Skip to content

build and run pt 2.8 tests to check build time #5269

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

Closed
wants to merge 5 commits into from
Closed

build and run pt 2.8 tests to check build time #5269

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
c7bb958
build and run pt 2.8 tests to check build time
jinyan-li1 Sep 16, 2025
1addcaa
run 2.7 ec2 tests
jinyan-li1 Sep 16, 2025
5a8bb5f
run tests for pt2.7 sm image
jinyan-li1 Sep 16, 2025
885eb0e
Merge branch 'master' into run-pt-2.7-tests
jinyan-li1 Sep 18, 2025
056c065
rerun ecs test with reordered param
jinyan-li1 Sep 18, 2025
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
27 changes: 12 additions & 15 deletions dlc_developer_config.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,16 +37,16 @@ deep_canary_mode = false
[build]
# Add in frameworks you would like to build. By default, builds are disabled unless you specify building an image.
# available frameworks - ["base", "vllm", "autogluon", "huggingface_tensorflow", "huggingface_pytorch", "huggingface_tensorflow_trcomp", "huggingface_pytorch_trcomp", "pytorch_trcomp", "tensorflow", "pytorch", "stabilityai_pytorch"]
build_frameworks = []
build_frameworks = ["pytorch"]


# By default we build both training and inference containers. Set true/false values to determine which to build.
build_training = true
build_inference = true
build_training = true
build_inference = false

# Set do_build to "false" to skip builds and test the latest image built by this PR
# Note: at least one build is required to set do_build to "false"
do_build = true
do_build = false

[notify]
### Notify on test failures
Expand All @@ -57,13 +57,13 @@ notify_test_failures = false

[test]
### On by default
sanity_tests = true
security_tests = true
sanity_tests = false
security_tests = false
safety_check_test = false
ecr_scan_allowlist_feature = false
ecs_tests = true
eks_tests = true
ec2_tests = true
eks_tests = false
ec2_tests = false
# Set it to true if you are preparing a Benchmark related PR
ec2_benchmark_tests = false

Expand All @@ -74,7 +74,7 @@ ec2_benchmark_tests = false
ec2_tests_on_heavy_instances = false
### SM specific tests
### On by default
sagemaker_local_tests = true
sagemaker_local_tests = false
### Set enable_ipv6 = true to run tests with IPv6-enabled resources
### Off by default (set to false)
enable_ipv6 = false
Expand All @@ -92,7 +92,7 @@ enable_ipv6 = false
ipv6_vpc_name = ""

# run standard sagemaker remote tests from test/sagemaker_tests
sagemaker_remote_tests = true
sagemaker_remote_tests = false
# run efa sagemaker tests
sagemaker_efa_tests = false
# run release_candidate_integration tests
Expand Down Expand Up @@ -122,7 +122,7 @@ use_scheduler = false
dlc-pr-base = ""

# Standard Framework Training
dlc-pr-pytorch-training = ""
dlc-pr-pytorch-training = "pytorch/training/buildspec-2-7-ec2.yml"
dlc-pr-tensorflow-2-training = ""
dlc-pr-autogluon-training = ""

Expand Down Expand Up @@ -179,7 +179,4 @@ dlc-pr-stabilityai-pytorch-inference = ""

# EIA Inference
dlc-pr-pytorch-eia-inference = ""
dlc-pr-tensorflow-2-eia-inference = ""

# vllm
dlc-pr-vllm = ""
dlc-pr-tensorflow-2-eia-inference = ""
8 changes: 4 additions & 4 deletions test/dlc_tests/ecs/pytorch/training/test_ecs_pytorch_training.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@
@pytest.mark.parametrize("ecs_ami", [ECS_AML2_CPU_USWEST2], indirect=True)
@pytest.mark.team("conda")
def test_ecs_pytorch_training_mnist_cpu(
cpu_only, ecs_container_instance, pytorch_training, training_cmd, ecs_cluster_name
pytorch_training, cpu_only, ecs_container_instance, training_cmd, ecs_cluster_name
):
"""
CPU mnist test for PyTorch Training
Expand Down Expand Up @@ -118,10 +118,10 @@ def test_ecs_pytorch_training_mnist_neuronx_inf2(
@pytest.mark.parametrize("use_large_storage", [True], indirect=True)
@pytest.mark.team("conda")
def test_ecs_pytorch_training_mnist_gpu(
pytorch_training,
gpu_only,
use_large_storage,
ecs_container_instance,
pytorch_training,
training_cmd,
ecs_cluster_name,
):
Expand Down Expand Up @@ -155,7 +155,7 @@ def test_ecs_pytorch_training_mnist_gpu(
@pytest.mark.parametrize("ecs_ami", [ECS_AML2_CPU_USWEST2], indirect=True)
@pytest.mark.team("dgl")
def test_ecs_pytorch_training_dgl_cpu(
cpu_only, py3_only, ecs_container_instance, pytorch_training, training_cmd, ecs_cluster_name
pytorch_training, cpu_only, py3_only, ecs_container_instance, training_cmd, ecs_cluster_name
):
"""
CPU DGL test for PyTorch Training
Expand Down Expand Up @@ -188,11 +188,11 @@ def test_ecs_pytorch_training_dgl_cpu(
@pytest.mark.parametrize("use_large_storage", [True], indirect=True)
@pytest.mark.team("dgl")
def test_ecs_pytorch_training_dgl_gpu(
pytorch_training,
gpu_only,
py3_only,
use_large_storage,
ecs_container_instance,
pytorch_training,
training_cmd,
ecs_cluster_name,
):
Expand Down