talk-llama : sync llama.cpp

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-18 10:22:47 +03:00
parent 69061e356f
commit 2f60ebc3c2
26 changed files with 1454 additions and 504 deletions

View File

@ -73,8 +73,7 @@ struct llama_memory_i {
virtual llama_memory_state_ptr init_batch(
const llama_batch & batch,
uint32_t n_ubatch,
bool embd_pooled,
bool logits_all) = 0;
bool embd_all) = 0;
// simulate full cache, used for allocating worst-case compute buffers
virtual llama_memory_state_ptr init_full() = 0;