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

mv position to reduce model reload

Browse source
This commit is contained in:
jianyuzh 2024-02-02 00:18:36 +08:00
parent da32e212a8
commit 30c52f32b8
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/llama-bench/llama-bench.cpp
View file

@ -534,12 +534,12 @@ static std::vector<cmd_params_instance> get_cmd_params_instances(const cmd_param
for (const auto & sm : params.split_mode)
for (const auto & mg : params.main_gpu)
for (const auto & ts : params.tensor_split)
for (const auto & mmp : params.use_mmap)
for (const auto & nb : params.n_batch)
for (const auto & tk : params.type_k)
for (const auto & tv : params.type_v)
for (const auto & mmq : params.mul_mat_q)
for (const auto & nkvo : params.no_kv_offload)
for (const auto & mmp : params.use_mmap)
for (const auto & nt : params.n_threads) {
for (const auto & n_prompt : params.n_prompt) {
if (n_prompt == 0) {