Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: Support Moore Threads GPU #8383

Merged
merged 6 commits into from
Jul 27, 2024
Merged

feat: Support Moore Threads GPU #8383

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
cb2c688
Update doc for MUSA
yeahdongcn Jul 12, 2024
779c920
Add GGML_MUSA in Makefile
yeahdongcn Jul 14, 2024
f085684
Add GGML_MUSA in CMake
yeahdongcn Jul 14, 2024
27396ea
CUDA => MUSA
yeahdongcn Jul 16, 2024
f4a9303
MUSA adds support for __vsubss4
yeahdongcn Jul 23, 2024
5afc5cf
Fix CI build failure
yeahdongcn Jul 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 46 additions & 9 deletions Makefile
View file
Open in desktop
Copy link
Collaborator

@JohannesGaessler JohannesGaessler Jul 9, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it would be better if the MUSA changes were completely separate from the CUDA logic in the Makefile/cmakelists.txt. But I don't feel particularly strongly about this.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I should refine this. But my initial thought is to mostly reuse the CUDA compiler settings and only change the different parts. This is because the CUDA compiler is already well-configured and I don't want to mess up with it.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

After conducting some local testing, I found that if we separate out the MUSA changes from the CUDA logic in the Makefile/CMakeLists.txt, we would end up duplicating a significant amount of code. This would lead to maintenance issues down the line.
I'd love to explore alternative solutions but I'm not sure what the best way to proceed is. I'm open to suggestions.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As I said, I don't feel particularly strongly about this. But what I would like is a consistent implementation between HIP and MUSA. So if we take the original approach of this PR then we should also adjust the HIP logic (in a separate PR).

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ok, I understand.

Original file line number Diff line number Diff line change
Expand Up @@ -526,10 +526,21 @@ ifndef GGML_NO_ACCELERATE
endif
endif # GGML_NO_ACCELERATE

ifdef GGML_MUSA
CC := clang
CXX := clang++
GGML_CUDA := 1
MK_CPPFLAGS += -DGGML_USE_MUSA
endif

ifndef GGML_NO_OPENMP
MK_CPPFLAGS += -DGGML_USE_OPENMP
MK_CFLAGS += -fopenmp
MK_CXXFLAGS += -fopenmp
ifdef GGML_MUSA
MK_CPPFLAGS += -I/usr/lib/llvm-10/include/openmp
MK_LDFLAGS += -L/usr/lib/llvm-10/lib
endif # GGML_MUSA
endif # GGML_NO_OPENMP

ifdef GGML_OPENBLAS
Expand Down Expand Up @@ -574,15 +585,27 @@ else
endif # GGML_CUDA_FA_ALL_QUANTS

ifdef GGML_CUDA
ifneq ('', '$(wildcard /opt/cuda)')
CUDA_PATH ?= /opt/cuda
ifdef GGML_MUSA
ifneq ('', '$(wildcard /opt/musa)')
CUDA_PATH ?= /opt/musa
else
CUDA_PATH ?= /usr/local/musa
endif

MK_CPPFLAGS += -DGGML_USE_CUDA -I$(CUDA_PATH)/include
MK_LDFLAGS += -lmusa -lmublas -lmusart -lpthread -ldl -lrt -L$(CUDA_PATH)/lib -L/usr/lib64
MK_NVCCFLAGS += -x musa -mtgpu --cuda-gpu-arch=mp_22
else
CUDA_PATH ?= /usr/local/cuda
endif
ifneq ('', '$(wildcard /opt/cuda)')
CUDA_PATH ?= /opt/cuda
else
CUDA_PATH ?= /usr/local/cuda
endif

MK_CPPFLAGS += -DGGML_USE_CUDA -I$(CUDA_PATH)/include -I$(CUDA_PATH)/targets/$(UNAME_M)-linux/include -DGGML_CUDA_USE_GRAPHS
MK_LDFLAGS += -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L$(CUDA_PATH)/lib64 -L/usr/lib64 -L$(CUDA_PATH)/targets/$(UNAME_M)-linux/lib -L$(CUDA_PATH)/lib64/stubs -L/usr/lib/wsl/lib
MK_NVCCFLAGS += -use_fast_math
MK_CPPFLAGS += -DGGML_USE_CUDA -I$(CUDA_PATH)/include -I$(CUDA_PATH)/targets/$(UNAME_M)-linux/include -DGGML_CUDA_USE_GRAPHS
MK_LDFLAGS += -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L$(CUDA_PATH)/lib64 -L/usr/lib64 -L$(CUDA_PATH)/targets/$(UNAME_M)-linux/lib -L$(CUDA_PATH)/lib64/stubs -L/usr/lib/wsl/lib
MK_NVCCFLAGS += -use_fast_math
endif # GGML_MUSA

OBJ_GGML += ggml/src/ggml-cuda.o
OBJ_GGML += $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/*.cu))
Expand All @@ -592,9 +615,11 @@ ifdef LLAMA_FATAL_WARNINGS
MK_NVCCFLAGS += -Werror all-warnings
endif # LLAMA_FATAL_WARNINGS

ifndef GGML_MUSA
ifndef JETSON_EOL_MODULE_DETECT
MK_NVCCFLAGS += --forward-unknown-to-host-compiler
endif # JETSON_EOL_MODULE_DETECT
endif # GGML_MUSA

ifdef LLAMA_DEBUG
MK_NVCCFLAGS += -lineinfo
Expand All @@ -607,8 +632,12 @@ endif # GGML_CUDA_DEBUG
ifdef GGML_CUDA_NVCC
NVCC = $(CCACHE) $(GGML_CUDA_NVCC)
else
NVCC = $(CCACHE) nvcc
endif #GGML_CUDA_NVCC
ifdef GGML_MUSA
NVCC = $(CCACHE) mcc
JohannesGaessler marked this conversation as resolved.
Show resolved Hide resolved
else
NVCC = $(CCACHE) nvcc
endif # GGML_MUSA
endif # GGML_CUDA_NVCC

ifdef CUDA_DOCKER_ARCH
MK_NVCCFLAGS += -Wno-deprecated-gpu-targets -arch=$(CUDA_DOCKER_ARCH)
Expand Down Expand Up @@ -679,9 +708,15 @@ define NVCC_COMPILE
$(NVCC) -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -O3 $(NVCCFLAGS) $(CPPFLAGS) -Xcompiler "$(CUDA_CXXFLAGS)" -c $< -o $@
endef # NVCC_COMPILE
else
ifdef GGML_MUSA
define NVCC_COMPILE
$(NVCC) $(NVCCFLAGS) $(CPPFLAGS) -c $< -o $@
endef # NVCC_COMPILE
else
define NVCC_COMPILE
$(NVCC) $(NVCCFLAGS) $(CPPFLAGS) -Xcompiler "$(CUDA_CXXFLAGS)" -c $< -o $@
endef # NVCC_COMPILE
endif # GGML_MUSA
endif # JETSON_EOL_MODULE_DETECT

ggml/src/ggml-cuda/%.o: \
Expand Down Expand Up @@ -907,6 +942,7 @@ $(info I CXX: $(shell $(CXX) --version | head -n 1))
ifdef GGML_CUDA
$(info I NVCC: $(shell $(NVCC) --version | tail -n 1))
CUDA_VERSION := $(shell $(NVCC) --version | grep -oP 'release (\K[0-9]+\.[0-9])')
ifndef GGML_MUSA
ifeq ($(shell awk -v "v=$(CUDA_VERSION)" 'BEGIN { print (v < 11.7) }'),1)

ifndef CUDA_DOCKER_ARCH
Expand All @@ -916,6 +952,7 @@ endif # CUDA_POWER_ARCH
endif # CUDA_DOCKER_ARCH

endif # eq ($(shell echo "$(CUDA_VERSION) < 11.7" | bc),1)
endif # GGML_MUSA
endif # GGML_CUDA
$(info )

Expand Down
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -405,6 +405,7 @@ Please refer to [Build llama.cpp locally](./docs/build.md)
| [BLAS](./docs/build.md#blas-build) | All |
| [BLIS](./docs/backend/BLIS.md) | All |
| [SYCL](./docs/backend/SYCL.md) | Intel and Nvidia GPU |
| [MUSA](./docs/build.md#musa) | Moore Threads GPU |
| [CUDA](./docs/build.md#cuda) | Nvidia GPU |
| [hipBLAS](./docs/build.md#hipblas) | AMD GPU |
| [Vulkan](./docs/build.md#vulkan) | GPU |
Expand Down
13 changes: 13 additions & 0 deletions docs/build.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,6 +181,19 @@ The environment variable [`CUDA_VISIBLE_DEVICES`](https://docs.nvidia.com/cuda/c
| GGML_CUDA_PEER_MAX_BATCH_SIZE | Positive integer | 128 | Maximum batch size for which to enable peer access between multiple GPUs. Peer access requires either Linux or NVLink. When using NVLink enabling peer access for larger batch sizes is potentially beneficial. |
| GGML_CUDA_FA_ALL_QUANTS | Boolean | false | Compile support for all KV cache quantization type (combinations) for the FlashAttention CUDA kernels. More fine-grained control over KV cache size but compilation takes much longer. |

### MUSA

- Using `make`:
```bash
make GGML_MUSA=1
```
- Using `CMake`:

```bash
cmake -B build -DGGML_MUSA=ON
cmake --build build --config Release
```

### hipBLAS

This provides BLAS acceleration on HIP-supported AMD GPUs.
Expand Down
1 change: 1 addition & 0 deletions ggml/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,6 +107,7 @@ set(GGML_BLAS_VENDOR ${GGML_BLAS_VENDOR_DEFAULT} CACHE STRING
option(GGML_LLAMAFILE "ggml: use LLAMAFILE" OFF)

option(GGML_CUDA "ggml: use CUDA" OFF)
option(GGML_MUSA "ggml: use MUSA" OFF)
option(GGML_CUDA_FORCE_DMMV "ggml: use dmmv instead of mmvq CUDA kernels" OFF)
option(GGML_CUDA_FORCE_MMQ "ggml: use mmq kernels instead of cuBLAS" OFF)
option(GGML_CUDA_FORCE_CUBLAS "ggml: always use cuBLAS instead of mmq kernels" OFF)
Expand Down
3 changes: 3 additions & 0 deletions ggml/include/ggml-cuda.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,9 @@
#ifdef GGML_USE_HIPBLAS
#define GGML_CUDA_NAME "ROCm"
#define GGML_CUBLAS_NAME "hipBLAS"
#elif defined(GGML_USE_MUSA)
#define GGML_CUDA_NAME "MUSA"
#define GGML_CUBLAS_NAME "muBLAS"
#else
#define GGML_CUDA_NAME "CUDA"
#define GGML_CUBLAS_NAME "cuBLAS"
Expand Down
62 changes: 55 additions & 7 deletions ggml/src/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,17 @@ if (GGML_METAL)
)
endif()

if (GGML_MUSA)
set(CMAKE_C_COMPILER clang)
set(CMAKE_C_EXTENSIONS OFF)
set(CMAKE_CXX_COMPILER clang++)
set(CMAKE_CXX_EXTENSIONS OFF)

set(GGML_CUDA ON)

list(APPEND GGML_CDEF_PUBLIC GGML_USE_MUSA)
endif()

if (GGML_OPENMP)
find_package(OpenMP)
if (OpenMP_FOUND)
Expand All @@ -147,6 +158,11 @@ if (GGML_OPENMP)
add_compile_definitions(GGML_USE_OPENMP)

set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} OpenMP::OpenMP_C OpenMP::OpenMP_CXX)

if (GGML_MUSA)
set(GGML_EXTRA_INCLUDES ${GGML_EXTRA_INCLUDES} "/usr/lib/llvm-10/include/openmp")
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} "/usr/lib/llvm-10/lib/libomp.so")
endif()
else()
message(WARNING "OpenMP not found")
endif()
Expand Down Expand Up @@ -249,7 +265,13 @@ endif()
if (GGML_CUDA)
cmake_minimum_required(VERSION 3.18) # for CMAKE_CUDA_ARCHITECTURES

find_package(CUDAToolkit)
if (GGML_MUSA)
list(APPEND CMAKE_MODULE_PATH "/usr/local/musa/cmake/")
find_package(MUSAToolkit)
set(CUDAToolkit_FOUND ${MUSAToolkit_FOUND})
else()
find_package(CUDAToolkit)
endif()

if (CUDAToolkit_FOUND)
message(STATUS "CUDA found")
Expand All @@ -268,7 +290,11 @@ if (GGML_CUDA)
endif()
message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")

enable_language(CUDA)
if (GGML_MUSA)
set(CMAKE_CUDA_COMPILER ${MUSAToolkit_MCC_EXECUTABLE})
else()
enable_language(CUDA)
endif()

file(GLOB GGML_HEADERS_CUDA "ggml-cuda/*.cuh")
list(APPEND GGML_HEADERS_CUDA "../include/ggml-cuda.h")
Expand Down Expand Up @@ -332,21 +358,40 @@ if (GGML_CUDA)
add_compile_definitions(GGML_CUDA_NO_PEER_COPY)
endif()

if (GGML_MUSA)
set_source_files_properties(${GGML_SOURCES_CUDA} PROPERTIES LANGUAGE CXX)
foreach(SOURCE ${GGML_SOURCES_CUDA})
set_property(SOURCE ${SOURCE} PROPERTY COMPILE_FLAGS "-x musa -mtgpu --cuda-gpu-arch=mp_22")
endforeach()
endif()

if (GGML_STATIC)
if (WIN32)
# As of 12.3.1 CUDA Toolkit for Windows does not offer a static cublas library
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas CUDA::cublasLt)
else ()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musart_static MUSA::mublas_static)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
endif()
endif()
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musart MUSA::mublas)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
endif()
endif()

if (GGML_CUDA_NO_VMM)
# No VMM requested, no need to link directly with the cuda driver lib (libcuda.so)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cuda_driver) # required by cuDeviceGetAttribute(), cuMemGetAllocationGranularity(...), ...
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musa_driver) # required by muDeviceGetAttribute(), muMemGetAllocationGranularity(...), ...
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cuda_driver) # required by cuDeviceGetAttribute(), cuMemGetAllocationGranularity(...), ...
endif()
endif()
else()
message(WARNING "CUDA not found")
Expand Down Expand Up @@ -757,8 +802,10 @@ function(get_flags CCID CCVER)
set(C_FLAGS -Wdouble-promotion)
set(CXX_FLAGS -Wno-array-bounds)

if (CCVER VERSION_GREATER_EQUAL 7.1.0)
list(APPEND CXX_FLAGS -Wno-format-truncation)
if (NOT GGML_MUSA)
if (CCVER VERSION_GREATER_EQUAL 7.1.0)
list(APPEND CXX_FLAGS -Wno-format-truncation)
endif()
endif()
if (CCVER VERSION_GREATER_EQUAL 8.1.0)
list(APPEND CXX_FLAGS -Wextra-semi)
Expand Down Expand Up @@ -1163,6 +1210,7 @@ endif()
target_compile_definitions(ggml PUBLIC ${GGML_CDEF_PUBLIC})
target_include_directories(ggml PUBLIC ../include)
target_include_directories(ggml PRIVATE . ${GGML_EXTRA_INCLUDES})
target_link_directories(ggml PRIVATE ${GGML_EXTRA_LIBDIRS})
target_compile_features (ggml PRIVATE c_std_11) # don't bump

target_link_libraries(ggml PRIVATE Threads::Threads ${GGML_EXTRA_LIBS})
Expand Down
6 changes: 5 additions & 1 deletion ggml/src/ggml-common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,11 @@ typedef half2 ggml_half2;

#define GGML_COMMON_DECL
#elif defined(GGML_COMMON_DECL_CUDA)
#if defined(GGML_COMMON_DECL_MUSA)
#include <musa_fp16.h>
#else
#include <cuda_fp16.h>
#endif
#include <cstdint>

typedef half ggml_half;
Expand Down Expand Up @@ -415,7 +419,7 @@ static_assert(sizeof(block_iq4_xs) == sizeof(ggml_half) + sizeof(uint16_t) + QK_
#define GGML_TABLE_END() };

#define GGML_COMMON_IMPL
#elif defined(GGML_COMMON_IMPL_CUDA) || defined(GGML_COMMON_IMPL_HIP)
#elif defined(GGML_COMMON_IMPL_CUDA) || defined(GGML_COMMON_IMPL_HIP) || defined(GGML_COMMON_IMPL_MUSA)
#include <cstdint>

#define GGML_TABLE_BEGIN(type, name, size) static const __device__ type name[size] = {
Expand Down
22 changes: 13 additions & 9 deletions ggml/src/ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,7 +167,7 @@ static ggml_cuda_device_info ggml_cuda_init() {
for (int id = 0; id < info.device_count; ++id) {
int device_vmm = 0;

#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
CUdevice device;
CU_CHECK(cuDeviceGet(&device, id));
CU_CHECK(cuDeviceGetAttribute(&device_vmm, CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED, device));
Expand All @@ -179,7 +179,7 @@ static ggml_cuda_device_info ggml_cuda_init() {
alloc_prop.location.id = id;
CU_CHECK(cuMemGetAllocationGranularity(&info.devices[id].vmm_granularity, &alloc_prop, CU_MEM_ALLOC_GRANULARITY_RECOMMENDED));
}
#endif // !defined(GGML_USE_HIPBLAS)
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
info.devices[id].vmm = !!device_vmm;

cudaDeviceProp prop;
Expand Down Expand Up @@ -315,7 +315,7 @@ struct ggml_cuda_pool_leg : public ggml_cuda_pool {
};

// pool with virtual memory
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
struct ggml_cuda_pool_vmm : public ggml_cuda_pool {
static const size_t CUDA_POOL_VMM_MAX_SIZE = 1ull << 35; // 32 GB

Expand Down Expand Up @@ -409,14 +409,14 @@ struct ggml_cuda_pool_vmm : public ggml_cuda_pool {
GGML_ASSERT(ptr == (void *) (pool_addr + pool_used));
}
};
#endif // !defined(GGML_USE_HIPBLAS)
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)

std::unique_ptr<ggml_cuda_pool> ggml_backend_cuda_context::new_pool_for_device(int device) {
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
if (ggml_cuda_info().devices[device].vmm) {
return std::unique_ptr<ggml_cuda_pool>(new ggml_cuda_pool_vmm(device));
}
#endif
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
return std::unique_ptr<ggml_cuda_pool>(new ggml_cuda_pool_leg(device));
}

Expand Down Expand Up @@ -1341,7 +1341,7 @@ static void ggml_cuda_set_peer_access(const int n_tokens, int main_device) {
static cudaError_t ggml_cuda_Memcpy2DPeerAsync(
void * dst, int dstDevice, size_t dpitch, void * src, int srcDevice, size_t spitch, size_t width, size_t height, cudaStream_t stream) {

#if !defined(GGML_USE_HIPBLAS)
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_USE_MUSA)
// cudaMemcpy2DAsync may fail with copies between vmm pools of different devices
cudaMemcpy3DPeerParms p = {};
p.dstDevice = dstDevice;
Expand All @@ -1355,7 +1355,7 @@ static cudaError_t ggml_cuda_Memcpy2DPeerAsync(
GGML_UNUSED(dstDevice);
GGML_UNUSED(srcDevice);
return cudaMemcpy2DAsync(dst, dpitch, src, spitch, width, height, cudaMemcpyDeviceToDevice, stream);
#endif // !defined(GGML_USE_HIPBLAS)
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_USE_MUSA)
}

static void ggml_cuda_op_mul_mat(
Expand Down Expand Up @@ -1821,6 +1821,9 @@ static void ggml_cuda_mul_mat_batched_cublas(ggml_backend_cuda_context & ctx, co
}
}
#else
#ifdef GGML_USE_MUSA
GGML_ASSERT(false);
#else // !GGML_USE_MUSA
if (r2 == 1 && r3 == 1 && ggml_is_contiguous_2(src0) && ggml_is_contiguous_2(src1)) {
// there is no broadcast and src0, src1 are contiguous across dims 2, 3
// use cublasGemmStridedBatchedEx
Expand Down Expand Up @@ -1863,6 +1866,7 @@ static void ggml_cuda_mul_mat_batched_cublas(ggml_backend_cuda_context & ctx, co
cu_compute_type,
CUBLAS_GEMM_DEFAULT_TENSOR_OP));
}
#endif // GGML_USE_MUSA
#endif

if (dst->op_params[0] == GGML_PREC_DEFAULT) {
Expand Down Expand Up @@ -3019,7 +3023,7 @@ GGML_CALL bool ggml_backend_cuda_register_host_buffer(void * buffer, size_t size
return false;
}

#if CUDART_VERSION >= 11100
#if CUDART_VERSION >= 11100 || defined(GGML_USE_MUSA)
cudaError_t err = cudaHostRegister(buffer, size, cudaHostRegisterPortable | cudaHostRegisterReadOnly);
if (err != cudaSuccess) {
// clear the error
Expand Down
Loading
Loading