mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-21 02:19:27 +00:00
a165a73120
# Conflicts: # examples/model-conversion/scripts/causal/run-casual-gen-embeddings-org.py # examples/model-conversion/scripts/utils/semantic_check.py # ggml/CMakeLists.txt # ggml/src/CMakeLists.txt # ggml/src/ggml-cann/ggml-cann.cpp # ggml/src/ggml-cpu/amx/amx.cpp # ggml/src/ggml-cuda/CMakeLists.txt # ggml/src/ggml-hexagon/ggml-hexagon.cpp # ggml/src/ggml-hip/CMakeLists.txt # ggml/src/ggml-opencl/ggml-opencl.cpp # ggml/src/ggml-openvino/ggml-openvino.cpp # ggml/src/ggml-rpc/ggml-rpc.cpp # ggml/src/ggml-sycl/ggml-sycl.cpp # ggml/src/ggml-virtgpu/ggml-backend-buffer.cpp # ggml/src/ggml-virtgpu/ggml-backend.cpp # ggml/src/ggml-webgpu/ggml-webgpu.cpp # ggml/src/ggml-zdnn/ggml-zdnn.cpp # ggml/src/ggml-zendnn/ggml-zendnn.cpp # pyproject.toml # requirements/requirements-convert_legacy_llama.txt # requirements/requirements-tool_bench.txt # src/llama-model.cpp # src/llama.cpp # tests/test-llama-archs.cpp # tests/test-tokenizer-0.py # tests/test-tokenizer-random.py # tools/llama-bench/llama-bench.cpp # tools/perplexity/perplexity.cpp
51 lines
1.8 KiB
C
51 lines
1.8 KiB
C
#pragma once
|
|
|
|
#include "ggml.h"
|
|
#include "ggml-backend.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#ifdef GGML_USE_HIP
|
|
#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"
|
|
#endif
|
|
#define GGML_CUDA_MAX_DEVICES 16
|
|
|
|
GGML_BACKEND_API void ggml_cuda_set_mul_mat_q(bool mul_mat_q);
|
|
// backend API
|
|
GGML_BACKEND_API ggml_backend_t ggml_backend_cuda_init(int device);
|
|
|
|
GGML_BACKEND_API bool ggml_backend_is_cuda(ggml_backend_t backend);
|
|
|
|
// device buffer
|
|
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cuda_buffer_type(int device);
|
|
|
|
// conduct allreduce operation between devices
|
|
GGML_BACKEND_API bool ggml_backend_cuda_allreduce_tensor(ggml_backend_t * backends, struct ggml_tensor ** tensors, size_t n_backends);
|
|
|
|
// split tensor buffer that splits matrices by rows across multiple devices
|
|
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_type(int main_device, const float * tensor_split);
|
|
|
|
// pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
|
|
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);
|
|
|
|
GGML_BACKEND_API int ggml_backend_cuda_get_device_count(void);
|
|
GGML_BACKEND_API void ggml_backend_cuda_get_device_description(int device, char * description, size_t description_size);
|
|
GGML_BACKEND_API void ggml_backend_cuda_get_device_memory(int device, size_t * free, size_t * total);
|
|
|
|
GGML_BACKEND_API bool ggml_backend_cuda_register_host_buffer(void * buffer, size_t size);
|
|
GGML_BACKEND_API void ggml_backend_cuda_unregister_host_buffer(void * buffer);
|
|
|
|
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_cuda_reg(void);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|