Skip to content

Commit

Permalink
add integration tests for AWS Neuron (aws#416)
Browse files Browse the repository at this point in the history
  • Loading branch information
aditya-purang authored Aug 21, 2024
1 parent 8c00f9f commit 766e41a
Show file tree
Hide file tree
Showing 20 changed files with 2,464 additions and 18 deletions.
32 changes: 32 additions & 0 deletions docs/resources/dummy-neuron-monitor/Dockerfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# set the base image
FROM public.ecr.aws/docker/library/ubuntu:20.04

# Set the working directory in the container
WORKDIR /root

# Neuron SDK components version numbers
ARG NEURONX_RUNTIME_LIB_VERSION=2.19.*
ARG NEURONX_COLLECTIVES_LIB_VERSION=2.19.*
ARG NEURONX_TOOLS_VERSION=2.17.*

# Install any necessary dependencies or tools
RUN apt-get update && apt-get install vim wget zip unzip sudo python3-pip -y

# Import Neuron GPG public key
RUN echo "deb https://apt.repos.neuron.amazonaws.com focal main" > /etc/apt/sources.list.d/neuron.list
RUN wget -qO - https://apt.repos.neuron.amazonaws.com/GPG-PUB-KEY-AMAZON-AWS-NEURON.PUB | apt-key add -


# Install Neuron Runtime and Neuron Tools
RUN apt-get update \
&& apt-get install -y \
aws-neuronx-tools=$NEURONX_TOOLS_VERSION \
aws-neuronx-collectives=$NEURONX_COLLECTIVES_LIB_VERSION \
aws-neuronx-runtime-lib=$NEURONX_RUNTIME_LIB_VERSION \
&& rm -rf /var/lib/apt/lists/* \
&& rm -rf /tmp/tmp* \
&& apt-get clean

COPY dummy_neuron_monitor.py /opt/aws/neuron/bin/dummy_neuron_monitor.py
RUN chmod 755 /opt/aws/neuron/bin/dummy_neuron_monitor.py
RUN pip3 install prometheus_client boto3 requests
890 changes: 890 additions & 0 deletions docs/resources/dummy-neuron-monitor/dummy_neuron_monitor.py

Large diffs are not rendered by default.

4 changes: 4 additions & 0 deletions generator/test_case_generator.go
Original file line number Diff line number Diff line change
Expand Up @@ -223,6 +223,10 @@ var testTypeToTestConfig = map[string][]testConfig{
testDir: "./test/gpu", terraformDir: "terraform/eks/daemon/gpu",
targets: map[string]map[string]struct{}{"arc": {"amd64": {}}},
},
{
testDir: "./test/awsneuron", terraformDir: "terraform/eks/daemon/awsneuron",
targets: map[string]map[string]struct{}{"arc": {"amd64": {}}},
},
},
"eks_deployment": {
{testDir: "./test/metric_value_benchmark"},
Expand Down
Loading

0 comments on commit 766e41a

Please sign in to comment.