updated versions

Author: philschmid

README.md

@@ -71,7 +71,7 @@ mkdir tmp2/
 AIP_MODE=PREDICTION AIP_PORT=8080 AIP_PREDICT_ROUTE=/pred AIP_HEALTH_ROUTE=/h HF_MODEL_DIR=tmp2 HF_MODEL_ID=distilbert/distilbert-base-uncased-finetuned-sst-2-english HF_TASK=text-classification uvicorn src.huggingface_inference_toolkit.webservice_starlette:app  --port 8080
 ```
 
-Send request. The API schema is the same as from the [inference API](https://huggingface.co/docs/api-inference/detailed_parameters)
+Send request
 
 ```bash
 curl --request POST \
@@ -83,6 +83,31 @@ curl --request POST \
 }'
 ```
 
+#### Container run with HF_MODEL_ID and HF_TASK
+
+1. build the preferred container for either CPU or GPU for PyTorch o.
+
+```bash
+docker build -t vertex -f dockerfiles/pytorch/Dockerfile -t vertex-test-pytorch:gpu .
+```
+
+2. Run the container and provide either environment variables to the HUB model you want to use or mount a volume to the container, where your model is stored.
+
+```bash
+docker run -ti -p 8080:8080 -e AIP_MODE=PREDICTION -e AIP_HTTP_PORT=8080 -e AIP_PREDICT_ROUTE=/pred -e AIP_HEALTH_ROUTE=/h -e HF_MODEL_ID=distilbert/distilbert-base-uncased-finetuned-sst-2-english -e HF_TASK=text-classification vertex-test-pytorch:gpu
+```
+
+1. Send request
+
+```bash
+curl --request POST \
+	--url http://localhost:8080/pred \
+	--header 'Content-Type: application/json' \
+	--data '{
+	"instances": ["I love this product", "I hate this product"],
+	"parameters": { "top_k": 2 }
+}'
+```
 
 
 ---

dockerfiles/inference-endpoints/Dockerfile

@@ -1,6 +1,6 @@
 ARG BASE_IMAGE=nvidia/cuda:12.1.0-devel-ubuntu22.04
 
-FROM $BASE_IMAGE
+FROM $BASE_IMAGE as base 
 SHELL ["/bin/bash", "-c"]
 
 LABEL maintainer="Hugging Face"
@@ -45,4 +45,10 @@ COPY src/huggingface_inference_toolkit/webservice_starlette.py webservice_starle
 # copy entrypoint and change permissions
 COPY --chmod=0755  scripts/entrypoint.sh entrypoint.sh
 
-ENTRYPOINT ["bash", "-c", "./entrypoint.sh"]
+ENTRYPOINT ["bash", "-c", "./entrypoint.sh"]
+
+
+from base as vertex
+
+# Install Vertex AI requiremented packages
+RUN pip install --no-cache-dir google-cloud-storage

dockerfiles/pytorch/Dockerfile

@@ -26,5 +26,11 @@ inference-pytorch-gpu:
 inference-pytorch-cpu:
 	docker build --build-arg="BASE_IMAGE=ubuntu:22.04" -f dockerfiles/pytorch/Dockerfile -t integration-test-pytorch:cpu .
 
+vertex-pytorch-gpu:
+	docker build -t vertex -f dockerfiles/pytorch/Dockerfile -t integration-test-pytorch:gpu .
+
+vertex-pytorch-cpu:
+	docker build  -t vertex --build-arg="BASE_IMAGE=ubuntu:22.04" -f dockerfiles/pytorch/Dockerfile -t integration-test-pytorch:cpu .
+
 stop-all:
 	docker stop $$(docker ps -a -q) && docker container prune --force

dockerfiles/tensorflow/cpu/Dockerfile

@@ -1,24 +1,18 @@
 from __future__ import absolute_import
-from datetime import date
 from setuptools import find_packages, setup
 
 # We don't declare our dependency on transformers here because we build with
 # different packages for different variants
 
 VERSION = "0.3.0"
 
-
 # Ubuntu packages
 # libsndfile1-dev: torchaudio requires the development version of the libsndfile package which can be installed via a system package manager. On Ubuntu it can be installed as follows: apt install libsndfile1-dev
 # ffmpeg: ffmpeg is required for audio processing. On Ubuntu it can be installed as follows: apt install ffmpeg
 # libavcodec-extra : libavcodec-extra  inculdes additional codecs for ffmpeg
 
 install_requires = [
-    "wheel==0.42.0",
-    "setuptools==69.1.0",
-    "cmake==3.28.3",
-    "transformers[sklearn,sentencepiece, audio, vision]==4.38.2",
-    "huggingface_hub==0.20.3",
+    "transformers[sklearn,sentencepiece, audio,vision]==4.41.1",
     "orjson",
     # vision
     "Pillow",
@@ -31,15 +25,14 @@
     "starlette",
     "uvicorn",
     "pandas",
-    "peft==0.9.0"
+    "peft==0.11.1"
 ]
 
 extras = {}
 
-extras["st"] = ["sentence_transformers==2.4.0"]
-extras["diffusers"] = ["diffusers==0.26.3", "accelerate==0.27.2"]
-extras["torch"] = ["torch==2.2.0", "torchvision", "torchaudio"]
-extras["tensorflow"] = ["tensorflow"]
+extras["st"] = ["sentence_transformers==2.7.0"]
+extras["diffusers"] = ["diffusers==0.28.0", "accelerate==0.30.1"]
+extras["torch"] = ["torch==2.3.0", "torchvision", "torchaudio"]
 extras["test"] = [
     "pytest==7.2.1",
     "pytest-xdist",