore rc in docker image tag

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

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR
2025-07-25 03:05:37 +08:00
committed by GitHub
parent 2df255da3c
commit 3f4fc97f1d
9 changed files with 36 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
ggml/src/ggml-cuda/cpy.cu
View File

@@ -1,9 +1,9 @@
#include "cpy.cuh"
#include "dequantize.cuh"
#include "cpy-utils.cuh"
#ifdef GGML_USE_MUSA
#if defined(GGML_USE_MUSA) && defined(GGML_MUSA_MUDNN_COPY)
#include "ggml-musa/mudnn.cuh"
#endif // GGML_USE_MUSA
#endif // GGML_USE_MUSA && GGML_MUSA_MUDNN_COPY
typedef void (*cpy_kernel_t)(const char * cx, char * cdst);
@@ -121,7 +121,7 @@ static __global__ void cpy_q_f32(const char * cx, char * cdst_direct, const int
// Copy destination pointers to GPU to be available when pointer indirection is in use
void ggml_cuda_cpy_dest_ptrs_copy(ggml_cuda_graph * cuda_graph, char ** host_dest_ptrs, const int host_dest_ptrs_size, cudaStream_t stream) {
#if defined(GGML_CUDA_USE_GRAPHS) || defined(GGML_HIP_GRAPHS)
#if defined(GGML_CUDA_USE_GRAPHS) || defined(GGML_HIP_GRAPHS) || defined(GGML_MUSA_GRAPHS)
if (cuda_graph->dest_ptrs_size < host_dest_ptrs_size) { // (re-)allocate GPU memory for destination pointers
CUDA_CHECK(cudaStreamSynchronize(stream));
if (cuda_graph->dest_ptrs_d != nullptr) {
@@ -314,7 +314,7 @@ void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, gg
char ** dest_ptrs_d = nullptr;
int graph_cpynode_index = -1;
#if defined(GGML_CUDA_USE_GRAPHS) || defined(GGML_HIP_GRAPHS)
#if defined(GGML_CUDA_USE_GRAPHS) || defined(GGML_HIP_GRAPHS) || defined(GGML_MUSA_GRAPHS)
if(ctx.cuda_graph->use_cpy_indirection && !disable_indirection_for_this_node) {
dest_ptrs_d = ctx.cuda_graph->dest_ptrs_d;
graph_cpynode_index = ctx.cuda_graph->graph_cpynode_index;
@@ -324,11 +324,11 @@ 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));
#ifdef GGML_USE_MUSA
#if defined(GGML_USE_MUSA) && defined(GGML_MUSA_MUDNN_COPY)
if (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16) {
CUDA_CHECK(mudnnMemcpyAsync(ctx, src1, src0));
} else
#endif // GGML_USE_MUSA
#endif // GGML_USE_MUSA && GGML_MUSA_MUDNN_COPY
{
CUDA_CHECK(cudaMemcpyAsync(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream));
}
@@ -379,7 +379,7 @@ void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, gg
GGML_ABORT("%s: unsupported type combination (%s to %s)\n", __func__,
ggml_type_name(src0->type), ggml_type_name(src1->type));
}
#if defined(GGML_CUDA_USE_GRAPHS) || defined(GGML_HIP_GRAPHS)
#if defined(GGML_CUDA_USE_GRAPHS) || defined(GGML_HIP_GRAPHS) || defined(GGML_MUSA_GRAPHS)
if(ctx.cuda_graph->use_cpy_indirection && !disable_indirection_for_this_node) {
ctx.cuda_graph->graph_cpynode_index = graph_cpynode_index;
}