Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[benchmark]add auto_pir case #8144

Merged
merged 1 commit into from
Mar 19, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=1
pp_degree=4
bs_item=16 # micro * dp * pp
fp_item=fp16O1
run_mode=DP2-MP1-PP4-SD2-stage1
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=1
level=o1
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=1
pp_degree=4
bs_item=16 # micro * dp * pp
fp_item=fp16O1
run_mode=DP2-MP1-PP4-SD2-stage2
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=2
level=o1
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=2
pp_degree=2
bs_item=16 # micro * dp * pp
fp_item=fp16O1
run_mode=DP2-MP2-PP2-SD2-stage1
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=1
level=o1
local_batch_size=8

model=gpt
micro_bs=4 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=2
pp_degree=2
bs_item=16 # micro * dp * pp
fp_item=fp16O1
run_mode=DP2-MP2-PP2-SD2-stage2
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=2
level=o1
local_batch_size=8

model=gpt
micro_bs=4 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=1
pp_degree=4
bs_item=16 # micro * dp * pp
fp_item=fp16O2
run_mode=DP2-MP1-PP4-SD2-stage1
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=1
level=o2
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=1
pp_degree=4
bs_item=16 # micro * dp * pp
fp_item=fp16O2
run_mode=DP2-MP1-PP4-SD2-stage2
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=2
level=o2
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=2
pp_degree=2
bs_item=16 # micro * dp * pp
fp_item=fp16O2
run_mode=DP2-MP2-PP2-SD2-stage1
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=1
level=o2
local_batch_size=8

model=gpt
micro_bs=4 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=2
pp_degree=2
bs_item=16 # micro * dp * pp
fp_item=fp16O2
run_mode=DP2-MP2-PP2-SD2-stage2
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=2
level=o2
local_batch_size=8

model=gpt
micro_bs=4 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=1
pp_degree=4
bs_item=16 # micro * dp * pp
fp_item=fp16O3
run_mode=DP2-MP1-PP4-SD2-stage1
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=1
level=o3
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=1
pp_degree=4
bs_item=16 # micro * dp * pp
fp_item=fp16O3
run_mode=DP2-MP1-PP4-SD2-stage2
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=2
level=o3
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=2
pp_degree=2
bs_item=16 # micro * dp * pp
fp_item=fp16O3
run_mode=DP2-MP2-PP2-SD2-stage1
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=1
level=o3
local_batch_size=8

model=gpt
micro_bs=4 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=2
mp_degree=2
pp_degree=2
bs_item=16 # micro * dp * pp
fp_item=fp16O3
run_mode=DP2-MP2-PP2-SD2-stage2
device_num=N1C8
sharding_degree=2 # sharding_degree = dp_degree
sharding_stage=2
level=o3
local_batch_size=8

model=gpt
micro_bs=4 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=1
mp_degree=1
pp_degree=8
bs_item=8 # micro * dp * pp
fp_item=fp16O1
run_mode=DP1-MP1-PP8-SD1-stage1
device_num=N1C8
sharding_degree=1
sharding_stage=1
level=o1
local_batch_size=8

model=gpt
micro_bs=1 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=1
mp_degree=2
pp_degree=4
bs_item=8 # micro * dp * pp
fp_item=fp16O1
run_mode=DP1-MP2-PP4-SD1-stage1
device_num=N1C8
sharding_degree=1 # sharding_degree = dp_degree
sharding_stage=1
level=o1
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=1
mp_degree=1
pp_degree=8
bs_item=8 # micro * dp * pp
fp_item=fp16O2
run_mode=DP1-MP1-PP8-SD1-stage1
device_num=N1C8
sharding_degree=1
sharding_stage=1
level=o2
local_batch_size=8

model=gpt
micro_bs=1 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=1
mp_degree=2
pp_degree=4
bs_item=8 # micro * dp * pp
fp_item=fp16O2
run_mode=DP1-MP2-PP4-SD1-stage1
device_num=N1C8
sharding_degree=1 # sharding_degree = dp_degree
sharding_stage=1
level=o2
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=1
mp_degree=1
pp_degree=8
bs_item=8 # micro * dp * pp
fp_item=fp16O3
run_mode=DP1-MP1-PP8-SD1-stage1
device_num=N1C8
sharding_degree=1
sharding_stage=1
level=o3
local_batch_size=8

model=gpt
micro_bs=1 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
model_item=gpt_auto_pir
dp_degree=1
mp_degree=2
pp_degree=4
bs_item=8 # micro * dp * pp
fp_item=fp16O3
run_mode=DP1-MP2-PP4-SD1-stage1
device_num=N1C8
sharding_degree=1 # sharding_degree = dp_degree
sharding_stage=1
level=o3
local_batch_size=8

model=gpt
micro_bs=2 # local_batch_size / pp_degree

cd ./benchmarks
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/prepare.sh
# run
bash ./test_tipc/gpt/static/new_exec_pp_pir/benchmark_common/run_benchmark.sh ${model_item} ${fp_item} ${dp_degree} ${mp_degree} ${pp_degree} ${micro_bs} ${bs_item} ${run_mode} ${device_num} \
${sharding_degree} ${sharding_stage} ${level} 2>&1;
Loading
Loading