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

6
common/sampling.cpp
View file

@ -142,7 +142,7 @@ std::string gpt_sampler_params::print() const {
struct gpt_sampler * gpt_sampler_init(const struct llama_model * model, const struct gpt_sampler_params & params) {
llama_sampler_chain_params lparams = llama_sampler_chain_default_params();
lparams.no_perf = false; // TODO: control via params
lparams.no_perf = params.no_perf;
auto * result = new gpt_sampler {
/* .params = */ params,
@ -257,10 +257,10 @@ void gpt_perf_print(const struct llama_context * ctx, const struct gpt_sampler *
// TODO: measure grammar performance
if (gsmpl) {
llama_perf_print(gsmpl->chain, LLAMA_PERF_TYPE_SAMPLER_CHAIN);
llama_perf_sampler_print(gsmpl->chain);
}
if (ctx) {
llama_perf_print(ctx, LLAMA_PERF_TYPE_CONTEXT);
llama_perf_context_print(ctx);
}
}