ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

batch : remove logits_all flag (#14141)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-06-12 11:49:26 +03:00 • committed by GitHub
parent e2c0b6e46a
commit c3ee46fab4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 17 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/llama-kv-cache-recurrent.cpp
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;