f34eef546a
* update doc and skip brittle grpo test * fix the path to run the multigpu tests * increase timeout, use LOC instead of NVL * typo * use hf cache from s3 backed cloudfront * mark grpo as flaky test dues to vllm start
21 lines
403 B
Python
21 lines
403 B
Python
"""Modal app to run axolotl GPU tests"""
|
|
|
|
from .single_gpu import GPU_CONFIG, VOLUME_CONFIG, app, cicd_image, run_cmd
|
|
|
|
|
|
@app.function(
|
|
image=cicd_image,
|
|
gpu=GPU_CONFIG,
|
|
timeout=90 * 60, # 90 min
|
|
cpu=8.0,
|
|
memory=131072,
|
|
volumes=VOLUME_CONFIG,
|
|
)
|
|
def cicd_pytest():
|
|
run_cmd("./cicd/cicd.sh", "/workspace/axolotl")
|
|
|
|
|
|
@app.local_entrypoint()
|
|
def main():
|
|
cicd_pytest.remote()
|