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

ggml : introduce ggml_status (ggml/750)

Browse source 
* using enum as an exit code instead of macros

* update return type from enum to unsigned int

* indentation fix

* compound update
ggml_compute_exit_code -> ggml_status
changed ggml_status from a bit-field type to simple codes
ggml_status to string cast

* ggml_status to string cast

* GGML_CALL was removed

Co-authored-by: slaren <slarengh@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Michael Podvitskiy 2024-03-04 10:05:42 +01:00 • committed by Georgi Gerganov
parent fe52be11e3
commit 9fa2627347
11 changed files with 88 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

17
ggml.h
View file

@ -315,6 +315,16 @@
extern "C" {
#endif
enum ggml_status {
GGML_STATUS_ALLOC_FAILED = -2,
GGML_STATUS_FAILED = -1,
GGML_STATUS_SUCCESS = 0,
GGML_STATUS_ABORTED = 1,
};
// get ggml_status name string
GGML_API GGML_CALL const char * ggml_status_to_string(enum ggml_status status);
typedef uint16_t ggml_fp16_t;
// convert FP16 <-> FP32
@ -1940,12 +1950,11 @@ extern "C" {
// ggml_graph_plan() has to be called before ggml_graph_compute()
// when plan.work_size > 0, caller must allocate memory for plan.work_data
GGML_API struct ggml_cplan ggml_graph_plan (const struct ggml_cgraph * cgraph, int n_threads /*= GGML_DEFAULT_N_THREADS*/);
GGML_API int ggml_graph_compute( struct ggml_cgraph * cgraph, struct ggml_cplan * cplan);
GGML_API struct ggml_cplan ggml_graph_plan (const struct ggml_cgraph * cgraph, int n_threads /*= GGML_DEFAULT_N_THREADS*/);
GGML_API enum ggml_status ggml_graph_compute ( struct ggml_cgraph * cgraph, struct ggml_cplan * cplan);
// same as ggml_graph_compute() but the work data is allocated as a part of the context
// note: the drawback of this API is that you must have ensured that the context has enough memory for the work data
GGML_API void ggml_graph_compute_with_ctx(struct ggml_context * ctx, struct ggml_cgraph * cgraph, int n_threads);
GGML_API enum ggml_status ggml_graph_compute_with_ctx(struct ggml_context * ctx, struct ggml_cgraph * cgraph, int n_threads);
GGML_API struct ggml_tensor * ggml_graph_get_tensor(struct ggml_cgraph * cgraph, const char * name);