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

llama.cpp : split llama_context_params into model and context params (#3301)

Browse source 
* llama.cpp : split llama_context_params into model and context params

ggml-ci

* fix metal build

* fix freq_base/scale default to model value

* llama-bench : keep the same model between tests when possible

* move n_threads to llama_context_params, add n_threads_batch

* fix mpi build

* remove kv_size(), cuda scratch fixes

* remove low-vram option

* add n_threads_batch to system info, refactor to get_system_info()

* add documentation about --threads-batch to the READMEs

* llama-bench fix

* main : fix rope freq/scale warning

* llama.cpp : add llama_get_model
common : add llama_tokenize from model

* remove duplicated ctx/model functions

ggml-ci

* cuda : print total VRAM used
This commit is contained in:
slaren 2023-09-28 21:42:38 +02:00 • committed by GitHub
parent 0512d66670
commit 16bc66d947
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
27 changed files with 713 additions and 633 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/beam-search/beam-search.cpp
View file

@ -160,7 +160,7 @@ int main(int argc, char ** argv)
int n_past = 0;
if (llama_decode(ctx, llama_batch_get_one(tokens_list.data(), tokens_list.size(), n_past, 0), params.n_threads))
if (llama_decode(ctx, llama_batch_get_one(tokens_list.data(), tokens_list.size(), n_past, 0)))
{
fprintf(stderr, "%s : failed to eval prompt.\n" , __func__ );
return 1;
@ -170,7 +170,7 @@ int main(int argc, char ** argv)
beam_search_callback_data callback_data{ctx, {}};
size_t const beam_width = static_cast<size_t>(params.n_beams);
int const n_predict = 256;
llama_beam_search(ctx, beam_search_callback, &callback_data, beam_width, n_past, n_predict, params.n_threads);
llama_beam_search(ctx, beam_search_callback, &callback_data, beam_width, n_past, n_predict);
std::cout << "\n\n";
for (llama_token const token_id : callback_data.response) {