vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-10 01:15:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add cpu flops test

Browse source
This commit is contained in:
Lizonghang 2024-11-09 20:53:42 +04:00
parent 2bd4d03aa8
commit 5fae6ac36f
6 changed files with 146 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files

3
include/llama.h
View file

@ -410,7 +410,7 @@ extern "C" {
// Call once at the start of the program
LLAMA_API void llama_backend_init(void);
LLAMA_API void llama_profile_device (struct device_info * dev_info, struct llama_model * model, const char * test_file);
LLAMA_API void llama_profile_device (struct device_info * dev_info, struct llama_model * model, const char * test_file, int n_threads);
LLAMA_API ggml_backend_buffer_type_t llama_dev_buffer_type(struct llama_model * model, int device);
//optional:
@ -476,6 +476,7 @@ extern "C" {
LLAMA_API int32_t llama_n_embd (const struct llama_model * model);
LLAMA_API int32_t llama_n_layer (const struct llama_model * model);
LLAMA_API int32_t llama_n_head (const struct llama_model * model);
LLAMA_API int32_t llama_n_ff_hidden(const struct llama_model * model);
LLAMA_API const struct llama_model * llama_get_model(const struct llama_context * ctx);