mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 10:54:36 +00:00
6bbc598a63
* use hipblas based on cublas * Update Makefile for the Cuda kernels * Expand arch list and make it overrideable * Fix multi GPU on multiple amd architectures with rocblas_initialize() (#5) * add hipBLAS to README * new build arg LLAMA_CUDA_MMQ_Y * fix half2 decomposition * Add intrinsics polyfills for AMD * AMD assembly optimized __dp4a * Allow overriding CC_TURING * use "ROCm" instead of "CUDA" * ignore all build dirs * Add Dockerfiles * fix llama-bench * fix -nommq help for non CUDA/HIP --------- Co-authored-by: YellowRoseCx <80486540+YellowRoseCx@users.noreply.github.com> Co-authored-by: ardfork <134447697+ardfork@users.noreply.github.com> Co-authored-by: funnbot <22226942+funnbot@users.noreply.github.com> Co-authored-by: Engininja2 <139037756+Engininja2@users.noreply.github.com> Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com> Co-authored-by: jammm <2500920+jammm@users.noreply.github.com> Co-authored-by: jdecourval <7315817+jdecourval@users.noreply.github.com>
47 lines
1.7 KiB
C
47 lines
1.7 KiB
C
#pragma once
|
|
|
|
#include "ggml.h"
|
|
|
|
#ifdef GGML_USE_HIPBLAS
|
|
#define GGML_CUDA_NAME "ROCm"
|
|
#define GGML_CUBLAS_NAME "hipBLAS"
|
|
#else
|
|
#define GGML_CUDA_NAME "CUDA"
|
|
#define GGML_CUBLAS_NAME "cuBLAS"
|
|
#endif
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define GGML_CUDA_MAX_DEVICES 16
|
|
|
|
GGML_API void ggml_init_cublas(void);
|
|
GGML_API void * ggml_cuda_host_malloc(size_t size);
|
|
GGML_API void ggml_cuda_host_free(void * ptr);
|
|
|
|
GGML_API bool ggml_cuda_can_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
|
|
GGML_API void ggml_cuda_set_tensor_split(const float * tensor_split);
|
|
GGML_API void ggml_cuda_transform_tensor(void * data, struct ggml_tensor * tensor);
|
|
GGML_API void ggml_cuda_free_data(struct ggml_tensor * tensor);
|
|
|
|
GGML_API void ggml_cuda_assign_buffers(struct ggml_tensor * tensor);
|
|
GGML_API void ggml_cuda_assign_buffers_no_scratch(struct ggml_tensor * tensor);
|
|
GGML_API void ggml_cuda_assign_buffers_force_inplace(struct ggml_tensor * tensor);
|
|
|
|
GGML_API void ggml_cuda_assign_buffers_no_alloc(struct ggml_tensor * tensor);
|
|
GGML_API void ggml_cuda_assign_scratch_offset(struct ggml_tensor * tensor, size_t offset);
|
|
|
|
GGML_API void ggml_cuda_set_main_device(int main_device);
|
|
GGML_API void ggml_cuda_set_mul_mat_q(bool mul_mat_q);
|
|
GGML_API void ggml_cuda_set_scratch_size(size_t scratch_size);
|
|
GGML_API void ggml_cuda_free_scratch(void);
|
|
GGML_API bool ggml_cuda_compute_forward(struct ggml_compute_params * params, struct ggml_tensor * tensor);
|
|
|
|
GGML_API int ggml_cuda_get_device_count(void);
|
|
GGML_API void ggml_cuda_get_device_description(int device, char * description, size_t description_size);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|