root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

llama : use aligned memory during ggml_init call from loading saved sessions (#1934)

Browse Source 
* fixed issue: memory is not guaranteed to be aligned properly during ggml_init call from loading saved sessions

* - removed commented out old code from fix
- updated another instance of same issue below original
This commit is contained in:
l3utterfly 2023-06-19 23:20:06 +08:00 committed by GitHub
parent 23fc5c219a
commit ba4e85a833
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llama.cpp
View File

@ -3126,9 +3126,7 @@ size_t llama_copy_state_data(struct llama_context * ctx, uint8_t * dst) {
if (kv_size) {
const size_t elt_size = ggml_element_size(kv_self.k);
char buffer[4096];
ggml_context * cpy_ctx = ggml_init({ sizeof(buffer), buffer, /* no_alloc */ true });
ggml_context * cpy_ctx = ggml_init({ 4096, NULL, /* no_alloc */ true });
ggml_cgraph gf{};
gf.n_threads = 1;
@ -3234,9 +3232,7 @@ size_t llama_set_state_data(struct llama_context * ctx, uint8_t * src) {
const size_t elt_size = ggml_element_size(kv_self.k);
char buffer[4096];
ggml_context * cpy_ctx = ggml_init({ sizeof(buffer), buffer, /* no_alloc */ true });
ggml_context * cpy_ctx = ggml_init({ 4096, NULL, /* no_alloc */ true });
ggml_cgraph gf{};
gf.n_threads = 1;