tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix llama_batch_ext_init_from_text

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 23:09:27 +01:00
parent 65f0184517
commit c3dd79007b
18 changed files with 40 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/llama.h
View File

@@ -928,12 +928,14 @@ extern "C" {
// Same with llama_batch_init, but initializes the batch with the provided text tokens
// First token will be at position pos0
// The sequence ID will be fixed to seq_id
// If output_last is true, the last token will have output set
// The batch has to be freed with llama_batch_ext_free()
LLAMA_API struct llama_batch_ext * llama_batch_ext_init_from_text(
llama_token * tokens,
int32_t n_tokens,
int32_t pos0,
int32_t seq_id);
int32_t seq_id,
bool output_last);
// Same with llama_batch_init, but initializes the batch with the provided raw embeddings
// First token will be at position pos0