diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml
index d0aaea27..0f037457 100644
--- a/.github/workflows/build.yaml
+++ b/.github/workflows/build.yaml
@@ -75,10 +75,10 @@ jobs:
                 export label_extension="-intel-cpu"
                 export docker_devices="none"
                 export docker_volume="/mnt/cache"
-                export runs_on="ubuntu-latest"
-                # export runs_on="aws-highmemory-32-plus-priv"
+                # export runs_on="ubuntu-latest"
+                export runs_on="aws-highmemory-32-plus-priv"
                 export platform="cpu"
-                export extra_pytest="-k test_flash_llama_load"
+                export extra_pytest="-k test_flash_llama_simple"
                 ;;
           esac
           echo $dockerfile
diff --git a/integration-tests/models/test_flash_llama.py b/integration-tests/models/test_flash_llama.py
index c69314ff..bf49dc0b 100644
--- a/integration-tests/models/test_flash_llama.py
+++ b/integration-tests/models/test_flash_llama.py
@@ -15,7 +15,7 @@ async def flash_llama(flash_llama_handle):
 
 @pytest.mark.asyncio
 @pytest.mark.private
-async def test_flash_llama(flash_llama, response_snapshot):
+async def test_flash_llama_simple(flash_llama, response_snapshot):
     response = await flash_llama.generate(
         "Test request", max_new_tokens=10, decoder_input_details=True
     )