generated from mlcommons/mlperf_inference_submissions
-
Notifications
You must be signed in to change notification settings - Fork 5
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Results from self hosted Github actions
- Loading branch information
1 parent
96b262a
commit 994758b
Showing
24 changed files
with
9,924 additions
and
0 deletions.
There are no files selected for viewing
3 changes: 3 additions & 0 deletions
3
...ns/measurements/gh_action-reference-cpu-pytorch_v2.5.1-default_config/README.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,3 @@ | ||
| | Model | Scenario | Accuracy | Throughput | Latency (in ms) | | ||
| |---------------|------------|------------------------------------|--------------|-------------------| | ||
| | llama2-70b-99 | offline | (61.7021, 37.9679, 39.3617, 610.0) | 0.4 | - | |
110 changes: 110 additions & 0 deletions
110
...ion-reference-cpu-pytorch_v2.5.1-default_config/llama2-70b-99/offline/README.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,110 @@ | ||
| *Check [CM MLPerf docs](https://docs.mlcommons.org/inference) for more details.* | ||
|
|
||
| ## Host platform | ||
|
|
||
| * OS version: Linux-6.8.0-49-generic-x86_64-with-glibc2.35 | ||
| * CPU version: x86_64 | ||
| * Python version: 3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0] | ||
| * MLCommons CM version: 3.5.2 | ||
|
|
||
| ## CM Run Command | ||
|
|
||
| See [CM installation guide](https://docs.mlcommons.org/inference/install/). | ||
|
|
||
| ```bash | ||
| pip install -U cmind | ||
|
|
||
| cm rm cache -f | ||
|
|
||
| cm pull repo gateoverflow@mlperf-automations --checkout=976c9274c443e08307b418cb10fa995b354ff021 | ||
|
|
||
| cm run script \ | ||
| --tags=app,mlperf,inference,generic,_reference,_llama2-70b-99,_pytorch,_cpu,_test,_r5.0-dev_default,_bfloat16,_offline \ | ||
| --quiet=true \ | ||
| --env.CM_MLPERF_MODEL_LLAMA2_70B_DOWNLOAD_TO_HOST=yes \ | ||
| --env.CM_QUIET=yes \ | ||
| --env.CM_MLPERF_IMPLEMENTATION=reference \ | ||
| --env.CM_MLPERF_MODEL=llama2-70b-99 \ | ||
| --env.CM_MLPERF_RUN_STYLE=test \ | ||
| --env.CM_MLPERF_SKIP_SUBMISSION_GENERATION=False \ | ||
| --env.CM_DOCKER_PRIVILEGED_MODE=True \ | ||
| --env.CM_MLPERF_SUBMISSION_DIVISION=open \ | ||
| --env.CM_MLPERF_INFERENCE_TP_SIZE=1 \ | ||
| --env.CM_MLPERF_BACKEND=pytorch \ | ||
| --env.CM_MLPERF_SUBMISSION_SYSTEM_TYPE=datacenter \ | ||
| --env.CM_MLPERF_CLEAN_ALL=True \ | ||
| --env.CM_MLPERF_DEVICE=cpu \ | ||
| --env.CM_MLPERF_USE_DOCKER=True \ | ||
| --env.CM_HW_NAME=gh_action \ | ||
| --env.CM_MLPERF_MODEL_PRECISION=bfloat16 \ | ||
| --env.CM_MLPERF_INFERENCE_PULL_CODE_CHANGES=yes \ | ||
| --env.CM_MLPERF_INFERENCE_PULL_SRC_CHANGES=yes \ | ||
| --env.OUTPUT_BASE_DIR=/cm-mount/home/arjun/gh_action_results \ | ||
| --env.CM_MLPERF_LOADGEN_SCENARIO=Offline \ | ||
| --env.CM_MLPERF_INFERENCE_SUBMISSION_DIR=/cm-mount/home/arjun/gh_action_submissions \ | ||
| --env.CM_MLPERF_SUBMITTER=MLCommons \ | ||
| --env.CM_MLPERF_LOADGEN_TARGET_QPS=0.001 \ | ||
| --env.CM_TEST_QUERY_COUNT=1 \ | ||
| --env.CM_MLPERF_LOADGEN_COMPLIANCE=no \ | ||
| --env.CM_MLPERF_SUBMISSION_RUN=yes \ | ||
| --env.CM_RUN_MLPERF_ACCURACY=on \ | ||
| --env.CM_RUN_SUBMISSION_CHECKER=yes \ | ||
| --env.CM_TAR_SUBMISSION_DIR=yes \ | ||
| --env.CM_RUN_MLPERF_SUBMISSION_PREPROCESSOR=False \ | ||
| --env.CM_MLPERF_SUBMISSION_GENERATION_STYLE=short \ | ||
| --env.CM_MLPERF_LOADGEN_ALL_MODES=yes \ | ||
| --env.CM_MLPERF_INFERENCE_VERSION=5.0-dev \ | ||
| --env.CM_RUN_MLPERF_INFERENCE_APP_DEFAULTS=r5.0-dev_default \ | ||
| --env.CM_MLPERF_SUBMISSION_CHECKER_VERSION=v5.0 \ | ||
| --env.CM_MLPERF_INFERENCE_SOURCE_VERSION=5.0.4 \ | ||
| --env.CM_MLPERF_LAST_RELEASE=v5.0 \ | ||
| --env.CM_TMP_PIP_VERSION_STRING= \ | ||
| --env.CM_MODEL=llama2-70b-99 \ | ||
| --env.CM_MLPERF_CLEAN_SUBMISSION_DIR=yes \ | ||
| --env.CM_RERUN=yes \ | ||
| --env.CM_MLPERF_LOADGEN_EXTRA_OPTIONS= \ | ||
| --env.CM_MLPERF_LOADGEN_MODE=performance \ | ||
| --env.CM_MLPERF_LOADGEN_SCENARIOS,=Offline \ | ||
| --env.CM_MLPERF_LOADGEN_MODES,=performance,accuracy \ | ||
| --env.CM_OUTPUT_FOLDER_NAME=test_results \ | ||
| --env.CM_DOCKER_REUSE_EXISTING_CONTAINER=no \ | ||
| --env.CM_DOCKER_DETACHED_MODE=yes \ | ||
| --add_deps_recursive.compiler.tags=gcc \ | ||
| --add_deps_recursive.submission-checker.tags=_short-run \ | ||
| --add_deps_recursive.get-mlperf-inference-results-dir.tags=_version.r5.0-dev \ | ||
| --add_deps_recursive.get-mlperf-inference-submission-dir.tags=_version.r5.0-dev \ | ||
| --add_deps_recursive.mlperf-inference-nvidia-scratch-space.tags=_version.r5.0-dev \ | ||
| --adr.compiler.tags=gcc \ | ||
| --adr.submission-checker.tags=_short-run \ | ||
| --adr.get-mlperf-inference-results-dir.tags=_version.r5.0-dev \ | ||
| --adr.get-mlperf-inference-submission-dir.tags=_version.r5.0-dev \ | ||
| --adr.mlperf-inference-nvidia-scratch-space.tags=_version.r5.0-dev \ | ||
| --v=False \ | ||
| --print_env=False \ | ||
| --print_deps=False \ | ||
| --dump_version_info=True | ||
| ``` | ||
| *Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf (CM scripts), | ||
| you should simply reload gateoverflow@mlperf-automations without checkout and clean CM cache as follows:* | ||
|
|
||
| ```bash | ||
| cm rm repo gateoverflow@mlperf-automations | ||
| cm pull repo gateoverflow@mlperf-automations | ||
| cm rm cache -f | ||
|
|
||
| ``` | ||
|
|
||
| ## Results | ||
|
|
||
| Platform: gh_action-reference-cpu-pytorch_v2.5.1-default_config | ||
|
|
||
| Model Precision: fp32 | ||
|
|
||
| ### Accuracy Results | ||
| `ROUGE1`: `61.7021`, Required accuracy for closed division `>= 43.98689` | ||
| `ROUGE2`: `37.9679`, Required accuracy for closed division `>= 21.81485` | ||
| `ROUGEL`: `39.3617`, Required accuracy for closed division `>= 28.33004` | ||
| `TOKENS_PER_SAMPLE`: `610.0`, Required accuracy for closed division `>= 265.005` and `<= 323.895` | ||
|
|
||
| ### Performance Results | ||
| `Samples per second`: `0.400375` |
28 changes: 28 additions & 0 deletions
28
...on-reference-cpu-pytorch_v2.5.1-default_config/llama2-70b-99/offline/accuracy_console.out
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
92 changes: 92 additions & 0 deletions
92
...s/gh_action-reference-cpu-pytorch_v2.5.1-default_config/llama2-70b-99/offline/cm-deps.mmd
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,92 @@ | ||
| graph TD | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_llama2-70b-99,_pytorch,_cpu,_test,_r5.0-dev_default,_bfloat16,_offline_) --> detect,os | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_llama2-70b-99,_pytorch,_cpu,_test,_r5.0-dev_default,_bfloat16,_offline_) --> get,sys-utils-cm | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_llama2-70b-99,_pytorch,_cpu,_test,_r5.0-dev_default,_bfloat16,_offline_) --> get,python | ||
| get-mlperf-inference-src,4b57186581024797 --> detect,os | ||
| get-mlperf-inference-src,4b57186581024797 --> get,python3 | ||
| get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_llama2-70b-99,_pytorch,_cpu,_test,_r5.0-dev_default,_bfloat16,_offline_) --> get,mlcommons,inference,src | ||
| pull-git-repo,c23132ed65c4421d --> detect,os | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_llama2-70b-99,_pytorch,_cpu,_test,_r5.0-dev_default,_bfloat16,_offline_) --> pull,git,repo | ||
| get-mlperf-inference-src,4b57186581024797 --> detect,os | ||
| get-mlperf-inference-src,4b57186581024797 --> get,python3 | ||
| get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference | ||
| get-mlperf-inference-utils,e341e5f86d8342e5 --> get,mlperf,inference,src | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_llama2-70b-99,_pytorch,_cpu,_test,_r5.0-dev_default,_bfloat16,_offline_) --> get,mlperf,inference,utils | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> detect,os | ||
| detect-cpu,586c8a43320142f7 --> detect,os | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> detect,cpu | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,sys-utils-cm | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,python | ||
| get-generic-python-lib,94b62a682bc44791_(_torch_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_torch | ||
| get-generic-python-lib,94b62a682bc44791_(_torchvision_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_torchvision | ||
| get-ml-model-huggingface-zoo,53cf8252a443446a_(_clone-repo,_model-stub.meta-llama/Llama-2-70b-chat-hf_) --> get,python3 | ||
| get-generic-python-lib,94b62a682bc44791_(_huggingface_hub_) --> detect,os | ||
| detect-cpu,586c8a43320142f7 --> detect,os | ||
| get-generic-python-lib,94b62a682bc44791_(_huggingface_hub_) --> detect,cpu | ||
| get-generic-python-lib,94b62a682bc44791_(_huggingface_hub_) --> get,python3 | ||
| get-generic-python-lib,94b62a682bc44791_(_pip_) --> get,python3 | ||
| get-generic-python-lib,94b62a682bc44791_(_huggingface_hub_) --> get,generic-python-lib,_pip | ||
| get-ml-model-huggingface-zoo,53cf8252a443446a_(_clone-repo,_model-stub.meta-llama/Llama-2-70b-chat-hf_) --> get,generic-python-lib,_huggingface_hub | ||
| get-ml-model-huggingface-zoo,53cf8252a443446a_(_clone-repo,_model-stub.meta-llama/Llama-2-70b-chat-hf_) --> get,git,repo,_lfs,_repo.https://huggingface.co/meta-llama/Llama-2-70b-chat-hf | ||
| get-ml-model-llama2,5db97be9f61244c6_(_pytorch_) --> get,ml-model,huggingface,zoo,_clone-repo,_model-stub.meta-llama/Llama-2-70b-chat-hf | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,ml-model,llama2,raw,_pytorch | ||
| get-preprocessed-dataset-openorca,5614c39cb1564d72_(_validation,_mlcommons_) --> get,sys-utils-cm | ||
| get-preprocessed-dataset-openorca,5614c39cb1564d72_(_validation,_mlcommons_) --> get,python3 | ||
| get-generic-python-lib,94b62a682bc44791_(_package.pyarrow_) --> get,python3 | ||
| get-preprocessed-dataset-openorca,5614c39cb1564d72_(_validation,_mlcommons_) --> get,generic-python-lib,_package.pyarrow | ||
| get-generic-python-lib,94b62a682bc44791_(_package.fastparquet_) --> get,python3 | ||
| get-preprocessed-dataset-openorca,5614c39cb1564d72_(_validation,_mlcommons_) --> get,generic-python-lib,_package.fastparquet | ||
| get-generic-python-lib,94b62a682bc44791_(_package.transformers_) --> get,python3 | ||
| get-preprocessed-dataset-openorca,5614c39cb1564d72_(_validation,_mlcommons_) --> get,generic-python-lib,_package.transformers | ||
| get-preprocessed-dataset-openorca,5614c39cb1564d72_(_validation,_mlcommons_) --> download-and-extract,_rclone,_url.mlc-inference:mlcommons-inference-wg-public/open_orca | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,preprocessed,dataset,openorca,_validation,_mlcommons | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> detect,os | ||
| detect-cpu,586c8a43320142f7 --> detect,os | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> detect,cpu | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> get,python | ||
| get-mlperf-inference-src,4b57186581024797 --> detect,os | ||
| get-mlperf-inference-src,4b57186581024797 --> get,python3 | ||
| get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> get,mlcommons,inference,src | ||
| get-mlperf-inference-sut-configs,c2fbf72009e2445b --> get,cache,dir,_name.mlperf-inference-sut-configs | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> get,sut,configs | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> generate,user-conf,mlperf,inference | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,loadgen | ||
| get-mlperf-inference-src,4b57186581024797 --> detect,os | ||
| get-mlperf-inference-src,4b57186581024797 --> get,python3 | ||
| get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,mlcommons,inference,src | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,mlcommons,inference,src | ||
| get-generic-python-lib,94b62a682bc44791_(_package.psutil_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.psutil | ||
| get-generic-python-lib,94b62a682bc44791_(_package.transformers_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.transformers | ||
| get-generic-python-lib,94b62a682bc44791_(_package.datasets_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.datasets | ||
| get-generic-python-lib,94b62a682bc44791_(_package.sentencepiece_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.sentencepiece | ||
| get-generic-python-lib,94b62a682bc44791_(_package.protobuf_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.protobuf | ||
| get-generic-python-lib,94b62a682bc44791_(_package.accelerate_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.accelerate | ||
| get-generic-python-lib,94b62a682bc44791_(_package.absl-py_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.absl-py | ||
| get-generic-python-lib,94b62a682bc44791_(_package.evaluate_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.evaluate | ||
| get-generic-python-lib,94b62a682bc44791_(_package.nltk_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.nltk | ||
| get-generic-python-lib,94b62a682bc44791_(_package.numpy_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.numpy | ||
| get-generic-python-lib,94b62a682bc44791_(_package.rouge-score_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.rouge-score | ||
| get-generic-python-lib,94b62a682bc44791_(_package.more-itertools_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.more-itertools | ||
| get-generic-python-lib,94b62a682bc44791_(_package.compressed_tensors_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> get,generic-python-lib,_package.compressed_tensors | ||
| detect-cpu,586c8a43320142f7 --> detect,os | ||
| benchmark-program,19f369ef47084895 --> detect,cpu | ||
| benchmark-program-mlperf,cfff0132a8aa4018 --> benchmark-program,program | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_offline,_cpu,_llama2-70b-99,_pytorch,_bfloat16_) --> benchmark-mlperf |
Binary file added
BIN
+4.91 MB
...n-reference-cpu-pytorch_v2.5.1-default_config/llama2-70b-99/offline/cm-deps.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Oops, something went wrong.