vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

[SYCL] offload op (#6217)

Browse source 
* remove no USM methods

* leave the schedule to ggml_backend_sched entirely
This commit is contained in:
Meng, Hengyu 2024-03-24 12:04:25 +08:00 • committed by GitHub
parent d03224ac98
commit ddf6568510
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 51 additions and 304 deletions
Download patch file Download diff file Expand all files Collapse all files

16
ggml-sycl.h
View file

@ -16,16 +16,22 @@ extern "C" {
#define GGML_SYCL_MAX_DEVICES 48
#define GGML_SYCL_NAME "SYCL"
GGML_API void ggml_init_sycl(void);
GGML_API bool ggml_sycl_compute_forward(struct ggml_compute_params * params, struct ggml_tensor * tensor);
// backend API
GGML_API ggml_backend_t ggml_backend_sycl_init(int device);
// devide buffer
GGML_API ggml_backend_buffer_type_t ggml_backend_sycl_buffer_type(int device);
// split tensor buffer that splits matrices by rows across multiple devices
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type(const float * tensor_split);
// pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
GGML_API ggml_backend_buffer_type_t ggml_backend_sycl_host_buffer_type(void);
GGML_API void ggml_backend_sycl_print_sycl_devices(void);
GGML_API GGML_CALL void ggml_sycl_get_gpu_list(int *id_list, int max_len);
GGML_API GGML_CALL void ggml_sycl_get_device_description(int device, char *description, size_t description_size);
GGML_API GGML_CALL int ggml_backend_sycl_get_device_count();
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type(const float * tensor_split);
GGML_API GGML_CALL void ggml_backend_sycl_get_device_memory(int device, size_t *free, size_t *total);
GGML_API GGML_CALL int ggml_backend_sycl_get_device_index(int device_id);
@ -34,6 +40,10 @@ GGML_API GGML_CALL int ggml_backend_sycl_get_device_index(int device_id);
GGML_API GGML_CALL int ggml_backend_sycl_get_device_id(int device_index);
GGML_API GGML_CALL void ggml_backend_sycl_set_single_device_mode(int main_gpu_id);
GGML_API GGML_CALL void ggml_backend_sycl_set_mul_device_mode();
// SYCL doesn't support registering host memory, keep here for reference
// GGML_API GGML_CALL bool ggml_backend_sycl_register_host_buffer(void * buffer, size_t size);
// GGML_API GGML_CALL void ggml_backend_sycl_unregister_host_buffer(void * buffer);
#ifdef __cplusplus
}
#endif