Skip to content

patch hf pt inference #5553

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

Open
sirutBuasai wants to merge 4 commits into
base: master
Choose a base branch
from
+11 −37
Open

patch hf pt inference #5553

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f0cdc3a
patch hf pt inference
sirutBuasai Dec 12, 2025
4c1f0c3
test hf
sirutBuasai Dec 12, 2025
fc14a95
install requirements.txt
sirutBuasai Dec 13, 2025
d29aadf
revert toml
sirutBuasai Dec 13, 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
3 changes: 2 additions & 1 deletion huggingface/pytorch/inference/docker/2.6/py3/Dockerfile.cpu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,8 @@ RUN pip install --no-cache-dir --extra-index-url https://download.pytorch.org/wh
"cryptography>=42.0.5" \
"ipython>=8.10.0,<9.0" \
"awscli<2" \
"urllib3>=1.26.18,<2" \
"urllib3>=2.6" \
"brotli>1.1" \
"prompt-toolkit<3.0.39" \
"setuptools>=70.0.0"

Expand Down
5 changes: 3 additions & 2 deletions huggingface/pytorch/inference/docker/2.6/py3/cu124/Dockerfile.gpu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,15 +194,16 @@ RUN pip install --no-cache-dir -U \
scipy \
# "nvgpu" is a dependency of TS but is disabled in SM DLC build,
# via ENV Variable "TS_DISABLE_SYSTEM_METRICS=true" in the SM section of this file.
# due to incompatibility with SM hosts
# due to incompatibility with SM hosts
nvgpu \
"pyopenssl>=24.0.0" \
enum-compat==0.0.3 \
captum \
"Pillow>=9.0.0" \
"cryptography>=42.0.5" \
"ipython>=8.10.0,<9.0" \
"urllib3>=1.26.18,<2" \
"urllib3>=2.6" \
"brotli>1.1" \
"prompt-toolkit<3.0.39" \
"setuptools>=70.0.0"

Expand Down
30 changes: 0 additions & 30 deletions test/sagemaker_tests/pytorch/inference/pytorch-inference-requirements.txt
View file
Open in desktop

This file was deleted.

5 changes: 5 additions & 0 deletions test/sagemaker_tests/pytorch/inference/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,10 @@
boto3
coverage
# SageMaker PyTorch Inference Toolkit still use docker compose v1
# https://github.com/aws/sagemaker-pytorch-inference-toolkit/blob/v2.0.25/setup.py#L58
# Docker v7.0.0 breaks compatibility with Docker Compose v1 (SageMaker Local)
docker==6.1.3
docker-compose
Flask==1.1.1
fabric
flake8==3.7.7
Expand Down
5 changes: 1 addition & 4 deletions test/test_utils/sagemaker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -347,10 +347,7 @@ def execute_local_tests(image, pytest_cache_params):
ec2_conn.run("sudo chmod +x /usr/local/bin/docker-compose")

with ec2_conn.cd(path):
if "pytorch-inference" in image:
ec2_conn.run(f"pip install -r pytorch-inference-requirements.txt")
else:
ec2_conn.run(f"pip install -r requirements.txt")
ec2_conn.run(f"pip install -r requirements.txt")

pytest_cache_util.download_pytest_cache_from_s3_to_ec2(
ec2_conn, path, **pytest_cache_params
Expand Down