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.

Sign up for GitHub

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

Jump to bottom

Merge from GO #142

Merged
merged 5 commits into from
Jul 26, 2024
Merged

Merge from GO #142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a9b8aea
fix pycuda version for nvidia implementation
arjunsuresh Jul 26, 2024
e4f4ca0
fix pycuda version for nvidia implementation
arjunsuresh Jul 26, 2024
3d5cd59
Fix for submission checker on file paths with spaces
arjunsuresh Jul 26, 2024
787b72f
fixes for run-pruned-bert script
arjunsuresh Jul 26, 2024
88b66b1
Merge branch 'mlcommons:mlperf-inference' into mlperf-inference
arjunsuresh Jul 26, 2024
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
3 changes: 3 additions & 0 deletions script/app-mlperf-inference-nvidia/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -262,6 +262,9 @@ deps:
CM_MLPERF_NVIDIA_HARNESS_RUN_MODE:
- run_harness

- tags: get,generic-python-lib,_package.pycuda
version: "2022.2.2"

- tags: get,generic-python-lib,_package.nvmitten
update_tags_from_env_with_prefix:
_path.:
Expand Down
1 change: 1 addition & 0 deletions script/build-mlperf-inference-server-nvidia/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,7 @@ deps:

# Detect pycuda
- tags: get,generic-python-lib,_pycuda
version: "2022.2.2"
skip_if_env:
CM_RUN_STATE_DOCKER:
- 'yes'
Expand Down
3 changes: 2 additions & 1 deletion script/get-nvidia-mitten/_cm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,8 @@
"tags": "get,python3"
},
{
"tags": "get,generic-python-lib,_pycuda"
"tags": "get,generic-python-lib,_pycuda",
"version": "2022.2.2"
},
{
"tags": "get,git,_repo.https://github.com/NVIDIA/mitten",
Expand Down
6 changes: 2 additions & 4 deletions script/run-all-mlperf-models/run-pruned-bert.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,10 +38,10 @@ rerun=""
power=" --power=yes --adr.mlperf-power-client.power_server=192.168.0.15 --env.CM_MLPERF_SKIP_POWER_CHECKS=yes"
power=" --power=yes --adr.mlperf-power-client.power_server=192.168.0.15"
power=""
max_batchsize=128
max_batchsize=1
scenario="Offline"
max_batchsize=128
scenario="SingleStream"
scenario="Offline"

if [[ $scenario == "Offline" ]]; then
for stub in ${zoo_stub_list[@]}; do
Expand All @@ -55,7 +55,6 @@ cmd="cm run script --tags=run,mlperf,inference,generate-run-cmds,_find-performan
--scenario=Offline \
--test_query_count=15000 \
--adr.mlperf-inference-implementation.max_batchsize=$max_batchsize \
--results_dir=$HOME/results_dir \
--env.CM_MLPERF_NEURALMAGIC_MODEL_ZOO_STUB=$stub \
${rerun} \
--quiet"
Expand All @@ -77,7 +76,6 @@ for stub in ${zoo_stub_list[@]}; do
--execution_mode=valid \
--adr.mlperf-inference-implementation.max_batchsize=$max_batchsize \
${power} \
--results_dir=$HOME/results_dir \
--env.CM_MLPERF_NEURALMAGIC_MODEL_ZOO_STUB=$stub \
--quiet"
echo ${cmd}
Expand Down
5 changes: 3 additions & 2 deletions script/run-mlperf-inference-submission-checker/customize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,15 +53,16 @@ def preprocess(i):

x_version = ' --version ' + version +' ' if version!='' else ''

CMD = env['CM_PYTHON_BIN_WITH_PATH'] + ' ' + submission_checker_file + ' --input "' + submission_dir + '"' + \
CMD = env['CM_PYTHON_BIN_WITH_PATH'] + ' \'' + submission_checker_file + '\' --input \'' + submission_dir + '\'' + \
x_submitter + \
x_version + \
skip_compliance + extra_map + power_check + extra_args

report_generator_file = os.path.join(env['CM_MLPERF_INFERENCE_SOURCE'], "tools", "submission",
"generate_final_report.py")
env['CM_RUN_CMD'] = CMD
env['CM_POST_RUN_CMD'] = env['CM_PYTHON_BIN_WITH_PATH'] + ' ' + report_generator_file + ' --input summary.csv'
print(CMD)
env['CM_POST_RUN_CMD'] = env['CM_PYTHON_BIN_WITH_PATH'] + ' \'' + report_generator_file + '\' --input summary.csv'

return {'return':0}

Expand Down
Loading