patch hf pt inference (#5553)

* patch hf pt inference

* test hf

* install requirements.txt

* revert toml

Author: sirutBuasai

huggingface/pytorch/inference/docker/2.6/py3/Dockerfile.cpu

@@ -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"
 

huggingface/pytorch/inference/docker/2.6/py3/cu124/Dockerfile.gpu

@@ -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"
 

test/sagemaker_tests/pytorch/inference/pytorch-inference-requirements.txt

@@ -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

test/sagemaker_tests/pytorch/inference/requirements.txt

@@ -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