|
|
@ -529,7 +529,7 @@ bool llama_eval(
|
|
|
|
|
|
|
|
|
|
|
|
const int d_key = n_embd/n_head;
|
|
|
|
const int d_key = n_embd/n_head;
|
|
|
|
|
|
|
|
|
|
|
|
static size_t buf_size = 256u*1024*1024;
|
|
|
|
static size_t buf_size = 512u*1024*1024;
|
|
|
|
static void * buf = malloc(buf_size);
|
|
|
|
static void * buf = malloc(buf_size);
|
|
|
|
|
|
|
|
|
|
|
|
if (mem_per_token > 0 && mem_per_token*N > buf_size) {
|
|
|
|
if (mem_per_token > 0 && mem_per_token*N > buf_size) {
|
|
|
|