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

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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);

2
examples/llava/minicpmv-cli.cpp
View file

@ -319,7 +319,7 @@ int main(int argc, char ** argv) {
}
}
printf("\n");
llama_perf_print(ctx_llava->ctx_llama, LLAMA_PERF_TYPE_CONTEXT);
llama_perf_context_print(ctx_llava->ctx_llama);
ctx_llava->model = NULL;
llava_free(ctx_llava);