From 3dbdf63ec547e4119a2573af5d819e9f9f1eeef8 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Thu, 10 Oct 2024 16:51:57 +0200 Subject: [PATCH] Intel ci (#2630) * Intel CI ? * Let's try non sharded gemma. * Snapshot rename * Apparently container can be gone already. --- .github/workflows/build.yaml | 6 +++--- integration-tests/conftest.py | 5 ++++- .../{test_flash_gemma.json => test_flash_gemma_simple.json} | 0 .../{test_flash_llama.json => test_flash_llama_simple.json} | 0 integration-tests/models/test_flash_gemma.py | 2 +- integration-tests/models/test_flash_llama.py | 2 +- 6 files changed, 9 insertions(+), 6 deletions(-) rename integration-tests/models/__snapshots__/test_flash_gemma/{test_flash_gemma.json => test_flash_gemma_simple.json} (100%) rename integration-tests/models/__snapshots__/test_flash_llama/{test_flash_llama.json => test_flash_llama_simple.json} (100%) diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml index d0aaea27c..c563fa274 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_gemma_simple" ;; esac echo $dockerfile diff --git a/integration-tests/conftest.py b/integration-tests/conftest.py index dbe69244f..f24fc0790 100644 --- a/integration-tests/conftest.py +++ b/integration-tests/conftest.py @@ -572,7 +572,10 @@ def launcher(event_loop): print(container_output, file=sys.stderr) finally: - container.remove() + try: + container.remove() + except Exception: + pass if DOCKER_IMAGE is not None: return docker_launcher diff --git a/integration-tests/models/__snapshots__/test_flash_gemma/test_flash_gemma.json b/integration-tests/models/__snapshots__/test_flash_gemma/test_flash_gemma_simple.json similarity index 100% rename from integration-tests/models/__snapshots__/test_flash_gemma/test_flash_gemma.json rename to integration-tests/models/__snapshots__/test_flash_gemma/test_flash_gemma_simple.json diff --git a/integration-tests/models/__snapshots__/test_flash_llama/test_flash_llama.json b/integration-tests/models/__snapshots__/test_flash_llama/test_flash_llama_simple.json similarity index 100% rename from integration-tests/models/__snapshots__/test_flash_llama/test_flash_llama.json rename to integration-tests/models/__snapshots__/test_flash_llama/test_flash_llama_simple.json diff --git a/integration-tests/models/test_flash_gemma.py b/integration-tests/models/test_flash_gemma.py index 7bee8dea2..4bd7bd145 100644 --- a/integration-tests/models/test_flash_gemma.py +++ b/integration-tests/models/test_flash_gemma.py @@ -16,7 +16,7 @@ async def flash_gemma(flash_gemma_handle): @pytest.mark.release @pytest.mark.asyncio @pytest.mark.private -async def test_flash_gemma(flash_gemma, response_snapshot): +async def test_flash_gemma_simple(flash_gemma, response_snapshot): response = await flash_gemma.generate( "Test request", max_new_tokens=10, decoder_input_details=True ) diff --git a/integration-tests/models/test_flash_llama.py b/integration-tests/models/test_flash_llama.py index c69314ffd..bf49dc0b4 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 )