tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-05 13:53:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

refact : fix convert script + zero out KV cache to avoid nans (#3523)

Browse Source 
* refact : fix convert script + zero out KV cache to avoid nans

* ggml : silu(-inf) should never happen

* metal : assert various kernel requirements
This commit is contained in:
Georgi Gerganov
2023-10-09 14:32:17 +03:00
committed by GitHub
parent dcc09d2596
commit fcca0a7004
6 changed files with 51 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama.cpp
View File

@ -1325,7 +1325,11 @@ static bool llama_kv_cache_init(
cache.cells.clear();
cache.cells.resize(n_ctx);
// TODO: this should be:
// cache.buf.resize(2u*n_elements*ggml_type_size(wtype) + 2u*ggml_tensor_overhead());
// change it and test that it works
cache.buf.resize(2u*n_elements*ggml_type_size(wtype) + 2u*MB);
memset(cache.buf.data, 0, cache.buf.size);
struct ggml_init_params params;
params.mem_size = cache.buf.size;