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

rebase to new embed

Browse source
This commit is contained in:
Douglas Hanley 2024-03-05 23:23:17 -06:00
parent 805ae529c4
commit 97936078b7
3 changed files with 18 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.h
View file

@ -262,6 +262,7 @@ extern "C" {
bool logits_all; // the llama_decode() call computes all logits, not just the last one (DEPRECATED - set llama_batch.logits instead)
bool embeddings; // if true, extract embeddings (together with logits)
bool offload_kqv; // whether to offload the KQV ops (including the KV cache) to GPU
bool causal_attn; // whether to use causal attention
// Abort callback
// if it returns true, execution of llama_decode() will be aborted