From c29def20ce515b0ffbba5cc028435bb37d8939f0 Mon Sep 17 00:00:00 2001
From: David Corvoysier <david@huggingface.co>
Date: Mon, 13 Nov 2023 12:44:16 +0000
Subject: [PATCH 1/2] fix(pipelines): support passing decoder model + tokenizer

---
 optimum/neuron/pipelines/transformers/base.py |  2 +-
 tests/pipelines/test_decoder_pipelines.py     | 10 ++++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/optimum/neuron/pipelines/transformers/base.py b/optimum/neuron/pipelines/transformers/base.py
index f054dad1c..0aa14dd4c 100644
--- a/optimum/neuron/pipelines/transformers/base.py
+++ b/optimum/neuron/pipelines/transformers/base.py
@@ -123,7 +123,7 @@ def load_pipeline(
             model, export=export, **compiler_args, **input_shapes, **hub_kwargs, **kwargs
         )
     # uses neuron model
-    elif isinstance(model, NeuronBaseModel):
+    elif isinstance(model, (NeuronBaseModel, NeuronModelForCausalLM)):
         if tokenizer is None and load_tokenizer:
             for preprocessor in model.preprocessors:
                 if isinstance(preprocessor, (PreTrainedTokenizer, PreTrainedTokenizerFast)):
diff --git a/tests/pipelines/test_decoder_pipelines.py b/tests/pipelines/test_decoder_pipelines.py
index 0a71b3b8f..6b58a5ff7 100644
--- a/tests/pipelines/test_decoder_pipelines.py
+++ b/tests/pipelines/test_decoder_pipelines.py
@@ -1,6 +1,7 @@
 import itertools
 
 import pytest
+from transformers import AutoTokenizer
 
 from optimum.neuron import NeuronModelForCausalLM
 from optimum.neuron.pipelines import pipeline
@@ -54,6 +55,15 @@ def test_load_no_parameters(inf_decoder_path):
     _test_generation(p)
 
 
+@is_inferentia_test
+@requires_neuronx
+def test_from_model_and_tokenizer(inf_decoder_path):
+    m = NeuronModelForCausalLM.from_pretrained(inf_decoder_path)
+    t = AutoTokenizer.from_pretrained(inf_decoder_path)
+    p = pipeline("text-generation", model=m, tokenizer=t)
+    _test_generation(p)
+
+
 @is_inferentia_test
 @requires_neuronx
 def test_error_already_exported(inf_decoder_path):

From 3d8e2e621618e02a29837a4b8be255e7c781cdf2 Mon Sep 17 00:00:00 2001
From: Guillaume LEGENDRE <glegendre01@gmail.com>
Date: Fri, 10 Nov 2023 09:24:26 +0100
Subject: [PATCH 2/2] Remove EC2 jobs

We also remove driver reinstallation step
---
 .github/workflows/test_inf1.yml | 76 +--------------------------------
 1 file changed, 1 insertion(+), 75 deletions(-)

diff --git a/.github/workflows/test_inf1.yml b/.github/workflows/test_inf1.yml
index d7b6b589d..7f2602ca8 100644
--- a/.github/workflows/test_inf1.yml
+++ b/.github/workflows/test_inf1.yml
@@ -15,65 +15,14 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  start-runner:
-    name: Start self-hosted EC2 runner
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: us-east-1
-      EC2_AMI_ID: ${{ vars.INFERENTIA_AMI_ID }}
-      EC2_INSTANCE_TYPE: inf1.6xlarge
-      EC2_SUBNET_ID: subnet-859322b4,subnet-b7533b96,subnet-47cfad21,subnet-a396b2ad,subnet-06576a4b,subnet-df0f6180
-      EC2_SECURITY_GROUP: sg-0bb210cd3ec725a13
-      EC2_IAM_ROLE: optimum-ec2-github-actions-role
-    outputs:
-      label: ${{ steps.start-ec2-runner.outputs.label }}
-      ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Start EC2 runner
-        id: start-ec2-runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: start
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          ec2-image-id: ${{ env.EC2_AMI_ID }}
-          ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
-          subnet-id: ${{ env.EC2_SUBNET_ID }}
-          security-group-id: ${{ env.EC2_SECURITY_GROUP }}
-          iam-role-name: ${{ env.EC2_IAM_ROLE }}
-          aws-resource-tags: > # optional, requires additional permissions
-            [
-              {"Key": "Name", "Value": "ec2-optimum-github-runner"},
-              {"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
-            ]
   do-the-job:
     name: Run INF1 tests
-    needs: start-runner # required to start the main job when the runner is ready
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
+    runs-on: [self-hosted, 4-aws-inf1, 24-cpu, ci]
     env:
       AWS_REGION: us-east-1
     steps:
       - name: Checkout
         uses: actions/checkout@v2
-      - name: Re-install neuron driver
-        run: |
-          sudo apt remove aws-neuronx-dkms -y
-          sudo apt remove aws-neuronx-tools -y
-          . /etc/os-release
-          sudo tee /etc/apt/sources.list.d/neuron.list > /dev/null <<EOF
-          deb https://apt.repos.neuron.amazonaws.com ${VERSION_CODENAME} main
-          EOF
-          wget -qO - https://apt.repos.neuron.amazonaws.com/GPG-PUB-KEY-AMAZON-AWS-NEURON.PUB | sudo apt-key add -
-          sudo apt-get update -y
-          sudo apt-get install linux-headers-$(uname -r) -y
-          sudo apt-get install aws-neuronx-dkms=2.* -y
-          sudo apt-get install aws-neuronx-tools=2.* -y
-          export PATH=/opt/aws/neuron/bin:$PATH
       - name: Install python dependencies
         run: |
           sudo apt install python3.8-venv -y
@@ -88,26 +37,3 @@ jobs:
         run: |
           source aws_neuron_venv_pytorch/bin/activate
           HF_TOKEN_OPTIMUM_NEURON_CI=${{ secrets.HF_TOKEN_OPTIMUM_NEURON_CI }} pytest -m is_inferentia_test tests
-  stop-runner:
-    name: Stop self-hosted EC2 runner
-    needs:
-      - start-runner # required to get output from the start-runner job
-      - do-the-job # required to wait when the main job is done
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: us-east-1
-    if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Stop EC2 runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: stop
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          label: ${{ needs.start-runner.outputs.label }}
-          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}