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

sync : ggml (part 2, CUDA)

Browse source
This commit is contained in:
Georgi Gerganov 2023-12-07 13:32:54 +02:00
parent 8bad78b8e2
commit 6b1cf54197
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
2 changed files with 1024 additions and 390 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1404
ggml-cuda.cu
View file

File diff suppressed because it is too large Load diff

10
ggml-cuda.h
View file

@ -49,7 +49,15 @@ 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);
// backend API
GGML_API ggml_backend_t ggml_backend_cuda_init(void); // TODO: take a list of devices to use
GGML_API ggml_backend_t ggml_backend_cuda_init(int device);
GGML_API bool ggml_backend_is_cuda(ggml_backend_t backend);
GGML_API int ggml_backend_cuda_get_device(ggml_backend_t backend);
GGML_API ggml_backend_buffer_type_t ggml_backend_cuda_buffer_type(int device);
// pinned host buffer for use with CPU backend for faster copies between CPU and GPU
GGML_API ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);
#ifdef __cplusplus
}