mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
@@ -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_pooled) = 0;
|
||||
|
||||
// simulate full cache, used for allocating worst-case compute buffers
|
||||
virtual llama_memory_state_ptr init_full() = 0;
|
||||
|
||||
Reference in New Issue
Block a user