ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

main: allow preloading conversation with -p and add -st / --single-turn (#12145)

Browse source 
* Add chat template formatting to -no-cnv

* only enable prompt formatting if explicitly enabled

* add -st / --single-turn

* add --single-turn and -p in conversation mode

* fix -sys + -p

* reword warning

* small readability change and fix (long) outdated example usage

* only activate single turn in conversation mode
This commit is contained in:
Sigbjørn Skjæret 2025-03-04 17:19:39 +01:00 • committed by GitHub
parent 1a24c4621f
commit 56d7a9f812
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 52 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.h
View file

@ -328,6 +328,8 @@ struct common_params {
bool warmup = true; // warmup run
bool check_tensors = false; // validate tensor data
bool single_turn = false; // single turn chat conversation
ggml_type cache_type_k = GGML_TYPE_F16; // KV cache data type for the K
ggml_type cache_type_v = GGML_TYPE_F16; // KV cache data type for the V