mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-19 09:15:18 +02:00
Concedo
fc6e197fdd
# Conflicts: # docs/backend/SYCL.md # docs/build.md # docs/ops.md # docs/ops/SYCL.csv # ggml/src/ggml-cuda/ggml-cuda.cu # ggml/src/ggml-hip/CMakeLists.txt # ggml/src/ggml-opencl/fa_tune.h # ggml/src/ggml-opencl/ggml-opencl.cpp # ggml/src/ggml-opencl/kernels/flash_attn_f16.cl # ggml/src/ggml-opencl/kernels/flash_attn_f32.cl # ggml/src/ggml-opencl/kernels/flash_attn_f32_f16.cl # ggml/src/ggml-opencl/kernels/flash_attn_f32_q4_0.cl # ggml/src/ggml-opencl/kernels/flash_attn_f32_q8_0.cl # ggml/src/ggml-opencl/kernels/mul_mv_f16_f32_l4.cl # ggml/src/ggml-sycl/backend.hpp # ggml/src/ggml-sycl/common.hpp # ggml/src/ggml-sycl/cpy.cpp # ggml/src/ggml-sycl/cpy.hpp # ggml/src/ggml-sycl/dmmv.cpp # ggml/src/ggml-sycl/element_wise.cpp # ggml/src/ggml-sycl/ggml-sycl.cpp # ggml/src/ggml-sycl/presets.hpp # src/llama-graph.cpp # src/llama-kv-cache.cpp
49 lines
1.6 KiB
C
49 lines
1.6 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);
|
|
|
|
// 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
|