tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

compile ok

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 22:56:35 +01:00
parent 9fb2d81eab
commit 65f0184517
9 changed files with 46 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/llava/llava-cli.cpp
View File

@ -20,7 +20,8 @@ static bool eval_tokens(struct llama_context * ctx_llama, std::vector<llama_toke
if (n_eval > n_batch) {
n_eval = n_batch;
}
if (llama_decode(ctx_llama, llama_batch_get_one(&tokens[i], n_eval))) {
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(&tokens[i], n_eval, *n_past, 0));
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;
}