CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Apply suggestions from code review

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2025-03-17 12:17:14 +01:00
committed by GitHub
parent de788e071b
commit eab5606d7b
3 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/batched-bench/batched-bench.cpp
View File

@@ -147,7 +147,7 @@ int main(int argc, char ** argv) {
llama_batch_ext_clear(batch); llama_batch_ext_clear(batch);
for (int j = 0; j < pl; ++j) { for (int j = 0; j < pl; ++j) {
llama_batch_ext_add_text(batch, 0, pp + i, &j, 1, false); llama_batch_ext_add_text(batch, 0, pp + i, &j, 1, true);
} }
if (!decode_helper(ctx, batch, ctx_params.n_batch)) { if (!decode_helper(ctx, batch, ctx_params.n_batch)) {

2
examples/batched/batched.cpp
View File

@@ -196,7 +196,7 @@ int main(int argc, char ** argv) {
i_batch[i] = llama_batch_ext_get_n_tokens(batch); i_batch[i] = llama_batch_ext_get_n_tokens(batch);
// push this new token for next evaluation // push this new token for next evaluation
llama_batch_ext_add_text(batch, new_token_id, n_cur, &i, 1, false); llama_batch_ext_add_text(batch, new_token_id, n_cur, &i, 1, true);
n_decode += 1; n_decode += 1;
} }

1
examples/main/main.cpp
View File

@@ -670,7 +670,6 @@ int main(int argc, char ** argv) {
LOG_DBG("eval: %s\n", string_from(ctx, embd).c_str()); LOG_DBG("eval: %s\n", string_from(ctx, embd).c_str());
auto batch = llama_batch_ext_ptr::init_from_text(&embd[i], n_eval, n_past, 0, true); auto batch = llama_batch_ext_ptr::init_from_text(&embd[i], n_eval, n_past, 0, true);
llama_batch_ext_set_output_last(batch.get());
if (llama_decode_ext(ctx, batch.get())) { if (llama_decode_ext(ctx, batch.get())) {
LOG_ERR("%s : failed to eval\n", __func__); LOG_ERR("%s : failed to eval\n", __func__);
return 1; return 1;