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

Be nice to CI machines by not allocating buffers

Browse source 
...for vocab_only=true
This commit is contained in:
Stephan Walter 2023-04-01 17:00:01 +02:00
parent d0a7f742e7
commit 3ef747808a
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -1608,7 +1608,7 @@ struct llama_context * llama_init_from_file(
}
// reserve memory for context buffers
{
if (!params.vocab_only) {
if (!kv_cache_init(ctx->model.hparams, ctx->model.kv_self, memory_type, ctx->model.hparams.n_ctx)) {
fprintf(stderr, "%s: kv_cache_init() failed for self-attention cache\n", __func__);
llama_free(ctx);