tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama_batch_ext_ptr::from_text/embd

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-14 17:12:03 +01:00
parent 8e7714fa77
commit eaffba0f2e
12 changed files with 34 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/llava/llava-cli.cpp
View File

@ -20,7 +20,7 @@ static bool eval_tokens(struct llama_context * ctx_llama, std::vector<llama_toke
if (n_eval > n_batch) {
n_eval = n_batch;
}
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(&tokens[i], n_eval, *n_past, 0, true));
auto batch = llama_batch_ext_ptr::from_text(&tokens[i], n_eval, *n_past, 0, true);
if (llama_decode_ext(ctx_llama, batch.get())) {
LOG_ERR("%s : failed to eval. token %d/%d (batch size %d, n_past %d)\n", __func__, i, N, n_batch, *n_past);
return false;