fix: Add additional dependencies for ModelTrainer (5668)#5731

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

Draft
aviruthen wants to merge 2 commits into
base:master
Choose a base branch
from
Draft

fix: Add additional dependencies for ModelTrainer (5668) #5731

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
19a3c1d
fix: Add additional dependencies for ModelTrainer (5668)
aviruthen Apr 7, 2026
4deb5ef
fix: address review comments (iteration #1)
aviruthen Apr 7, 2026
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
6 changes: 6 additions & 0 deletions sagemaker-core/src/sagemaker/core/training/configs.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -109,6 +109,10 @@ class SourceCode(BaseConfig):
ignore_patterns: (Optional[List[str]]) :
The ignore patterns to ignore specific files/folders when uploading to S3. If not specified,
default to: ['.env', '.git', '__pycache__', '.DS_Store', '.cache', '.ipynb_checkpoints'].
dependencies (Optional[List[str]]):
A list of paths to local directories (absolute or relative) containing additional
libraries that will be copied into the training container and added to PYTHONPATH.
Each path must be a valid local directory or file.
"""

source_dir: Optional[StrPipeVar] = None
Expand All@@ -123,6 +127,8 @@ class SourceCode(BaseConfig):
".cache",
".ipynb_checkpoints",
]
Comment thread
aviruthen marked this conversation as resolved.
dependencies: Optional[List[str]] = None


class OutputDataConfig(shapes.OutputDataConfig):
"""OutputDataConfig.
Expand Down
5 changes: 4 additions & 1 deletion sagemaker-train/src/sagemaker/train/constants.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -63,6 +63,9 @@
"amazon.nova-pro-v1:0": ["us-east-1"]
}

Comment thread
aviruthen marked this conversation as resolved.
SM_DEPENDENCIES = "sm_dependencies"
SM_DEPENDENCIES_CONTAINER_PATH = "/opt/ml/input/data/sm_dependencies"

SM_RECIPE = "recipe"
SM_RECIPE_YAML = "recipe.yaml"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
36 changes: 36 additions & 0 deletions sagemaker-train/src/sagemaker/train/model_trainer.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -83,6 +83,8 @@
SM_CODE_CONTAINER_PATH,
SM_DRIVERS,
SM_DRIVERS_LOCAL_PATH,
SM_DEPENDENCIES,
SM_DEPENDENCIES_CONTAINER_PATH,
SM_RECIPE,
SM_RECIPE_YAML,
SM_RECIPE_CONTAINER_PATH,
Expand All@@ -99,6 +101,7 @@
EXECUTE_BASIC_SCRIPT_DRIVER,
INSTALL_AUTO_REQUIREMENTS,
INSTALL_REQUIREMENTS,
INSTALL_DEPENDENCIES,
)
from sagemaker.core.telemetry.telemetry_logging import _telemetry_emitter
from sagemaker.core.telemetry.constants import Feature
Expand DownExpand Up@@ -269,6 +272,7 @@ class ModelTrainer(BaseModel):

# Private Attributes for AWS_Batch
_temp_code_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)
_temp_deps_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)

CONFIGURABLE_ATTRIBUTES: ClassVar[List[str]] = [
"role",
Expand DownExpand Up@@ -408,6 +412,8 @@ def __del__(self):
self._temp_recipe_train_dir.cleanup()
if self._temp_code_dir is not None:
self._temp_code_dir.cleanup()
if self._temp_deps_dir is not None:
self._temp_deps_dir.cleanup()

def _validate_training_image_and_algorithm_name(
self, training_image: Optional[str], algorithm_name: Optional[str]
Expand DownExpand Up@@ -484,6 +490,13 @@ def _validate_source_code(self, source_code: Optional[SourceCode]):
f"Invalid 'entry_script': {entry_script}. "
"Must be a valid file within the 'source_dir'.",
)
Comment thread
aviruthen marked this conversation as resolved.
if source_code.dependencies:
for dep_path in source_code.dependencies:
if not _is_valid_path(dep_path, path_type="Directory"):
raise ValueError(
f"Invalid dependency path: {dep_path}. "
"Each dependency must be a valid local directory path."
)

@staticmethod
def _validate_and_fetch_hyperparameters_file(hyperparameters_file: str):
Expand DownExpand Up@@ -654,6 +667,21 @@ def _create_training_job_args(
)
final_input_data_config.append(source_code_channel)

# If dependencies are provided, create a channel for the dependencies
# The dependencies will be mounted at /opt/ml/input/data/sm_dependencies
if self.source_code.dependencies:
self._temp_deps_dir = TemporaryDirectory()
for dep_path in self.source_code.dependencies:
dep_basename = os.path.basename(os.path.normpath(dep_path))
dest_path = os.path.join(self._temp_deps_dir.name, dep_basename)
shutil.copytree(dep_path, dest_path, dirs_exist_ok=True)
dependencies_channel = self.create_input_data_channel(
channel_name=SM_DEPENDENCIES,
data_source=self._temp_deps_dir.name,
key_prefix=input_data_key_prefix,
)
final_input_data_config.append(dependencies_channel)

self._prepare_train_script(
tmp_dir=self._temp_code_dir,
source_code=self.source_code,
Expand DownExpand Up@@ -813,6 +841,9 @@ def train(
local_container.train(wait)
if self._temp_code_dir is not None:
self._temp_code_dir.cleanup()
if self._temp_deps_dir is not None:
self._temp_deps_dir.cleanup()
self._temp_deps_dir = None


def create_input_data_channel(
Expand DownExpand Up@@ -1010,6 +1041,10 @@ def _prepare_train_script(
base_command = source_code.command.split()
base_command = " ".join(base_command)

install_dependencies = ""
Comment thread
aviruthen marked this conversation as resolved.
if source_code.dependencies:
install_dependencies = INSTALL_DEPENDENCIES

install_requirements = ""
if source_code.requirements:
if self._jumpstart_config and source_code.requirements == "auto":
Expand DownExpand Up@@ -1049,6 +1084,7 @@ def _prepare_train_script(

train_script = TRAIN_SCRIPT_TEMPLATE.format(
working_dir=working_dir,
install_dependencies=install_dependencies,
install_requirements=install_requirements,
execute_driver=execute_driver,
)
Expand Down
24 changes: 24 additions & 0 deletions sagemaker-train/src/sagemaker/train/templates.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -39,6 +39,29 @@
$SM_PIP_CMD install -r {requirements_file}
"""

INSTALL_DEPENDENCIES = """
Comment thread
aviruthen marked this conversation as resolved.
echo "Setting up additional dependencies"
if [ -d /opt/ml/input/data/sm_dependencies ]; then
for dep in /opt/ml/input/data/sm_dependencies/*; do
if [ -d "$dep" ]; then
echo "Adding directory $dep to PYTHONPATH"
export PYTHONPATH="$dep:$PYTHONPATH"
elif [ -f "$dep" ]; then
case "$dep" in
*.whl|*.tar.gz)
echo "Installing package $dep via pip"
$SM_PIP_CMD install "$dep"
;;
*)
echo "Adding parent directory of $dep to PYTHONPATH"
export PYTHONPATH="/opt/ml/input/data/sm_dependencies:$PYTHONPATH"
;;
esac
fi
done
fi
"""

EXEUCTE_DISTRIBUTED_DRIVER = """
echo "Running {driver_name} Driver"
$SM_PYTHON_CMD /opt/ml/input/data/sm_drivers/distributed_drivers/{driver_script}
Expand DownExpand Up@@ -95,6 +118,7 @@
set -x

{working_dir}
{install_dependencies}
{install_requirements}
{execute_driver}

Expand Down
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
fix: Add additional dependencies for ModelTrainer (5668)#5731

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

 Draft

aviruthen
wants to merge
2
commits into

base:master
Choose a base branch

from

 Draft


fix: Add additional dependencies for ModelTrainer (5668)
#5731
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
19a3c1d

fix: Add additional dependencies for ModelTrainer (5668)


aviruthen Apr 7, 2026
4deb5ef

fix: address review comments (iteration #1)


aviruthen Apr 7, 2026

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


6 changes: 6 additions & 0 deletions
sagemaker-core/src/sagemaker/core/training/configs.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -109,6 +109,10 @@ class SourceCode(BaseConfig):
 ignore_patterns: (Optional[List[str]]) :
 The ignore patterns to ignore specific files/folders when uploading to S3. If not specified,
 default to: ['.env', '.git', '__pycache__', '.DS_Store', '.cache', '.ipynb_checkpoints'].
 dependencies (Optional[List[str]]):
 A list of paths to local directories (absolute or relative) containing additional
 libraries that will be copied into the training container and added to PYTHONPATH.
 Each path must be a valid local directory or file.
 """

 source_dir: Optional[StrPipeVar] = None
Expand All@@ -123,6 +127,8 @@ class SourceCode(BaseConfig):
 ".cache",
 ".ipynb_checkpoints",
 ]
Comment thread
aviruthen marked this conversation as resolved.

 dependencies: Optional[List[str]] = None


class OutputDataConfig(shapes.OutputDataConfig):
 """OutputDataConfig.
Expand Down

5 changes: 4 additions & 1 deletion
sagemaker-train/src/sagemaker/train/constants.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -63,6 +63,9 @@
 "amazon.nova-pro-v1:0": ["us-east-1"]
}

Comment thread
aviruthen marked this conversation as resolved.

SM_DEPENDENCIES = "sm_dependencies"
SM_DEPENDENCIES_CONTAINER_PATH = "/opt/ml/input/data/sm_dependencies"

SM_RECIPE = "recipe"
SM_RECIPE_YAML = "recipe.yaml"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"

36 changes: 36 additions & 0 deletions
sagemaker-train/src/sagemaker/train/model_trainer.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,6 +83,8 @@
 SM_CODE_CONTAINER_PATH,
 SM_DRIVERS,
 SM_DRIVERS_LOCAL_PATH,
 SM_DEPENDENCIES,
 SM_DEPENDENCIES_CONTAINER_PATH,
 SM_RECIPE,
 SM_RECIPE_YAML,
 SM_RECIPE_CONTAINER_PATH,
Expand All@@ -99,6 +101,7 @@
 EXECUTE_BASIC_SCRIPT_DRIVER,
 INSTALL_AUTO_REQUIREMENTS,
 INSTALL_REQUIREMENTS,
 INSTALL_DEPENDENCIES,
)
from sagemaker.core.telemetry.telemetry_logging import _telemetry_emitter
from sagemaker.core.telemetry.constants import Feature
Expand DownExpand Up@@ -269,6 +272,7 @@ class ModelTrainer(BaseModel):

 # Private Attributes for AWS_Batch
 _temp_code_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)
 _temp_deps_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)

 CONFIGURABLE_ATTRIBUTES: ClassVar[List[str]] = [
 "role",
Expand DownExpand Up@@ -408,6 +412,8 @@ def __del__(self):
 self._temp_recipe_train_dir.cleanup()
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()

 def _validate_training_image_and_algorithm_name(
 self, training_image: Optional[str], algorithm_name: Optional[str]
Expand DownExpand Up@@ -484,6 +490,13 @@ def _validate_source_code(self, source_code: Optional[SourceCode]):
 f"Invalid 'entry_script': {entry_script}. "
 "Must be a valid file within the 'source_dir'.",
 )
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 for dep_path in source_code.dependencies:
 if not _is_valid_path(dep_path, path_type="Directory"):
 raise ValueError(
 f"Invalid dependency path: {dep_path}. "
 "Each dependency must be a valid local directory path."
 )

 @staticmethod
 def _validate_and_fetch_hyperparameters_file(hyperparameters_file: str):
Expand DownExpand Up@@ -654,6 +667,21 @@ def _create_training_job_args(
 )
 final_input_data_config.append(source_code_channel)

 # If dependencies are provided, create a channel for the dependencies
 # The dependencies will be mounted at /opt/ml/input/data/sm_dependencies
 if self.source_code.dependencies:
 self._temp_deps_dir = TemporaryDirectory()
 for dep_path in self.source_code.dependencies:
 dep_basename = os.path.basename(os.path.normpath(dep_path))
 dest_path = os.path.join(self._temp_deps_dir.name, dep_basename)
 shutil.copytree(dep_path, dest_path, dirs_exist_ok=True)
 dependencies_channel = self.create_input_data_channel(
 channel_name=SM_DEPENDENCIES,
 data_source=self._temp_deps_dir.name,
 key_prefix=input_data_key_prefix,
 )
 final_input_data_config.append(dependencies_channel)

 self._prepare_train_script(
 tmp_dir=self._temp_code_dir,
 source_code=self.source_code,
Expand DownExpand Up@@ -813,6 +841,9 @@ def train(
 local_container.train(wait)
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()
 self._temp_deps_dir = None


 def create_input_data_channel(
Expand DownExpand Up@@ -1010,6 +1041,10 @@ def _prepare_train_script(
 base_command = source_code.command.split()
 base_command = " ".join(base_command)

 install_dependencies = ""
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 install_dependencies = INSTALL_DEPENDENCIES

 install_requirements = ""
 if source_code.requirements:
 if self._jumpstart_config and source_code.requirements == "auto":
Expand DownExpand Up@@ -1049,6 +1084,7 @@ def _prepare_train_script(

 train_script = TRAIN_SCRIPT_TEMPLATE.format(
 working_dir=working_dir,
 install_dependencies=install_dependencies,
 install_requirements=install_requirements,
 execute_driver=execute_driver,
 )
Expand Down

24 changes: 24 additions & 0 deletions
sagemaker-train/src/sagemaker/train/templates.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -39,6 +39,29 @@
$SM_PIP_CMD install -r {requirements_file}
"""

INSTALL_DEPENDENCIES = """
Comment thread
aviruthen marked this conversation as resolved.

echo "Setting up additional dependencies"
if [ -d /opt/ml/input/data/sm_dependencies ]; then
 for dep in /opt/ml/input/data/sm_dependencies/*; do
 if [ -d "$dep" ]; then
 echo "Adding directory $dep to PYTHONPATH"
 export PYTHONPATH="$dep:$PYTHONPATH"
 elif [ -f "$dep" ]; then
 case "$dep" in
 *.whl|*.tar.gz)
 echo "Installing package $dep via pip"
 $SM_PIP_CMD install "$dep"
 ;;
 *)
 echo "Adding parent directory of $dep to PYTHONPATH"
 export PYTHONPATH="/opt/ml/input/data/sm_dependencies:$PYTHONPATH"
 ;;
 esac
 fi
 done
fi
"""

EXEUCTE_DISTRIBUTED_DRIVER = """
echo "Running {driver_name} Driver"
$SM_PYTHON_CMD /opt/ml/input/data/sm_drivers/distributed_drivers/{driver_script}
Expand DownExpand Up@@ -95,6 +118,7 @@
set -x

{working_dir}
{install_dependencies}
{install_requirements}
{execute_driver}

Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
fix: Add additional dependencies for ModelTrainer (5668)#5731

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

 Draft

aviruthen
wants to merge
2
commits into

base:master
Choose a base branch

from

 Draft


fix: Add additional dependencies for ModelTrainer (5668)
#5731
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
19a3c1d

fix: Add additional dependencies for ModelTrainer (5668)


aviruthen Apr 7, 2026
4deb5ef

fix: address review comments (iteration #1)


aviruthen Apr 7, 2026

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


6 changes: 6 additions & 0 deletions
sagemaker-core/src/sagemaker/core/training/configs.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -109,6 +109,10 @@ class SourceCode(BaseConfig):
 ignore_patterns: (Optional[List[str]]) :
 The ignore patterns to ignore specific files/folders when uploading to S3. If not specified,
 default to: ['.env', '.git', '__pycache__', '.DS_Store', '.cache', '.ipynb_checkpoints'].
 dependencies (Optional[List[str]]):
 A list of paths to local directories (absolute or relative) containing additional
 libraries that will be copied into the training container and added to PYTHONPATH.
 Each path must be a valid local directory or file.
 """

 source_dir: Optional[StrPipeVar] = None
Expand All@@ -123,6 +127,8 @@ class SourceCode(BaseConfig):
 ".cache",
 ".ipynb_checkpoints",
 ]
Comment thread
aviruthen marked this conversation as resolved.

 dependencies: Optional[List[str]] = None


class OutputDataConfig(shapes.OutputDataConfig):
 """OutputDataConfig.
Expand Down

5 changes: 4 additions & 1 deletion
sagemaker-train/src/sagemaker/train/constants.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -63,6 +63,9 @@
 "amazon.nova-pro-v1:0": ["us-east-1"]
}

Comment thread
aviruthen marked this conversation as resolved.

SM_DEPENDENCIES = "sm_dependencies"
SM_DEPENDENCIES_CONTAINER_PATH = "/opt/ml/input/data/sm_dependencies"

SM_RECIPE = "recipe"
SM_RECIPE_YAML = "recipe.yaml"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"

36 changes: 36 additions & 0 deletions
sagemaker-train/src/sagemaker/train/model_trainer.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,6 +83,8 @@
 SM_CODE_CONTAINER_PATH,
 SM_DRIVERS,
 SM_DRIVERS_LOCAL_PATH,
 SM_DEPENDENCIES,
 SM_DEPENDENCIES_CONTAINER_PATH,
 SM_RECIPE,
 SM_RECIPE_YAML,
 SM_RECIPE_CONTAINER_PATH,
Expand All@@ -99,6 +101,7 @@
 EXECUTE_BASIC_SCRIPT_DRIVER,
 INSTALL_AUTO_REQUIREMENTS,
 INSTALL_REQUIREMENTS,
 INSTALL_DEPENDENCIES,
)
from sagemaker.core.telemetry.telemetry_logging import _telemetry_emitter
from sagemaker.core.telemetry.constants import Feature
Expand DownExpand Up@@ -269,6 +272,7 @@ class ModelTrainer(BaseModel):

 # Private Attributes for AWS_Batch
 _temp_code_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)
 _temp_deps_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)

 CONFIGURABLE_ATTRIBUTES: ClassVar[List[str]] = [
 "role",
Expand DownExpand Up@@ -408,6 +412,8 @@ def __del__(self):
 self._temp_recipe_train_dir.cleanup()
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()

 def _validate_training_image_and_algorithm_name(
 self, training_image: Optional[str], algorithm_name: Optional[str]
Expand DownExpand Up@@ -484,6 +490,13 @@ def _validate_source_code(self, source_code: Optional[SourceCode]):
 f"Invalid 'entry_script': {entry_script}. "
 "Must be a valid file within the 'source_dir'.",
 )
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 for dep_path in source_code.dependencies:
 if not _is_valid_path(dep_path, path_type="Directory"):
 raise ValueError(
 f"Invalid dependency path: {dep_path}. "
 "Each dependency must be a valid local directory path."
 )

 @staticmethod
 def _validate_and_fetch_hyperparameters_file(hyperparameters_file: str):
Expand DownExpand Up@@ -654,6 +667,21 @@ def _create_training_job_args(
 )
 final_input_data_config.append(source_code_channel)

 # If dependencies are provided, create a channel for the dependencies
 # The dependencies will be mounted at /opt/ml/input/data/sm_dependencies
 if self.source_code.dependencies:
 self._temp_deps_dir = TemporaryDirectory()
 for dep_path in self.source_code.dependencies:
 dep_basename = os.path.basename(os.path.normpath(dep_path))
 dest_path = os.path.join(self._temp_deps_dir.name, dep_basename)
 shutil.copytree(dep_path, dest_path, dirs_exist_ok=True)
 dependencies_channel = self.create_input_data_channel(
 channel_name=SM_DEPENDENCIES,
 data_source=self._temp_deps_dir.name,
 key_prefix=input_data_key_prefix,
 )
 final_input_data_config.append(dependencies_channel)

 self._prepare_train_script(
 tmp_dir=self._temp_code_dir,
 source_code=self.source_code,
Expand DownExpand Up@@ -813,6 +841,9 @@ def train(
 local_container.train(wait)
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()
 self._temp_deps_dir = None


 def create_input_data_channel(
Expand DownExpand Up@@ -1010,6 +1041,10 @@ def _prepare_train_script(
 base_command = source_code.command.split()
 base_command = " ".join(base_command)

 install_dependencies = ""
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 install_dependencies = INSTALL_DEPENDENCIES

 install_requirements = ""
 if source_code.requirements:
 if self._jumpstart_config and source_code.requirements == "auto":
Expand DownExpand Up@@ -1049,6 +1084,7 @@ def _prepare_train_script(

 train_script = TRAIN_SCRIPT_TEMPLATE.format(
 working_dir=working_dir,
 install_dependencies=install_dependencies,
 install_requirements=install_requirements,
 execute_driver=execute_driver,
 )
Expand Down

24 changes: 24 additions & 0 deletions
sagemaker-train/src/sagemaker/train/templates.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -39,6 +39,29 @@
$SM_PIP_CMD install -r {requirements_file}
"""

INSTALL_DEPENDENCIES = """
Comment thread
aviruthen marked this conversation as resolved.

echo "Setting up additional dependencies"
if [ -d /opt/ml/input/data/sm_dependencies ]; then
 for dep in /opt/ml/input/data/sm_dependencies/*; do
 if [ -d "$dep" ]; then
 echo "Adding directory $dep to PYTHONPATH"
 export PYTHONPATH="$dep:$PYTHONPATH"
 elif [ -f "$dep" ]; then
 case "$dep" in
 *.whl|*.tar.gz)
 echo "Installing package $dep via pip"
 $SM_PIP_CMD install "$dep"
 ;;
 *)
 echo "Adding parent directory of $dep to PYTHONPATH"
 export PYTHONPATH="/opt/ml/input/data/sm_dependencies:$PYTHONPATH"
 ;;
 esac
 fi
 done
fi
"""

EXEUCTE_DISTRIBUTED_DRIVER = """
echo "Running {driver_name} Driver"
$SM_PYTHON_CMD /opt/ml/input/data/sm_drivers/distributed_drivers/{driver_script}
Expand DownExpand Up@@ -95,6 +118,7 @@
set -x

{working_dir}
{install_dependencies}
{install_requirements}
{execute_driver}

Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
fix: Add additional dependencies for ModelTrainer (5668)#5731

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

 Draft

aviruthen
wants to merge
2
commits into

base:master
Choose a base branch

from

 Draft


fix: Add additional dependencies for ModelTrainer (5668)
#5731
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
19a3c1d

fix: Add additional dependencies for ModelTrainer (5668)


aviruthen Apr 7, 2026
4deb5ef

fix: address review comments (iteration #1)


aviruthen Apr 7, 2026

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


6 changes: 6 additions & 0 deletions
sagemaker-core/src/sagemaker/core/training/configs.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -109,6 +109,10 @@ class SourceCode(BaseConfig):
 ignore_patterns: (Optional[List[str]]) :
 The ignore patterns to ignore specific files/folders when uploading to S3. If not specified,
 default to: ['.env', '.git', '__pycache__', '.DS_Store', '.cache', '.ipynb_checkpoints'].
 dependencies (Optional[List[str]]):
 A list of paths to local directories (absolute or relative) containing additional
 libraries that will be copied into the training container and added to PYTHONPATH.
 Each path must be a valid local directory or file.
 """

 source_dir: Optional[StrPipeVar] = None
Expand All@@ -123,6 +127,8 @@ class SourceCode(BaseConfig):
 ".cache",
 ".ipynb_checkpoints",
 ]
Comment thread
aviruthen marked this conversation as resolved.

 dependencies: Optional[List[str]] = None


class OutputDataConfig(shapes.OutputDataConfig):
 """OutputDataConfig.
Expand Down

5 changes: 4 additions & 1 deletion
sagemaker-train/src/sagemaker/train/constants.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -63,6 +63,9 @@
 "amazon.nova-pro-v1:0": ["us-east-1"]
}

Comment thread
aviruthen marked this conversation as resolved.

SM_DEPENDENCIES = "sm_dependencies"
SM_DEPENDENCIES_CONTAINER_PATH = "/opt/ml/input/data/sm_dependencies"

SM_RECIPE = "recipe"
SM_RECIPE_YAML = "recipe.yaml"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"

36 changes: 36 additions & 0 deletions
sagemaker-train/src/sagemaker/train/model_trainer.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,6 +83,8 @@
 SM_CODE_CONTAINER_PATH,
 SM_DRIVERS,
 SM_DRIVERS_LOCAL_PATH,
 SM_DEPENDENCIES,
 SM_DEPENDENCIES_CONTAINER_PATH,
 SM_RECIPE,
 SM_RECIPE_YAML,
 SM_RECIPE_CONTAINER_PATH,
Expand All@@ -99,6 +101,7 @@
 EXECUTE_BASIC_SCRIPT_DRIVER,
 INSTALL_AUTO_REQUIREMENTS,
 INSTALL_REQUIREMENTS,
 INSTALL_DEPENDENCIES,
)
from sagemaker.core.telemetry.telemetry_logging import _telemetry_emitter
from sagemaker.core.telemetry.constants import Feature
Expand DownExpand Up@@ -269,6 +272,7 @@ class ModelTrainer(BaseModel):

 # Private Attributes for AWS_Batch
 _temp_code_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)
 _temp_deps_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)

 CONFIGURABLE_ATTRIBUTES: ClassVar[List[str]] = [
 "role",
Expand DownExpand Up@@ -408,6 +412,8 @@ def __del__(self):
 self._temp_recipe_train_dir.cleanup()
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()

 def _validate_training_image_and_algorithm_name(
 self, training_image: Optional[str], algorithm_name: Optional[str]
Expand DownExpand Up@@ -484,6 +490,13 @@ def _validate_source_code(self, source_code: Optional[SourceCode]):
 f"Invalid 'entry_script': {entry_script}. "
 "Must be a valid file within the 'source_dir'.",
 )
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 for dep_path in source_code.dependencies:
 if not _is_valid_path(dep_path, path_type="Directory"):
 raise ValueError(
 f"Invalid dependency path: {dep_path}. "
 "Each dependency must be a valid local directory path."
 )

 @staticmethod
 def _validate_and_fetch_hyperparameters_file(hyperparameters_file: str):
Expand DownExpand Up@@ -654,6 +667,21 @@ def _create_training_job_args(
 )
 final_input_data_config.append(source_code_channel)

 # If dependencies are provided, create a channel for the dependencies
 # The dependencies will be mounted at /opt/ml/input/data/sm_dependencies
 if self.source_code.dependencies:
 self._temp_deps_dir = TemporaryDirectory()
 for dep_path in self.source_code.dependencies:
 dep_basename = os.path.basename(os.path.normpath(dep_path))
 dest_path = os.path.join(self._temp_deps_dir.name, dep_basename)
 shutil.copytree(dep_path, dest_path, dirs_exist_ok=True)
 dependencies_channel = self.create_input_data_channel(
 channel_name=SM_DEPENDENCIES,
 data_source=self._temp_deps_dir.name,
 key_prefix=input_data_key_prefix,
 )
 final_input_data_config.append(dependencies_channel)

 self._prepare_train_script(
 tmp_dir=self._temp_code_dir,
 source_code=self.source_code,
Expand DownExpand Up@@ -813,6 +841,9 @@ def train(
 local_container.train(wait)
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()
 self._temp_deps_dir = None


 def create_input_data_channel(
Expand DownExpand Up@@ -1010,6 +1041,10 @@ def _prepare_train_script(
 base_command = source_code.command.split()
 base_command = " ".join(base_command)

 install_dependencies = ""
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 install_dependencies = INSTALL_DEPENDENCIES

 install_requirements = ""
 if source_code.requirements:
 if self._jumpstart_config and source_code.requirements == "auto":
Expand DownExpand Up@@ -1049,6 +1084,7 @@ def _prepare_train_script(

 train_script = TRAIN_SCRIPT_TEMPLATE.format(
 working_dir=working_dir,
 install_dependencies=install_dependencies,
 install_requirements=install_requirements,
 execute_driver=execute_driver,
 )
Expand Down

24 changes: 24 additions & 0 deletions
sagemaker-train/src/sagemaker/train/templates.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -39,6 +39,29 @@
$SM_PIP_CMD install -r {requirements_file}
"""

INSTALL_DEPENDENCIES = """
Comment thread
aviruthen marked this conversation as resolved.

echo "Setting up additional dependencies"
if [ -d /opt/ml/input/data/sm_dependencies ]; then
 for dep in /opt/ml/input/data/sm_dependencies/*; do
 if [ -d "$dep" ]; then
 echo "Adding directory $dep to PYTHONPATH"
 export PYTHONPATH="$dep:$PYTHONPATH"
 elif [ -f "$dep" ]; then
 case "$dep" in
 *.whl|*.tar.gz)
 echo "Installing package $dep via pip"
 $SM_PIP_CMD install "$dep"
 ;;
 *)
 echo "Adding parent directory of $dep to PYTHONPATH"
 export PYTHONPATH="/opt/ml/input/data/sm_dependencies:$PYTHONPATH"
 ;;
 esac
 fi
 done
fi
"""

EXEUCTE_DISTRIBUTED_DRIVER = """
echo "Running {driver_name} Driver"
$SM_PYTHON_CMD /opt/ml/input/data/sm_drivers/distributed_drivers/{driver_script}
Expand DownExpand Up@@ -95,6 +118,7 @@
set -x

{working_dir}
{install_dependencies}
{install_requirements}
{execute_driver}

Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
fix: Add additional dependencies for ModelTrainer (5668)#5731

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

 Draft

aviruthen
wants to merge
2
commits into

base:master
Choose a base branch

from

 Draft


fix: Add additional dependencies for ModelTrainer (5668)
#5731
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
19a3c1d

fix: Add additional dependencies for ModelTrainer (5668)


aviruthen Apr 7, 2026
4deb5ef

fix: address review comments (iteration #1)


aviruthen Apr 7, 2026

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


6 changes: 6 additions & 0 deletions
sagemaker-core/src/sagemaker/core/training/configs.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -109,6 +109,10 @@ class SourceCode(BaseConfig):
 ignore_patterns: (Optional[List[str]]) :
 The ignore patterns to ignore specific files/folders when uploading to S3. If not specified,
 default to: ['.env', '.git', '__pycache__', '.DS_Store', '.cache', '.ipynb_checkpoints'].
 dependencies (Optional[List[str]]):
 A list of paths to local directories (absolute or relative) containing additional
 libraries that will be copied into the training container and added to PYTHONPATH.
 Each path must be a valid local directory or file.
 """

 source_dir: Optional[StrPipeVar] = None
Expand All@@ -123,6 +127,8 @@ class SourceCode(BaseConfig):
 ".cache",
 ".ipynb_checkpoints",
 ]
Comment thread
aviruthen marked this conversation as resolved.

 dependencies: Optional[List[str]] = None


class OutputDataConfig(shapes.OutputDataConfig):
 """OutputDataConfig.
Expand Down

5 changes: 4 additions & 1 deletion
sagemaker-train/src/sagemaker/train/constants.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -63,6 +63,9 @@
 "amazon.nova-pro-v1:0": ["us-east-1"]
}

Comment thread
aviruthen marked this conversation as resolved.

SM_DEPENDENCIES = "sm_dependencies"
SM_DEPENDENCIES_CONTAINER_PATH = "/opt/ml/input/data/sm_dependencies"

SM_RECIPE = "recipe"
SM_RECIPE_YAML = "recipe.yaml"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"

36 changes: 36 additions & 0 deletions
sagemaker-train/src/sagemaker/train/model_trainer.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,6 +83,8 @@
 SM_CODE_CONTAINER_PATH,
 SM_DRIVERS,
 SM_DRIVERS_LOCAL_PATH,
 SM_DEPENDENCIES,
 SM_DEPENDENCIES_CONTAINER_PATH,
 SM_RECIPE,
 SM_RECIPE_YAML,
 SM_RECIPE_CONTAINER_PATH,
Expand All@@ -99,6 +101,7 @@
 EXECUTE_BASIC_SCRIPT_DRIVER,
 INSTALL_AUTO_REQUIREMENTS,
 INSTALL_REQUIREMENTS,
 INSTALL_DEPENDENCIES,
)
from sagemaker.core.telemetry.telemetry_logging import _telemetry_emitter
from sagemaker.core.telemetry.constants import Feature
Expand DownExpand Up@@ -269,6 +272,7 @@ class ModelTrainer(BaseModel):

 # Private Attributes for AWS_Batch
 _temp_code_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)
 _temp_deps_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)

 CONFIGURABLE_ATTRIBUTES: ClassVar[List[str]] = [
 "role",
Expand DownExpand Up@@ -408,6 +412,8 @@ def __del__(self):
 self._temp_recipe_train_dir.cleanup()
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()

 def _validate_training_image_and_algorithm_name(
 self, training_image: Optional[str], algorithm_name: Optional[str]
Expand DownExpand Up@@ -484,6 +490,13 @@ def _validate_source_code(self, source_code: Optional[SourceCode]):
 f"Invalid 'entry_script': {entry_script}. "
 "Must be a valid file within the 'source_dir'.",
 )
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 for dep_path in source_code.dependencies:
 if not _is_valid_path(dep_path, path_type="Directory"):
 raise ValueError(
 f"Invalid dependency path: {dep_path}. "
 "Each dependency must be a valid local directory path."
 )

 @staticmethod
 def _validate_and_fetch_hyperparameters_file(hyperparameters_file: str):
Expand DownExpand Up@@ -654,6 +667,21 @@ def _create_training_job_args(
 )
 final_input_data_config.append(source_code_channel)

 # If dependencies are provided, create a channel for the dependencies
 # The dependencies will be mounted at /opt/ml/input/data/sm_dependencies
 if self.source_code.dependencies:
 self._temp_deps_dir = TemporaryDirectory()
 for dep_path in self.source_code.dependencies:
 dep_basename = os.path.basename(os.path.normpath(dep_path))
 dest_path = os.path.join(self._temp_deps_dir.name, dep_basename)
 shutil.copytree(dep_path, dest_path, dirs_exist_ok=True)
 dependencies_channel = self.create_input_data_channel(
 channel_name=SM_DEPENDENCIES,
 data_source=self._temp_deps_dir.name,
 key_prefix=input_data_key_prefix,
 )
 final_input_data_config.append(dependencies_channel)

 self._prepare_train_script(
 tmp_dir=self._temp_code_dir,
 source_code=self.source_code,
Expand DownExpand Up@@ -813,6 +841,9 @@ def train(
 local_container.train(wait)
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()
 self._temp_deps_dir = None


 def create_input_data_channel(
Expand DownExpand Up@@ -1010,6 +1041,10 @@ def _prepare_train_script(
 base_command = source_code.command.split()
 base_command = " ".join(base_command)

 install_dependencies = ""
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 install_dependencies = INSTALL_DEPENDENCIES

 install_requirements = ""
 if source_code.requirements:
 if self._jumpstart_config and source_code.requirements == "auto":
Expand DownExpand Up@@ -1049,6 +1084,7 @@ def _prepare_train_script(

 train_script = TRAIN_SCRIPT_TEMPLATE.format(
 working_dir=working_dir,
 install_dependencies=install_dependencies,
 install_requirements=install_requirements,
 execute_driver=execute_driver,
 )
Expand Down

24 changes: 24 additions & 0 deletions
sagemaker-train/src/sagemaker/train/templates.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -39,6 +39,29 @@
$SM_PIP_CMD install -r {requirements_file}
"""

INSTALL_DEPENDENCIES = """
Comment thread
aviruthen marked this conversation as resolved.

echo "Setting up additional dependencies"
if [ -d /opt/ml/input/data/sm_dependencies ]; then
 for dep in /opt/ml/input/data/sm_dependencies/*; do
 if [ -d "$dep" ]; then
 echo "Adding directory $dep to PYTHONPATH"
 export PYTHONPATH="$dep:$PYTHONPATH"
 elif [ -f "$dep" ]; then
 case "$dep" in
 *.whl|*.tar.gz)
 echo "Installing package $dep via pip"
 $SM_PIP_CMD install "$dep"
 ;;
 *)
 echo "Adding parent directory of $dep to PYTHONPATH"
 export PYTHONPATH="/opt/ml/input/data/sm_dependencies:$PYTHONPATH"
 ;;
 esac
 fi
 done
fi
"""

EXEUCTE_DISTRIBUTED_DRIVER = """
echo "Running {driver_name} Driver"
$SM_PYTHON_CMD /opt/ml/input/data/sm_drivers/distributed_drivers/{driver_script}
Expand DownExpand Up@@ -95,6 +118,7 @@
set -x

{working_dir}
{install_dependencies}
{install_requirements}
{execute_driver}

Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
fix: Add additional dependencies for ModelTrainer (5668)#5731

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

 Draft

aviruthen
wants to merge
2
commits into

base:master
Choose a base branch

from

 Draft


fix: Add additional dependencies for ModelTrainer (5668)
#5731
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
19a3c1d

fix: Add additional dependencies for ModelTrainer (5668)


aviruthen Apr 7, 2026
4deb5ef

fix: address review comments (iteration #1)


aviruthen Apr 7, 2026

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


6 changes: 6 additions & 0 deletions
sagemaker-core/src/sagemaker/core/training/configs.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -109,6 +109,10 @@ class SourceCode(BaseConfig):
 ignore_patterns: (Optional[List[str]]) :
 The ignore patterns to ignore specific files/folders when uploading to S3. If not specified,
 default to: ['.env', '.git', '__pycache__', '.DS_Store', '.cache', '.ipynb_checkpoints'].
 dependencies (Optional[List[str]]):
 A list of paths to local directories (absolute or relative) containing additional
 libraries that will be copied into the training container and added to PYTHONPATH.
 Each path must be a valid local directory or file.
 """

 source_dir: Optional[StrPipeVar] = None
Expand All@@ -123,6 +127,8 @@ class SourceCode(BaseConfig):
 ".cache",
 ".ipynb_checkpoints",
 ]
Comment thread
aviruthen marked this conversation as resolved.

 dependencies: Optional[List[str]] = None


class OutputDataConfig(shapes.OutputDataConfig):
 """OutputDataConfig.
Expand Down

5 changes: 4 additions & 1 deletion
sagemaker-train/src/sagemaker/train/constants.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -63,6 +63,9 @@
 "amazon.nova-pro-v1:0": ["us-east-1"]
}

Comment thread
aviruthen marked this conversation as resolved.

SM_DEPENDENCIES = "sm_dependencies"
SM_DEPENDENCIES_CONTAINER_PATH = "/opt/ml/input/data/sm_dependencies"

SM_RECIPE = "recipe"
SM_RECIPE_YAML = "recipe.yaml"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"

36 changes: 36 additions & 0 deletions
sagemaker-train/src/sagemaker/train/model_trainer.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,6 +83,8 @@
 SM_CODE_CONTAINER_PATH,
 SM_DRIVERS,
 SM_DRIVERS_LOCAL_PATH,
 SM_DEPENDENCIES,
 SM_DEPENDENCIES_CONTAINER_PATH,
 SM_RECIPE,
 SM_RECIPE_YAML,
 SM_RECIPE_CONTAINER_PATH,
Expand All@@ -99,6 +101,7 @@
 EXECUTE_BASIC_SCRIPT_DRIVER,
 INSTALL_AUTO_REQUIREMENTS,
 INSTALL_REQUIREMENTS,
 INSTALL_DEPENDENCIES,
)
from sagemaker.core.telemetry.telemetry_logging import _telemetry_emitter
from sagemaker.core.telemetry.constants import Feature
Expand DownExpand Up@@ -269,6 +272,7 @@ class ModelTrainer(BaseModel):

 # Private Attributes for AWS_Batch
 _temp_code_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)
 _temp_deps_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)

 CONFIGURABLE_ATTRIBUTES: ClassVar[List[str]] = [
 "role",
Expand DownExpand Up@@ -408,6 +412,8 @@ def __del__(self):
 self._temp_recipe_train_dir.cleanup()
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()

 def _validate_training_image_and_algorithm_name(
 self, training_image: Optional[str], algorithm_name: Optional[str]
Expand DownExpand Up@@ -484,6 +490,13 @@ def _validate_source_code(self, source_code: Optional[SourceCode]):
 f"Invalid 'entry_script': {entry_script}. "
 "Must be a valid file within the 'source_dir'.",
 )
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 for dep_path in source_code.dependencies:
 if not _is_valid_path(dep_path, path_type="Directory"):
 raise ValueError(
 f"Invalid dependency path: {dep_path}. "
 "Each dependency must be a valid local directory path."
 )

 @staticmethod
 def _validate_and_fetch_hyperparameters_file(hyperparameters_file: str):
Expand DownExpand Up@@ -654,6 +667,21 @@ def _create_training_job_args(
 )
 final_input_data_config.append(source_code_channel)

 # If dependencies are provided, create a channel for the dependencies
 # The dependencies will be mounted at /opt/ml/input/data/sm_dependencies
 if self.source_code.dependencies:
 self._temp_deps_dir = TemporaryDirectory()
 for dep_path in self.source_code.dependencies:
 dep_basename = os.path.basename(os.path.normpath(dep_path))
 dest_path = os.path.join(self._temp_deps_dir.name, dep_basename)
 shutil.copytree(dep_path, dest_path, dirs_exist_ok=True)
 dependencies_channel = self.create_input_data_channel(
 channel_name=SM_DEPENDENCIES,
 data_source=self._temp_deps_dir.name,
 key_prefix=input_data_key_prefix,
 )
 final_input_data_config.append(dependencies_channel)

 self._prepare_train_script(
 tmp_dir=self._temp_code_dir,
 source_code=self.source_code,
Expand DownExpand Up@@ -813,6 +841,9 @@ def train(
 local_container.train(wait)
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()
 self._temp_deps_dir = None


 def create_input_data_channel(
Expand DownExpand Up@@ -1010,6 +1041,10 @@ def _prepare_train_script(
 base_command = source_code.command.split()
 base_command = " ".join(base_command)

 install_dependencies = ""
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 install_dependencies = INSTALL_DEPENDENCIES

 install_requirements = ""
 if source_code.requirements:
 if self._jumpstart_config and source_code.requirements == "auto":
Expand DownExpand Up@@ -1049,6 +1084,7 @@ def _prepare_train_script(

 train_script = TRAIN_SCRIPT_TEMPLATE.format(
 working_dir=working_dir,
 install_dependencies=install_dependencies,
 install_requirements=install_requirements,
 execute_driver=execute_driver,
 )
Expand Down

24 changes: 24 additions & 0 deletions
sagemaker-train/src/sagemaker/train/templates.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -39,6 +39,29 @@
$SM_PIP_CMD install -r {requirements_file}
"""

INSTALL_DEPENDENCIES = """
Comment thread
aviruthen marked this conversation as resolved.

echo "Setting up additional dependencies"
if [ -d /opt/ml/input/data/sm_dependencies ]; then
 for dep in /opt/ml/input/data/sm_dependencies/*; do
 if [ -d "$dep" ]; then
 echo "Adding directory $dep to PYTHONPATH"
 export PYTHONPATH="$dep:$PYTHONPATH"
 elif [ -f "$dep" ]; then
 case "$dep" in
 *.whl|*.tar.gz)
 echo "Installing package $dep via pip"
 $SM_PIP_CMD install "$dep"
 ;;
 *)
 echo "Adding parent directory of $dep to PYTHONPATH"
 export PYTHONPATH="/opt/ml/input/data/sm_dependencies:$PYTHONPATH"
 ;;
 esac
 fi
 done
fi
"""

EXEUCTE_DISTRIBUTED_DRIVER = """
echo "Running {driver_name} Driver"
$SM_PYTHON_CMD /opt/ml/input/data/sm_drivers/distributed_drivers/{driver_script}
Expand DownExpand Up@@ -95,6 +118,7 @@
set -x

{working_dir}
{install_dependencies}
{install_requirements}
{execute_driver}

Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
fix: Add additional dependencies for ModelTrainer (5668)#5731

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

 Draft

aviruthen
wants to merge
2
commits into

base:master
Choose a base branch

from

 Draft


fix: Add additional dependencies for ModelTrainer (5668)
#5731
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
19a3c1d

fix: Add additional dependencies for ModelTrainer (5668)


aviruthen Apr 7, 2026
4deb5ef

fix: address review comments (iteration #1)


aviruthen Apr 7, 2026

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


6 changes: 6 additions & 0 deletions
sagemaker-core/src/sagemaker/core/training/configs.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -109,6 +109,10 @@ class SourceCode(BaseConfig):
 ignore_patterns: (Optional[List[str]]) :
 The ignore patterns to ignore specific files/folders when uploading to S3. If not specified,
 default to: ['.env', '.git', '__pycache__', '.DS_Store', '.cache', '.ipynb_checkpoints'].
 dependencies (Optional[List[str]]):
 A list of paths to local directories (absolute or relative) containing additional
 libraries that will be copied into the training container and added to PYTHONPATH.
 Each path must be a valid local directory or file.
 """

 source_dir: Optional[StrPipeVar] = None
Expand All@@ -123,6 +127,8 @@ class SourceCode(BaseConfig):
 ".cache",
 ".ipynb_checkpoints",
 ]
Comment thread
aviruthen marked this conversation as resolved.

 dependencies: Optional[List[str]] = None


class OutputDataConfig(shapes.OutputDataConfig):
 """OutputDataConfig.
Expand Down

5 changes: 4 additions & 1 deletion
sagemaker-train/src/sagemaker/train/constants.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -63,6 +63,9 @@
 "amazon.nova-pro-v1:0": ["us-east-1"]
}

Comment thread
aviruthen marked this conversation as resolved.

SM_DEPENDENCIES = "sm_dependencies"
SM_DEPENDENCIES_CONTAINER_PATH = "/opt/ml/input/data/sm_dependencies"

SM_RECIPE = "recipe"
SM_RECIPE_YAML = "recipe.yaml"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"

36 changes: 36 additions & 0 deletions
sagemaker-train/src/sagemaker/train/model_trainer.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,6 +83,8 @@
 SM_CODE_CONTAINER_PATH,
 SM_DRIVERS,
 SM_DRIVERS_LOCAL_PATH,
 SM_DEPENDENCIES,
 SM_DEPENDENCIES_CONTAINER_PATH,
 SM_RECIPE,
 SM_RECIPE_YAML,
 SM_RECIPE_CONTAINER_PATH,
Expand All@@ -99,6 +101,7 @@
 EXECUTE_BASIC_SCRIPT_DRIVER,
 INSTALL_AUTO_REQUIREMENTS,
 INSTALL_REQUIREMENTS,
 INSTALL_DEPENDENCIES,
)
from sagemaker.core.telemetry.telemetry_logging import _telemetry_emitter
from sagemaker.core.telemetry.constants import Feature
Expand DownExpand Up@@ -269,6 +272,7 @@ class ModelTrainer(BaseModel):

 # Private Attributes for AWS_Batch
 _temp_code_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)
 _temp_deps_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)

 CONFIGURABLE_ATTRIBUTES: ClassVar[List[str]] = [
 "role",
Expand DownExpand Up@@ -408,6 +412,8 @@ def __del__(self):
 self._temp_recipe_train_dir.cleanup()
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()

 def _validate_training_image_and_algorithm_name(
 self, training_image: Optional[str], algorithm_name: Optional[str]
Expand DownExpand Up@@ -484,6 +490,13 @@ def _validate_source_code(self, source_code: Optional[SourceCode]):
 f"Invalid 'entry_script': {entry_script}. "
 "Must be a valid file within the 'source_dir'.",
 )
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 for dep_path in source_code.dependencies:
 if not _is_valid_path(dep_path, path_type="Directory"):
 raise ValueError(
 f"Invalid dependency path: {dep_path}. "
 "Each dependency must be a valid local directory path."
 )

 @staticmethod
 def _validate_and_fetch_hyperparameters_file(hyperparameters_file: str):
Expand DownExpand Up@@ -654,6 +667,21 @@ def _create_training_job_args(
 )
 final_input_data_config.append(source_code_channel)

 # If dependencies are provided, create a channel for the dependencies
 # The dependencies will be mounted at /opt/ml/input/data/sm_dependencies
 if self.source_code.dependencies:
 self._temp_deps_dir = TemporaryDirectory()
 for dep_path in self.source_code.dependencies:
 dep_basename = os.path.basename(os.path.normpath(dep_path))
 dest_path = os.path.join(self._temp_deps_dir.name, dep_basename)
 shutil.copytree(dep_path, dest_path, dirs_exist_ok=True)
 dependencies_channel = self.create_input_data_channel(
 channel_name=SM_DEPENDENCIES,
 data_source=self._temp_deps_dir.name,
 key_prefix=input_data_key_prefix,
 )
 final_input_data_config.append(dependencies_channel)

 self._prepare_train_script(
 tmp_dir=self._temp_code_dir,
 source_code=self.source_code,
Expand DownExpand Up@@ -813,6 +841,9 @@ def train(
 local_container.train(wait)
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()
 self._temp_deps_dir = None


 def create_input_data_channel(
Expand DownExpand Up@@ -1010,6 +1041,10 @@ def _prepare_train_script(
 base_command = source_code.command.split()
 base_command = " ".join(base_command)

 install_dependencies = ""
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 install_dependencies = INSTALL_DEPENDENCIES

 install_requirements = ""
 if source_code.requirements:
 if self._jumpstart_config and source_code.requirements == "auto":
Expand DownExpand Up@@ -1049,6 +1084,7 @@ def _prepare_train_script(

 train_script = TRAIN_SCRIPT_TEMPLATE.format(
 working_dir=working_dir,
 install_dependencies=install_dependencies,
 install_requirements=install_requirements,
 execute_driver=execute_driver,
 )
Expand Down

24 changes: 24 additions & 0 deletions
sagemaker-train/src/sagemaker/train/templates.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -39,6 +39,29 @@
$SM_PIP_CMD install -r {requirements_file}
"""

INSTALL_DEPENDENCIES = """
Comment thread
aviruthen marked this conversation as resolved.

echo "Setting up additional dependencies"
if [ -d /opt/ml/input/data/sm_dependencies ]; then
 for dep in /opt/ml/input/data/sm_dependencies/*; do
 if [ -d "$dep" ]; then
 echo "Adding directory $dep to PYTHONPATH"
 export PYTHONPATH="$dep:$PYTHONPATH"
 elif [ -f "$dep" ]; then
 case "$dep" in
 *.whl|*.tar.gz)
 echo "Installing package $dep via pip"
 $SM_PIP_CMD install "$dep"
 ;;
 *)
 echo "Adding parent directory of $dep to PYTHONPATH"
 export PYTHONPATH="/opt/ml/input/data/sm_dependencies:$PYTHONPATH"
 ;;
 esac
 fi
 done
fi
"""

EXEUCTE_DISTRIBUTED_DRIVER = """
echo "Running {driver_name} Driver"
$SM_PYTHON_CMD /opt/ml/input/data/sm_drivers/distributed_drivers/{driver_script}
Expand DownExpand Up@@ -95,6 +118,7 @@
set -x

{working_dir}
{install_dependencies}
{install_requirements}
{execute_driver}

Expand Down
Loading
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
fix: Add additional dependencies for ModelTrainer (5668)#5731

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

 Draft

aviruthen
wants to merge
2
commits into

base:master
Choose a base branch

from

 Draft


fix: Add additional dependencies for ModelTrainer (5668)
#5731
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
19a3c1d

fix: Add additional dependencies for ModelTrainer (5668)


aviruthen Apr 7, 2026
4deb5ef

fix: address review comments (iteration #1)


aviruthen Apr 7, 2026

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


6 changes: 6 additions & 0 deletions
sagemaker-core/src/sagemaker/core/training/configs.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -109,6 +109,10 @@ class SourceCode(BaseConfig):
 ignore_patterns: (Optional[List[str]]) :
 The ignore patterns to ignore specific files/folders when uploading to S3. If not specified,
 default to: ['.env', '.git', '__pycache__', '.DS_Store', '.cache', '.ipynb_checkpoints'].
 dependencies (Optional[List[str]]):
 A list of paths to local directories (absolute or relative) containing additional
 libraries that will be copied into the training container and added to PYTHONPATH.
 Each path must be a valid local directory or file.
 """

 source_dir: Optional[StrPipeVar] = None
Expand All@@ -123,6 +127,8 @@ class SourceCode(BaseConfig):
 ".cache",
 ".ipynb_checkpoints",
 ]
Comment thread
aviruthen marked this conversation as resolved.

 dependencies: Optional[List[str]] = None


class OutputDataConfig(shapes.OutputDataConfig):
 """OutputDataConfig.
Expand Down

5 changes: 4 additions & 1 deletion
sagemaker-train/src/sagemaker/train/constants.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -63,6 +63,9 @@
 "amazon.nova-pro-v1:0": ["us-east-1"]
}

Comment thread
aviruthen marked this conversation as resolved.

SM_DEPENDENCIES = "sm_dependencies"
SM_DEPENDENCIES_CONTAINER_PATH = "/opt/ml/input/data/sm_dependencies"

SM_RECIPE = "recipe"
SM_RECIPE_YAML = "recipe.yaml"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"
SM_RECIPE_CONTAINER_PATH = f"/opt/ml/input/data/recipe/{SM_RECIPE_YAML}"

36 changes: 36 additions & 0 deletions
sagemaker-train/src/sagemaker/train/model_trainer.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,6 +83,8 @@
 SM_CODE_CONTAINER_PATH,
 SM_DRIVERS,
 SM_DRIVERS_LOCAL_PATH,
 SM_DEPENDENCIES,
 SM_DEPENDENCIES_CONTAINER_PATH,
 SM_RECIPE,
 SM_RECIPE_YAML,
 SM_RECIPE_CONTAINER_PATH,
Expand All@@ -99,6 +101,7 @@
 EXECUTE_BASIC_SCRIPT_DRIVER,
 INSTALL_AUTO_REQUIREMENTS,
 INSTALL_REQUIREMENTS,
 INSTALL_DEPENDENCIES,
)
from sagemaker.core.telemetry.telemetry_logging import _telemetry_emitter
from sagemaker.core.telemetry.constants import Feature
Expand DownExpand Up@@ -269,6 +272,7 @@ class ModelTrainer(BaseModel):

 # Private Attributes for AWS_Batch
 _temp_code_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)
 _temp_deps_dir: Optional[TemporaryDirectory] = PrivateAttr(default=None)

 CONFIGURABLE_ATTRIBUTES: ClassVar[List[str]] = [
 "role",
Expand DownExpand Up@@ -408,6 +412,8 @@ def __del__(self):
 self._temp_recipe_train_dir.cleanup()
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()

 def _validate_training_image_and_algorithm_name(
 self, training_image: Optional[str], algorithm_name: Optional[str]
Expand DownExpand Up@@ -484,6 +490,13 @@ def _validate_source_code(self, source_code: Optional[SourceCode]):
 f"Invalid 'entry_script': {entry_script}. "
 "Must be a valid file within the 'source_dir'.",
 )
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 for dep_path in source_code.dependencies:
 if not _is_valid_path(dep_path, path_type="Directory"):
 raise ValueError(
 f"Invalid dependency path: {dep_path}. "
 "Each dependency must be a valid local directory path."
 )

 @staticmethod
 def _validate_and_fetch_hyperparameters_file(hyperparameters_file: str):
Expand DownExpand Up@@ -654,6 +667,21 @@ def _create_training_job_args(
 )
 final_input_data_config.append(source_code_channel)

 # If dependencies are provided, create a channel for the dependencies
 # The dependencies will be mounted at /opt/ml/input/data/sm_dependencies
 if self.source_code.dependencies:
 self._temp_deps_dir = TemporaryDirectory()
 for dep_path in self.source_code.dependencies:
 dep_basename = os.path.basename(os.path.normpath(dep_path))
 dest_path = os.path.join(self._temp_deps_dir.name, dep_basename)
 shutil.copytree(dep_path, dest_path, dirs_exist_ok=True)
 dependencies_channel = self.create_input_data_channel(
 channel_name=SM_DEPENDENCIES,
 data_source=self._temp_deps_dir.name,
 key_prefix=input_data_key_prefix,
 )
 final_input_data_config.append(dependencies_channel)

 self._prepare_train_script(
 tmp_dir=self._temp_code_dir,
 source_code=self.source_code,
Expand DownExpand Up@@ -813,6 +841,9 @@ def train(
 local_container.train(wait)
 if self._temp_code_dir is not None:
 self._temp_code_dir.cleanup()
 if self._temp_deps_dir is not None:
 self._temp_deps_dir.cleanup()
 self._temp_deps_dir = None


 def create_input_data_channel(
Expand DownExpand Up@@ -1010,6 +1041,10 @@ def _prepare_train_script(
 base_command = source_code.command.split()
 base_command = " ".join(base_command)

 install_dependencies = ""
Comment thread
aviruthen marked this conversation as resolved.

 if source_code.dependencies:
 install_dependencies = INSTALL_DEPENDENCIES

 install_requirements = ""
 if source_code.requirements:
 if self._jumpstart_config and source_code.requirements == "auto":
Expand DownExpand Up@@ -1049,6 +1084,7 @@ def _prepare_train_script(

 train_script = TRAIN_SCRIPT_TEMPLATE.format(
 working_dir=working_dir,
 install_dependencies=install_dependencies,
 install_requirements=install_requirements,
 execute_driver=execute_driver,
 )
Expand Down

24 changes: 24 additions & 0 deletions
sagemaker-train/src/sagemaker/train/templates.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -39,6 +39,29 @@
$SM_PIP_CMD install -r {requirements_file}
"""

INSTALL_DEPENDENCIES = """
Comment thread
aviruthen marked this conversation as resolved.

echo "Setting up additional dependencies"
if [ -d /opt/ml/input/data/sm_dependencies ]; then
 for dep in /opt/ml/input/data/sm_dependencies/*; do
 if [ -d "$dep" ]; then
 echo "Adding directory $dep to PYTHONPATH"
 export PYTHONPATH="$dep:$PYTHONPATH"
 elif [ -f "$dep" ]; then
 case "$dep" in
 *.whl|*.tar.gz)
 echo "Installing package $dep via pip"
 $SM_PIP_CMD install "$dep"
 ;;
 *)
 echo "Adding parent directory of $dep to PYTHONPATH"
 export PYTHONPATH="/opt/ml/input/data/sm_dependencies:$PYTHONPATH"
 ;;
 esac
 fi
 done
fi
"""

EXEUCTE_DISTRIBUTED_DRIVER = """
echo "Running {driver_name} Driver"
$SM_PYTHON_CMD /opt/ml/input/data/sm_drivers/distributed_drivers/{driver_script}
Expand DownExpand Up@@ -95,6 +118,7 @@
set -x

{working_dir}
{install_dependencies}
{install_requirements}
{execute_driver}

Expand Down
Loading
Loading