Update llama.cpp
Add review comments Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
This commit is contained in:
parent
14804b7978
commit
a0c895c087
1 changed files with 1 additions and 1 deletions
|
@ -1670,7 +1670,7 @@ int llama_model_quantize(
|
|||
|
||||
// Returns the KV cache that will contain the context for the
|
||||
// ongoing prediction with the model.
|
||||
uint8_t* llama_get_kv_cache(struct llama_context * ctx) {
|
||||
const uint8_t * llama_get_kv_cache(struct llama_context * ctx) {
|
||||
return ctx->model.kv_self.buf.data();
|
||||
}
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue