tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 12:55:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove token_info API

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-01 16:21:16 +01:00
parent 1170135dfb
commit 1d6ba97789
3 changed files with 82 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
include/llama.h
View File

@ -263,14 +263,6 @@ extern "C" {
// It can contain text tokens and embeddings for one or many sequences
struct llama_batch_ext;
struct llama_batch_ext_token_info {
llama_token token;
llama_pos pos;
int32_t n_seq_id;
llama_seq_id * seq_id;
int8_t logits;
};
enum llama_model_kv_override_type {
LLAMA_KV_OVERRIDE_TYPE_INT,
LLAMA_KV_OVERRIDE_TYPE_FLOAT,
@ -896,10 +888,6 @@ extern "C" {
// Get the number of tokens in the batch
LLAMA_API int32_t llama_batch_ext_get_n_tokens(const struct llama_batch_ext * batch);
LLAMA_API struct llama_batch_ext_token_info llama_batch_ext_get_token_info(
struct llama_batch_ext * batch,
int32_t i);
// Add text tokens to the batch
// Return values:
// 0 : success