Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-09 22:39:04 +02:00
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
src/llama-kv-cache-recurrent.cpp
+2 -2
View File
@@ -359,10 +359,10 @@ llama_pos llama_kv_cache_recurrent::seq_pos_max(llama_seq_id seq_id) const {
return result;
}
llama_memory_state_ptr llama_kv_cache_recurrent::init_batch(const llama_batch & batch, uint32_t n_ubatch, bool embd_pooled, bool logits_all) {
llama_memory_state_ptr llama_kv_cache_recurrent::init_batch(const llama_batch & batch, uint32_t n_ubatch, bool embd_pooled) {
GGML_UNUSED(embd_pooled);
auto sbatch = llama_sbatch(batch, hparams.n_embd, false, logits_all);
auto sbatch = llama_sbatch(batch, hparams.n_embd, false);
std::vector<llama_ubatch> ubatches;