Skip to content

Fixes for MLPerf inference, intel conda URL #491

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

Merged
arjunsuresh merged 7 commits into from
Nov 6, 2024
Merged

Fixes for MLPerf inference, intel conda URL #491

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
09fc291
Added an option to pull inference src changes for mlperf-inference
arjunsuresh Nov 6, 2024
9c6f5de
Added an option to pull inference src changes for mlperf-inference
arjunsuresh Nov 6, 2024
aa1c68a
Merge branch 'mlcommons:mlperf-inference' into mlperf-inference
arjunsuresh Nov 6, 2024
423e692
Fix diffuser version for SDXL reference implementation
arjunsuresh Nov 6, 2024
244952d
Update float16 name for SDXL model
arjunsuresh Nov 6, 2024
79e7cb5
Use http link for intel conda packages
arjunsuresh Nov 6, 2024
2e5eaec
Merge branch 'mlcommons:mlperf-inference' into mlperf-inference
arjunsuresh Nov 6, 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
2 changes: 1 addition & 1 deletion .github/workflows/test-nvidia-mlperf-implementation.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,5 +21,5 @@ jobs:
source gh_action/bin/activate
export CM_REPOS=$HOME/GH_CM
pip install --upgrade cm4mlops
cm run script --tags=run-mlperf,inference,_all-scenarios,_submission,_full,_r4.1-dev --preprocess_submission=yes --execution_mode=valid --gpu_name=rtx_4090 --pull_changes=yes --model=${{ matrix.model }} --submitter="MLCommons" --hw_name=RTX4090x2 --implementation=nvidia --backend=tensorrt --category=datacenter,edge --division=closed --docker_dt=yes --docker_it=no --docker_cm_repo=gateoverflow@cm4mlops --adr.compiler.tags=gcc --device=cuda --use_dataset_from_host=yes --results_dir=$HOME/gh_action_results --submission_dir=$HOME/gh_action_submissions --clean --docker --quiet
cm run script --tags=run-mlperf,inference,_all-scenarios,_submission,_full,_r4.1-dev --preprocess_submission=yes --execution_mode=valid --gpu_name=rtx_4090 --pull_changes=yes --pull_inference_changes=yes --model=${{ matrix.model }} --submitter="MLCommons" --hw_name=RTX4090x2 --implementation=nvidia --backend=tensorrt --category=datacenter,edge --division=closed --docker_dt=yes --docker_it=no --docker_cm_repo=gateoverflow@cm4mlops --adr.compiler.tags=gcc --device=cuda --use_dataset_from_host=yes --results_dir=$HOME/gh_action_results --submission_dir=$HOME/gh_action_submissions --clean --docker --quiet
cm run script --tags=push,github,mlperf,inference,submission --repo_url=https://github.com/gateoverflow/mlperf_inference_unofficial_submissions_v5.0 --repo_branch=main --commit_message="Results from GH action on NVIDIA_RTX4090x2" --quiet --submission_dir=$HOME/gh_action_submissions --hw_name=RTX4090x2
3 changes: 3 additions & 0 deletions script/app-mlperf-inference-mlcommons-python/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -394,6 +394,7 @@ deps:
names:
- ml-model
- sdxl-model
- ml-model-float16
enable_if_env:
CM_MODEL:
- stable-diffusion-xl
Expand Down Expand Up @@ -929,6 +930,8 @@ variations:
- tags: get,generic-python-lib,_package.diffusers
names:
- diffusers
version_max: "0.30.3"
version_max_usable: "0.30.3"
- tags: get,generic-python-lib,_package.transformers
names:
- transformers
Expand Down
7 changes: 6 additions & 1 deletion script/app-mlperf-inference/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,12 @@ deps:
- tags: get,mlcommons,inference,src
names:
- inference-src

- tags: pull,git,repo
env:
CM_GIT_CHECKOUT_PATH: '<<<CM_MLPERF_INFERENCE_SOURCE>>>'
enable_if_env:
CM_MLPERF_INFERENCE_PULL_SRC_CHANGES:
- 'yes'
- tags: get,mlperf,inference,utils

- tags: install,pip-package,for-cmind-python,_package.pandas
Expand Down
6 changes: 6 additions & 0 deletions script/install-generic-conda-package/_cm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,12 @@
"CM_CONDA_PKG_NAME": "#"
}
},
"source.intel": {
"group": "package-source",
"env": {
"CM_CONDA_PKG_SRC": "https://software.repos.intel.com/python/conda/"
}
},
"source.#": {
"group": "package-source",
"env": {
Expand Down
1 change: 1 addition & 0 deletions script/run-mlperf-inference-app/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,7 @@ input_mapping:
preprocess_submission: CM_RUN_MLPERF_SUBMISSION_PREPROCESSOR
push_to_github: CM_MLPERF_RESULT_PUSH_TO_GITHUB
pull_changes: CM_MLPERF_INFERENCE_PULL_CODE_CHANGES
pull_inference_changes: CM_MLPERF_INFERENCE_PULL_SRC_CHANGES
readme: CM_MLPERF_README
regenerate_accuracy_file: CM_MLPERF_REGENERATE_ACCURACY_FILE
regenerate_files: CM_REGENERATE_MEASURE_FILES
Expand Down