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

llama : support save/load state with FA enabled

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-04-25 18:18:13 +03:00
parent cb3547ac46
commit 1fd5bc3d5e
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
2 changed files with 12 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ci/run.sh
View file

@ -517,7 +517,8 @@ function gg_run_open_llama_7b_v2 {
(time ./bin/imatrix --model ${model_f16} -f ${wiki_test} -t 1 -ngl 999 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-imatrix.log
(time ./bin/save-load-state --model ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
(time ./bin/save-load-state --model ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
(time ./bin/save-load-state --model -fa ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
function check_ppl {
qnt="$1"