mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-17 21:51:27 -04:00
sync : ggml (new ops, tests, backend, etc.) (#4359)
* sync : ggml (part 1)
* sync : ggml (part 2, CUDA)
* sync : ggml (part 3, Metal)
* ggml : build fixes
ggml-ci
* cuda : restore lost changes
* cuda : restore lost changes (StableLM rope)
* cmake : enable separable compilation for CUDA
ggml-ci
* ggml-cuda : remove device side dequantize
* Revert "cmake : enable separable compilation for CUDA"
This reverts commit 09e35d04b1
.
* cuda : remove assert for rope
* tests : add test-backend-ops
* ggml : fix bug in ggml_concat
* ggml : restore `ggml_get_n_tasks()` logic in `ggml_graph_plan()`
* ci : try to fix macOS
* ggml-backend : remove backend self-registration
* ci : disable Metal for macOS cmake build
ggml-ci
* metal : fix "supports family" call
* metal : fix assert
* metal : print resource path
ggml-ci
---------
Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
10
ggml-cuda.h
10
ggml-cuda.h
@@ -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
|
||||
}
|
||||
|
Reference in New Issue
Block a user