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

remove from common/common.h and examples/main/main.cpp

Browse source
This commit is contained in:
Roland Burke 2023-09-14 15:59:58 -04:00
parent b5e786f036
commit 00e1c707b1
2 changed files with 0 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

1
common/common.h
View file

@ -110,7 +110,6 @@ struct gpt_params {
bool perplexity = false; // compute perplexity over the prompt bool perplexity = false; // compute perplexity over the prompt
bool use_mmap = true; // use mmap for faster loads bool use_mmap = true; // use mmap for faster loads
bool use_mlock = false; // use mlock to keep model in memory bool use_mlock = false; // use mlock to keep model in memory
bool mem_test = false; // compute maximum memory usage
bool numa = false; // attempt optimizations that help on some NUMA systems bool numa = false; // attempt optimizations that help on some NUMA systems
bool export_cgraph = false; // export the computation graph bool export_cgraph = false; // export the computation graph
bool verbose_prompt = false; // print prompt tokens before generation bool verbose_prompt = false; // print prompt tokens before generation

17
examples/main/main.cpp
View file

@ -198,23 +198,6 @@ int main(int argc, char ** argv) {
params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info()); params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
} }
// determine the maximum memory usage needed to do inference for the given n_batch and n_ctx parameters
// uncomment the "used_mem" line in llama.cpp to see the results
if (params.mem_test) {
{
LOG_TEE("%s: testing memory usage for n_batch = %d, n_ctx = %d\n", __func__, params.n_batch, params.n_ctx);
const std::vector<llama_token> tmp(params.n_batch, llama_token_bos(ctx));
llama_eval(ctx, tmp.data(), tmp.size(), params.n_ctx, params.n_threads);
}
llama_print_timings(ctx);
llama_free(ctx);
llama_free_model(model);
return 0;
}
// export the cgraph and exit // export the cgraph and exit
if (params.export_cgraph) { if (params.export_cgraph) {
llama_eval_export(ctx, "llama.ggml"); llama_eval_export(ctx, "llama.ggml");