Skip to content

Improvements for reproducing AMD implementation #379

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 8 commits into from
Oct 16, 2024
Merged

Improvements for reproducing AMD implementation #379

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
79a911d
changed inference_submission -> inference_result repo
anandhu-eng Oct 16, 2024
5f36860
Added 4.1 default version
anandhu-eng Oct 16, 2024
fa2eacf
fix syntax error
anandhu-eng Oct 16, 2024
edbc0ed
fix typo
anandhu-eng Oct 16, 2024
55cd121
added echo and run commands
anandhu-eng Oct 16, 2024
fcc1249
removed test command as -xeu is set
anandhu-eng Oct 16, 2024
898a564
use cm-code-only as branch
anandhu-eng Oct 16, 2024
5d8d11a
clone cm-code-only branch
anandhu-eng Oct 16, 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
9 changes: 7 additions & 2 deletions script/app-mlperf-inference-amd/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -255,8 +255,8 @@ variations:
- tags: get,generic-python-lib,_package.vllm
names:
- vllm
- tags: get,git,repo,_repo.https://github.com/mlcommons/submissions_inference_v4.1
extra_cache_tags: inference,submissions
- tags: get,git,repo,_repo.https://github.com/mlcommons/inference_results_v4.1,_branch.cm-code-only
extra_cache_tags: inference,results
env:
CM_GIT_CHECKOUT_PATH_ENV_NAME: CM_MLPERF_INFERENCE_RESULTS_PATH

Expand Down Expand Up @@ -315,5 +315,10 @@ variations:
env:
CM_MLPERF_INFERENCE_RESULTS_REPO: https://github.com/mlcommons/inference_results_v4.0

r4.1_default:
group: version
env:
CM_MLPERF_INFERENCE_RESULTS_REPO: https://github.com/mlcommons/inference_results_v4.1

docker:
real_run: False
8 changes: 6 additions & 2 deletions script/app-mlperf-inference-amd/run-llama2.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,8 +33,8 @@ LOG_DIR=${CM_MLPERF_OUTPUT_DIR}

cp $USER_CONF ${LOG_DIR}/user.conf

cmd ="${CM_PYTHON_BIN_WITH_PATH} ${CM_MLPERF_AMD_LLAMA2_CODE_PATH}/mainVllmFp8_Offline.py \
--scenario ${CM_MLPERF_LOADGEN_SCENARIO \
cmd="${CM_PYTHON_BIN_WITH_PATH} ${CM_MLPERF_AMD_LLAMA2_CODE_PATH}/mainVllmFp8_Offline.py \
--scenario ${CM_MLPERF_LOADGEN_SCENARIO} \
--output-log-dir ${LOG_DIR} \
--model-path $MODEL_PATH \
--mlperf-conf $MLPERF_CONF \
Expand All @@ -54,3 +54,7 @@ cmd ="${CM_PYTHON_BIN_WITH_PATH} ${CM_MLPERF_AMD_LLAMA2_CODE_PATH}/mainVllmFp8_O
--sorting ${SORTING} \
--enforce-eager True \
--gpu-memory-utilization 0.99"

echo "${cmd}"
# uncomment the below lines for testing
#eval "${cmd}"
4 changes: 2 additions & 2 deletions script/get-ml-model-llama2/_cm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,8 +174,8 @@
"tags": "get,preprocessed,dataset,openorca,_calibration,_mlc"
},
{
"tags": "get,git,repo,_repo.https://github.com/mlcommons/submissions_inference_v4.1",
"extra_cache_tags": "inference,submissions",
"tags": "get,git,repo,_repo.https://github.com/mlcommons/inference_results_v4.1,_branch.cm-code-only",
"extra_cache_tags": "inference,results",
"env": {
"CM_GIT_CHECKOUT_PATH_ENV_NAME": "CM_MLPERF_INFERENCE_RESULTS_PATH"
}
Expand Down