8000 hparams : initialize arrays by ggerganov · Pull Request #13728 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

hparams : initialize arrays #13728

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 23, 2025
Merged

hparams : initialize arrays #13728

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions src/llama-hparams.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,6 @@

#include "ggml.h"

llama_hparams::llama_hparams() {
swa_layers.fill(false);
}

void llama_hparams::set_swa_pattern(uint32_t n_pattern) {
for (uint32_t il = 0; il < n_layer; ++il) {
swa_layers[il] = n_pattern == 0 || (il % n_pattern < (n_pattern - 1));
Expand Down
2 changes: 0 additions & 2 deletions src/llama-hparams.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,8 +145,6 @@ struct llama_hparams {
enum llama_rope_type rope_type = LLAMA_ROPE_TYPE_NONE;
enum llama_rope_scaling_type rope_scaling_type_train = LLAMA_ROPE_SCALING_TYPE_NONE;

llama_hparams();

// this value n_pattern means that every nth layer is dense (i.e. non-SWA)
// note that if n_pattern == 0, all layers are SWA
// if n_pattern == 1, all layers are dense
Expand Down
5 changes: 4 additions & 1 deletion src/llama-model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -463,11 +463,14 @@ void llama_model::load_hparams(llama_model_loader & ml) {
GGML_ASSERT(hparams.n_expert_used == 0);
}

// zero-out the array hparams
std::fill(hparams.n_head_arr.begin(), hparams.n_head_arr.end(), 0);
std::fill(hparams.n_head_kv_arr.begin(), hparams.n_head_kv_arr.end(), 0);
std::fill(hparams.n_ff_arr.begin(), hparams.n_ff_arr.end(), 0);

std::fill(hparams.rope_sections.begin(), hparams.rope_sections.end(), 0);

std::fill(hparams.swa_layers.begin(), hparams.swa_layers.end(), 0);

ml.get_key_or_arr(LLM_KV_FEED_FORWARD_LENGTH, hparams.n_ff_arr, hparams.n_layer, false);
ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT, hparams.n_head_arr, hparams.n_layer, false);

Expand Down
Loading
0