* Intel CI ?

* Let's try non sharded gemma.

* Snapshot rename

* Apparently container can be gone already.
This commit is contained in:
Nicolas Patry 2024-10-10 16:51:57 +02:00 committed by GitHub
parent d912f0bf55
commit 3dbdf63ec5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 9 additions and 6 deletions

View File

@ -75,10 +75,10 @@ jobs:
export label_extension="-intel-cpu" export label_extension="-intel-cpu"
export docker_devices="none" export docker_devices="none"
export docker_volume="/mnt/cache" export docker_volume="/mnt/cache"
export runs_on="ubuntu-latest" # export runs_on="ubuntu-latest"
# export runs_on="aws-highmemory-32-plus-priv" export runs_on="aws-highmemory-32-plus-priv"
export platform="cpu" export platform="cpu"
export extra_pytest="-k test_flash_llama_load" export extra_pytest="-k test_flash_gemma_simple"
;; ;;
esac esac
echo $dockerfile echo $dockerfile

View File

@ -572,7 +572,10 @@ def launcher(event_loop):
print(container_output, file=sys.stderr) print(container_output, file=sys.stderr)
finally: finally:
try:
container.remove() container.remove()
except Exception:
pass
if DOCKER_IMAGE is not None: if DOCKER_IMAGE is not None:
return docker_launcher return docker_launcher

View File

@ -16,7 +16,7 @@ async def flash_gemma(flash_gemma_handle):
@pytest.mark.release @pytest.mark.release
@pytest.mark.asyncio @pytest.mark.asyncio
@pytest.mark.private @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( response = await flash_gemma.generate(
"Test request", max_new_tokens=10, decoder_input_details=True "Test request", max_new_tokens=10, decoder_input_details=True
) )

View File

@ -15,7 +15,7 @@ async def flash_llama(flash_llama_handle):
@pytest.mark.asyncio @pytest.mark.asyncio
@pytest.mark.private @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( response = await flash_llama.generate(
"Test request", max_new_tokens=10, decoder_input_details=True "Test request", max_new_tokens=10, decoder_input_details=True
) )