vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix CI: ARM NEON, quantization unit tests, editorconfig (#1122)

Browse source
This commit is contained in:
Stephan Walter 2023-04-22 10:54:13 +00:00 • committed by GitHub
parent 5f939498d5
commit c50b628810
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 11 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.cpp
View file

@ -2256,7 +2256,6 @@ std::vector<std::pair<std::string, struct ggml_tensor *>>& llama_internal_get_te
// Returns the size of the state
size_t llama_get_state_size(struct llama_context * ctx) {
const size_t s_bool = sizeof(int32_t);
// we don't know size of rng until we actually serialize it. so reserve more than enough memory for its serialized state.
// for reference, std::mt19937(1337) serializes to 6701 bytes.
const size_t s_rng_size = sizeof(size_t);