From c342e4fdf30c336d8036bf6349e605cc2f9a6d85 Mon Sep 17 00:00:00 2001
From: Alvaro Moran <alvaro.moran@huggingface.co>
Date: Wed, 13 Mar 2024 16:01:50 +0000
Subject: [PATCH] fix(CI): added HF_TOKEN to use models that require it

Also manually install accelerate to avoid memory issues when loading
gemma.
---
 .github/workflows/test-pytorch-xla-tpu-tgi.yml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/test-pytorch-xla-tpu-tgi.yml b/.github/workflows/test-pytorch-xla-tpu-tgi.yml
index 83c8a232..53134849 100644
--- a/.github/workflows/test-pytorch-xla-tpu-tgi.yml
+++ b/.github/workflows/test-pytorch-xla-tpu-tgi.yml
@@ -32,4 +32,6 @@ jobs:
         run: python -c "import torch_xla.core.xla_model as xm; assert xm.xla_device().type == 'xla', 'XLA device not available'"
 
       - name: Build and test TGI server
-        run: make tgi_test
+        run: |
+        pip install accelerate==0.27.2
+        HF_TOKEN=${{ secrets.HF_TOKEN_OPTIMUM_TPU_CI }} make tgi_test