Skip to content

Remove hugectr test #771

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
jperez999 merged 2 commits into from
Dec 20, 2022
Merged

Remove hugectr test #771

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4b000d1
remove hugectr test
jperez999 Dec 20, 2022
4a7b3d0
adding tf gpu allocator env var
jperez999 Dec 20, 2022
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
158 changes: 79 additions & 79 deletions tests/unit/examples/test_scaling_criteo_merlin_models_hugectr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,93 +1,93 @@
import os
# import os

import pytest
from testbook import testbook
from tests.conftest import REPO_ROOT
# from testbook import testbook
# from tests.conftest import REPO_ROOT

pytest.importorskip("hugectr")


def test_test_scaling_criteo_merlin_models_hugectr():
with testbook(
REPO_ROOT / "examples" / "scaling-criteo" / "02-ETL-with-NVTabular.ipynb",
execute=False,
timeout=180,
) as tb1:
tb1.inject(
"""
import os
os.environ["BASE_DIR"] = "/tmp/test_merlin_criteo_hugectr/input/criteo/"
os.environ["INPUT_DATA_DIR"] = "/tmp/test_merlin_criteo_hugectr/input/criteo/"
os.environ["OUTPUT_DATA_DIR"] = "/tmp/test_merlin_criteo_hugectr/output/criteo/"
os.environ["USE_HUGECTR"] = "True"
# def test_test_scaling_criteo_merlin_models_hugectr():
# with testbook(
# REPO_ROOT / "examples" / "scaling-criteo" / "02-ETL-with-NVTabular.ipynb",
# execute=False,
# timeout=180,
# ) as tb1:
# tb1.inject(
# """
# import os
# os.environ["BASE_DIR"] = "/tmp/test_merlin_criteo_hugectr/input/criteo/"
# os.environ["INPUT_DATA_DIR"] = "/tmp/test_merlin_criteo_hugectr/input/criteo/"
# os.environ["OUTPUT_DATA_DIR"] = "/tmp/test_merlin_criteo_hugectr/output/criteo/"
# os.environ["USE_HUGECTR"] = "True"

os.system("mkdir -p /tmp/test_merlin_criteo_hugectr/input/criteo")
os.system("mkdir -p /tmp/test_merlin_criteo_hugectr/output/criteo/")
# os.system("mkdir -p /tmp/test_merlin_criteo_hugectr/input/criteo")
# os.system("mkdir -p /tmp/test_merlin_criteo_hugectr/output/criteo/")

from merlin.datasets.synthetic import generate_data
# from merlin.datasets.synthetic import generate_data

train, valid = generate_data("criteo", int(100000), set_sizes=(0.7, 0.3))
# train, valid = generate_data("criteo", int(100000), set_sizes=(0.7, 0.3))

train.to_ddf().compute().to_parquet('/tmp/test_merlin_criteo_hugectr/input/criteo/day_0.parquet')
valid.to_ddf().compute().to_parquet('/tmp/test_merlin_criteo_hugectr/input/criteo/day_1.parquet')
"""
)
tb1.execute()
assert os.path.isfile("/tmp/test_merlin_criteo_hugectr/output/criteo/train/part_0.parquet")
assert os.path.isfile("/tmp/test_merlin_criteo_hugectr/output/criteo/valid/part_0.parquet")
assert os.path.isfile("/tmp/test_merlin_criteo_hugectr/output/criteo/workflow/metadata.json")
# train.to_ddf().compute().to_parquet('/tmp/test_merlin_criteo_hugectr/input/criteo/day_0.parquet')
# valid.to_ddf().compute().to_parquet('/tmp/test_merlin_criteo_hugectr/input/criteo/day_1.parquet')
# """
# )
# tb1.execute()
# assert os.path.isfile("/tmp/test_merlin_criteo_hugectr/output/criteo/train/part_0.parquet")
# assert os.path.isfile("/tmp/test_merlin_criteo_hugectr/output/criteo/valid/part_0.parquet")
# assert os.path.isfile("/tmp/test_merlin_criteo_hugectr/output/criteo/workflow/metadata.json")

with testbook(
REPO_ROOT
/ "examples"
/ "scaling-criteo"
/ "03-Training-with-HugeCTR.ipynb",
execute=False,
timeout=360,
) as tb2:
tb2.inject(
"""
import os
os.environ["OUTPUT_DATA_DIR"] = "/tmp/test_merlin_criteo_hugectr/output/criteo/"
"""
)
tb2.execute()
assert os.path.isfile(os.path.join('/tmp/test_merlin_criteo_hugectr/output/criteo/', "criteo_hugectr/1/", "criteo.json"))
# with testbook(
# REPO_ROOT
# / "examples"
# / "scaling-criteo"
# / "03-Training-with-HugeCTR.ipynb",
# execute=False,
# timeout=180,
# ) as tb2:
# tb2.inject(
# """
# import os
# os.environ["OUTPUT_DATA_DIR"] = "/tmp/test_merlin_criteo_hugectr/output/criteo/"
# """
# )
# tb2.execute()
# assert os.path.isfile(os.path.join('/tmp/test_merlin_criteo_hugectr/output/criteo/', "criteo_hugectr/1/", "criteo.json"))

with testbook(
REPO_ROOT
/ "examples"
/ "scaling-criteo"
/ "04-Triton-Inference-with-HugeCTR.ipynb",
execute=False,
timeout=180,
) as tb3:
tb3.inject(
"""
import os
os.environ["OUTPUT_DATA_DIR"] = "/tmp/test_merlin_criteo_hugectr/output/criteo/"
os.environ["INPUT_FOLDER"] = "/tmp/test_merlin_criteo_hugectr/input/criteo/"
"""
)
NUM_OF_CELLS = len(tb3.cells)
tb3.execute_cell(list(range(0, NUM_OF_CELLS - 5)))
tb3.inject(
"""
import shutil
from merlin.systems.triton.utils import run_triton_server, send_triton_request
outputs = ["OUTPUT0"]
# with testbook(
# REPO_ROOT
# / "examples"
# / "scaling-criteo"
# / "04-Triton-Inference-with-HugeCTR.ipynb",
# execute=False,
# timeout=180,
# ) as tb3:
# tb3.inject(
# """
# import os
# os.environ["OUTPUT_DATA_DIR"] = "/tmp/test_merlin_criteo_hugectr/output/criteo/"
# os.environ["INPUT_FOLDER"] = "/tmp/test_merlin_criteo_hugectr/input/criteo/"
# """
# )
# NUM_OF_CELLS = len(tb3.cells)
# tb3.execute_cell(list(range(0, NUM_OF_CELLS - 5)))
# tb3.inject(
# """
# import shutil
# from merlin.systems.triton.utils import run_triton_server, send_triton_request
# outputs = ["OUTPUT0"]

with run_triton_server(
"/tmp/test_merlin_criteo_hugectr/output/criteo/model_inference/",
backend_config='hugectr,ps=/tmp/test_merlin_criteo_hugectr/output/criteo/model_inference/ps.json'
) as client:
response = send_triton_request(
input_schema, batch.fillna(0), outputs, client=client, triton_model="criteo_ens"
)
# with run_triton_server(
# "/tmp/test_merlin_criteo_hugectr/output/criteo/model_inference/",
# backend_config='hugectr,ps=/tmp/test_merlin_criteo_hugectr/output/criteo/model_inference/ps.json'
# ) as client:
# response = send_triton_request(
# input_schema, batch.fillna(0), outputs, client=client, triton_model="criteo_ens"
# )

response = response["OUTPUT0"]
"""
)
tb3.execute_cell(NUM_OF_CELLS - 4)
response = tb3.ref("response")
assert len(response) == 3
# response = response["OUTPUT0"]
# """
# )
# tb3.execute_cell(NUM_OF_CELLS - 4)
# response = tb3.ref("response")
# assert len(response) == 3
2 changes: 2 additions & 0 deletions tox.ini
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,8 @@ commands =
[testenv:test-gpu]
passenv =
OPAL_PREFIX
setenv =
TF_GPU_ALLOCATOR=cuda_malloc_async
sitepackages=true
; Runs in: Internal Jenkins
; Runs GPU-based tests.
Expand Down