vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 10:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source
This commit is contained in:
Concedo 2023-04-22 00:19:50 +08:00
commit cee018960e
5 changed files with 260 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -2099,7 +2099,11 @@ void llama_set_kv_cache(
int n_token_count) {
// Make sure we have the same kv cache setup
LLAMA_ASSERT(ctx->model.kv_self.buf.size == n_size);
void * k_data = ctx->model.kv_self.k->data; // remember data pointers
void * v_data = ctx->model.kv_self.v->data; // because their value is stored in buf and overwritten by memcpy
memcpy(ctx->model.kv_self.buf.addr, kv_cache, n_size);
ctx->model.kv_self.k->data = k_data; // restore correct data pointers
ctx->model.kv_self.v->data = v_data;
ctx->model.kv_self.n = n_token_count;
}