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

batch : remove logits_all flag

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-12 10:10:45 +03:00
parent 9596506965
commit c53acda0b8
10 changed files with 17 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-batch.h
View File

@ -39,8 +39,6 @@ struct llama_sbatch {
size_t n_embd;
bool logits_all; // TODO: remove once lctx.logits_all is removed too
// sorted indices into the batch
std::vector<int64_t> ids;
// batch indices of the output
@ -76,7 +74,7 @@ struct llama_sbatch {
llama_ubatch split_seq(size_t n_ubatch);
llama_sbatch() = default;
llama_sbatch(const llama_batch & batch, size_t n_embd, bool simple_split = false, bool logits_all = false);
llama_sbatch(const llama_batch & batch, size_t n_embd, bool simple_split = false);
};
// temporary allocate memory for the input batch if needed