tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : llama_perf + option to disable timings during decode (#9355)

Browse Source 
* llama : llama_perf + option to disable timings during decode

ggml-ci

* common : add llama_arg

* Update src/llama.cpp

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* perf : separate functions in the API

ggml-ci

* perf : safer pointer handling + naming update

ggml-ci

* minor : better local var name

* perf : abort on invalid sampler pointer

ggml-ci

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Georgi Gerganov
2024-09-13 09:53:38 +03:00
committed by GitHub
parent bd35cb0ae3
commit 0abc6a2c25
23 changed files with 135 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/llava/llava-cli.cpp
View File

@ -308,7 +308,7 @@ int main(int argc, char ** argv) {
// process the prompt
process_prompt(ctx_llava, image_embed, &params, params.prompt);
llama_perf_print(ctx_llava->ctx_llama, LLAMA_PERF_TYPE_CONTEXT);
llama_perf_context_print(ctx_llava->ctx_llama);
llava_image_embed_free(image_embed);
ctx_llava->model = NULL;
llava_free(ctx_llava);
@ -325,7 +325,7 @@ int main(int argc, char ** argv) {
// process the prompt
process_prompt(ctx_llava, image_embed, &params, params.prompt);
llama_perf_print(ctx_llava->ctx_llama, LLAMA_PERF_TYPE_CONTEXT);
llama_perf_context_print(ctx_llava->ctx_llama);
llava_image_embed_free(image_embed);
ctx_llava->model = NULL;
llava_free(ctx_llava);