mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-06 10:00:48 -05:00
ci : add CUDA save-load-state tests
ggml-ci
This commit is contained in:
@@ -336,7 +336,8 @@ function gg_run_open_llama_3b_v2 {
|
||||
|
||||
(time ./bin/imatrix --model ${model_f16} -f ${wiki_test_60} -c 128 -b 128 --chunks 1 ) 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 -fa --model ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
|
||||
|
||||
function check_ppl {
|
||||
qnt="$1"
|
||||
@@ -517,8 +518,10 @@ 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 -fa ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
|
||||
(time ./bin/save-load-state --model -ngl 10 ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
|
||||
(time ./bin/save-load-state --model -fa -ngl 10 ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
|
||||
(time ./bin/save-load-state --model -ngl 99 ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
|
||||
(time ./bin/save-load-state --model -fa -ngl 99 ${model_q4_0} ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log
|
||||
|
||||
function check_ppl {
|
||||
qnt="$1"
|
||||
|
||||
Reference in New Issue
Block a user