CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

qwen2vl: use llama_batch_ext_set_pos

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-14 11:25:36 +01:00
parent ba79369615
commit a363251fac
3 changed files with 18 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/llama.h
View File

@@ -950,6 +950,12 @@ extern "C" {
int32_t pos0,
int32_t seq_id);
// Set arbitrary token to the embeddings batch
// Note: this is only to be used in conjunction with llama_batch_ext_init_from_embd()
// n_pos must match the n_tokens of the batch
// Returns -1 if n_pos does not match the n_tokens of the batch
LLAMA_API int32_t llama_batch_ext_set_pos(struct llama_batch_ext * batch, llama_pos * pos, size_t n_pos);
// Get the number of tokens in the batch
LLAMA_API int32_t llama_batch_ext_get_n_tokens(const struct llama_batch_ext * batch);