CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-07 09:57:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

rebase to master (except ggml-cuda)

Browse Source
This commit is contained in:
slaren
2023-07-16 14:36:32 +02:00
parent 33ab185dd1
commit 9c72e7e916
5 changed files with 21 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llama.cpp
View File

@@ -1168,7 +1168,7 @@ static ggml_graph_splits llama_build_graph(
struct ggml_graph_splits splits = ggml_graph_split_init();
// initalize contexts for every backend
// initialize contexts for every backend
struct ggml_context * ctx_cpu = nullptr;
// TODO: don't create context if there are no CPU layers
@@ -1295,8 +1295,8 @@ static ggml_graph_splits llama_build_graph(
// TODO: replace with ggml_dependency / ggml_depends_on
k = ggml_view_tensor(ctx_kv, kv_self.k);
v = ggml_view_tensor(ctx_kv, kv_self.v);
k->src0 = k_cpy;
v->src0 = v_cpy;
k->src[0] = k_cpy;
v->src[0] = v_cpy;
}
struct ggml_tensor * Q =