Skip to content

ipv6 pr ec2 tests #4816

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.

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

Open
wants to merge 24 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
24 commits
Select commit Hold shift + click to select a range
ca9b4a9
ipv4 ec2 sm tests
jinyan-li1 May 13, 2025
31df801
add ipv6 for ec2 tests
jinyan-li1 May 16, 2025
a39c340
add logs about ipv6 configs
jinyan-li1 May 16, 2025
e5ce3e8
update logs about ipv6
jinyan-li1 May 16, 2025
3eac9e4
add more logs for testing
jinyan-li1 May 16, 2025
006c8cf
change filter for ipv6 sg
jinyan-li1 May 16, 2025
7423a59
uncomment tests and remove some logging
jinyan-li1 May 16, 2025
20def6f
disassociate eip for non default vpc
jinyan-li1 May 17, 2025
aceef56
add docstring and remove logs used for debugging
jinyan-li1 May 20, 2025
09e9de4
remove trailing character
jinyan-li1 May 20, 2025
e3b1005
build new image
jinyan-li1 May 20, 2025
4287346
run both training and inference
jinyan-li1 May 20, 2025
146d948
run inference tests only ec2
jinyan-li1 May 20, 2025
d5dbf1c
update pytorch/inference/buildspec-2-6-sm for testing
jinyan-li1 May 20, 2025
489dfb5
build new image
jinyan-li1 May 20, 2025
ae71969
Merge branch 'master' into ipv6-test
jinyan-li1 May 20, 2025
056a90d
run training and inference tests for pt 2.6 ec2
jinyan-li1 May 20, 2025
f53cf26
fix formatting and run both training and inference for pt 2.6 ec2
jinyan-li1 May 20, 2025
0fba311
run both training and inference for pt 2.5 sm
jinyan-li1 May 21, 2025
2b202af
Merge branch 'master' into ipv6-test
jinyan-li1 May 21, 2025
dd4f652
run both training and inference for pt 2.5 ec2
jinyan-li1 May 21, 2025
162030f
run both training and inference for pt 2.4 sm
jinyan-li1 May 21, 2025
f0f3dbc
Merge branch 'master' into ipv6-test
jinyan-li1 May 21, 2025
f31a992
run both training and inference for pt 2.4 ec2
jinyan-li1 May 21, 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
13 changes: 8 additions & 5 deletions dlc_developer_config.toml
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@ 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", "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.
Expand Down Expand Up @@ -71,13 +71,16 @@ ec2_benchmark_tests = false
### default. If false, these types of tests will be skipped while other tests will run as usual.
### These tests are run in EC2 test jobs, so ec2_tests must be true if ec2_tests_on_heavy_instances is true.
### Off by default (set to false)
ec2_tests_on_heavy_instances = false
ec2_tests_on_heavy_instances = true
### Set enable_ipv6 = true to run tests with IPv6-enabled resources
### Off by default (set to false)
enable_ipv6 = true
### SM specific tests
### On by default
sagemaker_local_tests = true

# 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 All @@ -104,7 +107,7 @@ use_scheduler = false
### TRAINING PR JOBS ###

# Standard Framework Training
dlc-pr-pytorch-training = ""
dlc-pr-pytorch-training = "pytorch/training/buildspec-2-4-ec2.yml"
dlc-pr-tensorflow-2-training = ""
dlc-pr-autogluon-training = ""

Expand Down Expand Up @@ -134,7 +137,7 @@ dlc-pr-tensorflow-2-habana-training = ""
### INFERENCE PR JOBS ###

# Standard Framework Inference
dlc-pr-pytorch-inference = ""
dlc-pr-pytorch-inference = "pytorch/inference/buildspec-2-4-ec2.yml"
dlc-pr-tensorflow-2-inference = ""
dlc-pr-autogluon-inference = ""

Expand Down
4 changes: 3 additions & 1 deletion pytorch/inference/buildspec-2-4-ec2.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.4.0
short_version: &SHORT_VERSION "2.4"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
inference_repository: &INFERENCE_REPOSITORY
Expand Down Expand Up @@ -44,6 +44,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "beta:2.4.0-cpu-py311-ubuntu22.04-ec2"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand All @@ -61,6 +62,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "beta:2.4.0-gpu-py311-cu124-ubuntu22.04-ec2"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand Down
4 changes: 3 additions & 1 deletion pytorch/inference/buildspec-2-4-sm.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.4.0
short_version: &SHORT_VERSION "2.4"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
inference_repository: &INFERENCE_REPOSITORY
Expand Down Expand Up @@ -45,6 +45,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.4.0-cpu-py311-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: sagemaker
context:
Expand All @@ -63,6 +64,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.4.0-gpu-py311-cu124-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: sagemaker
Expand Down
4 changes: 3 additions & 1 deletion pytorch/inference/buildspec-2-5-ec2.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.5.1
short_version: &SHORT_VERSION "2.5"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
inference_repository: &INFERENCE_REPOSITORY
Expand Down Expand Up @@ -44,6 +44,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "beta:2.5.0-cpu-py311-ubuntu22.04-ec2"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand All @@ -61,6 +62,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "beta:2.5.0-gpu-py311-cu124-ubuntu22.04-ec2"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand Down
4 changes: 3 additions & 1 deletion pytorch/inference/buildspec-2-5-sm.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.5.1
short_version: &SHORT_VERSION "2.5"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
inference_repository: &INFERENCE_REPOSITORY
Expand Down Expand Up @@ -45,6 +45,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.5.0-cpu-py311-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: sagemaker
context:
Expand All @@ -63,6 +64,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.5.0-gpu-py311-cu124-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: sagemaker
Expand Down
4 changes: 3 additions & 1 deletion pytorch/inference/buildspec-2-6-ec2.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.6.0
short_version: &SHORT_VERSION "2.6"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
inference_repository: &INFERENCE_REPOSITORY
Expand Down Expand Up @@ -44,6 +44,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "False"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand All @@ -61,6 +62,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "False"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand Down
4 changes: 3 additions & 1 deletion pytorch/inference/buildspec-2-6-sm.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.6.0
short_version: &SHORT_VERSION "2.6"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
inference_repository: &INFERENCE_REPOSITORY
Expand Down Expand Up @@ -48,6 +48,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.5.0-cpu-py311-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: sagemaker
context:
Expand All @@ -66,6 +67,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.5.0-gpu-py311-cu124-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: sagemaker
Expand Down
6 changes: 3 additions & 3 deletions pytorch/training/buildspec-2-4-ec2.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.4.0
short_version: &SHORT_VERSION "2.4"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
training_repository: &TRAINING_REPOSITORY
Expand Down Expand Up @@ -42,7 +42,7 @@ images:
os_version: &OS_VERSION ubuntu22.04
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "True"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand All @@ -58,7 +58,7 @@ images:
os_version: &OS_VERSION ubuntu22.04
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "True"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: ec2
Expand Down
4 changes: 3 additions & 1 deletion pytorch/training/buildspec-2-4-sm.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.4.0
short_version: &SHORT_VERSION "2.4"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
training_repository: &TRAINING_REPOSITORY
Expand Down Expand Up @@ -43,6 +43,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.4.0-cpu-py311-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: sagemaker
context:
Expand All @@ -59,6 +60,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.4.0-gpu-py311-cu124-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: sagemaker
Expand Down
4 changes: 3 additions & 1 deletion pytorch/training/buildspec-2-5-ec2.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.5.1
short_version: &SHORT_VERSION "2.5"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
training_repository: &TRAINING_REPOSITORY
Expand Down Expand Up @@ -43,6 +43,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "beta:2.5.1-cpu-py311-ubuntu22.04-ec2"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand All @@ -59,6 +60,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "beta:2.5.1-gpu-py311-cu121-ubuntu22.04-ec2"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: ec2
Expand Down
4 changes: 3 additions & 1 deletion pytorch/training/buildspec-2-5-sm.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.5.1
short_version: &SHORT_VERSION "2.5"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
training_repository: &TRAINING_REPOSITORY
Expand Down Expand Up @@ -49,6 +49,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.5.1-cpu-py311-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: sagemaker
context:
Expand All @@ -65,6 +66,7 @@ images:
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.5.1-gpu-py311-cu124-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: sagemaker
Expand Down
6 changes: 3 additions & 3 deletions pytorch/training/buildspec-2-6-ec2.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.6.0
short_version: &SHORT_VERSION "2.6"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
training_repository: &TRAINING_REPOSITORY
Expand Down Expand Up @@ -48,7 +48,7 @@ images:
os_version: &OS_VERSION ubuntu22.04
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "True"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: ec2
context:
Expand All @@ -64,7 +64,7 @@ images:
os_version: &OS_VERSION ubuntu22.04
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-ec2" ]
# build_tag_override: "True"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: ec2
Expand Down
6 changes: 3 additions & 3 deletions pytorch/training/buildspec-2-6-sm.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ framework: &FRAMEWORK pytorch
version: &VERSION 2.6.0
short_version: &SHORT_VERSION "2.6"
arch_type: x86
autopatch_build: "True"
# autopatch_build: "True"

repository_info:
training_repository: &TRAINING_REPOSITORY
Expand Down Expand Up @@ -48,7 +48,7 @@ images:
os_version: &OS_VERSION ubuntu22.04
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.6.0-cpu-py311-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /Dockerfile., *DEVICE_TYPE ]
target: sagemaker
context:
Expand All @@ -64,7 +64,7 @@ images:
os_version: &OS_VERSION ubuntu22.04
tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
latest_release_tag: !join [ *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
# build_tag_override: "beta:2.6.0-gpu-py311-cu124-ubuntu22.04-sagemaker"
build_tag_override: "True"
docker_file: !join [ docker/, *SHORT_VERSION, /, *DOCKER_PYTHON_VERSION, /, *CUDA_VERSION, /Dockerfile.,
*DEVICE_TYPE ]
target: sagemaker
Expand Down
4 changes: 4 additions & 0 deletions src/config.py
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,10 @@ def are_heavy_instance_ec2_tests_enabled():
return parse_dlc_developer_configs("test", "ec2_tests_on_heavy_instances")


def is_ipv6_test_enabled():
return parse_dlc_developer_configs("test", "enable_ipv6")


def is_ecs_test_enabled():
return parse_dlc_developer_configs("test", "ecs_tests")

Expand Down
8 changes: 8 additions & 0 deletions src/start_testbuilds.py
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,9 @@ def run_test_job(commit, codebuild_project, images_str=""):
config.are_heavy_instance_ec2_tests_enabled() and "ec2" in codebuild_project
)

# For EC2 tests, enable IPv6 testing when config is enabled
is_ipv6_test_enabled = config.is_ipv6_test_enabled() and "ec2" in codebuild_project

if config.is_deep_canary_mode_enabled():
env_overrides.append({"name": "DEEP_CANARY_MODE", "value": "true", "type": "PLAINTEXT"})

Expand Down Expand Up @@ -90,6 +93,11 @@ def run_test_job(commit, codebuild_project, images_str=""):
"value": str(are_heavy_instance_ec2_tests_enabled),
"type": "PLAINTEXT",
},
{
"name": "ENABLE_IPV6_TESTING",
"value": str(is_ipv6_test_enabled),
"type": "PLAINTEXT",
},
{
"name": "FRAMEWORK_BUILDSPEC_FILE",
"value": config.get_buildspec_override() or os.getenv("FRAMEWORK_BUILDSPEC_FILE"),
Expand Down
Loading