@@ -386,10 +386,10 @@ function gg_run_open_llama_7b_v2 {
386
386
387
387
(time ./bin/llama-imatrix --model ${model_f16} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT /${ci} -imatrix.log
388
388
389
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 0 ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
390
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 0 -fa ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
391
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
392
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
389
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 0 -fa off ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
390
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 0 -fa on ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
391
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa off ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
392
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa on ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
393
393
394
394
function check_ppl {
395
395
qnt=" $1 "
@@ -520,8 +520,8 @@ function gg_run_pythia_1_4b {
520
520
521
521
(time ./bin/llama-imatrix --model ${model_f16} -f ${wiki_test_60} -ngl 99 -c 128 -b 128 --chunks 1 ) 2>&1 | tee -a $OUT /${ci} -imatrix.log
522
522
523
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
524
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
523
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa off ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
524
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa on ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
525
525
526
526
function check_ppl {
527
527
qnt=" $1 "
@@ -651,10 +651,10 @@ function gg_run_pythia_2_8b {
651
651
652
652
(time ./bin/llama-imatrix --model ${model_f16} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT /${ci} -imatrix.log
653
653
654
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 0 ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
655
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 0 -fa ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
656
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
657
- (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
654
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 0 -fa off ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
655
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 0 -fa on ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
656
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa off ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
657
+ (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 0 -fa on ) 2>&1 | tee -a $OUT /${ci} -save-load-state.log
658
658
659
659
function check_ppl {
660
660
qnt=" $1 "
0 commit comments