Skip to content

fix: fast follow on js uncompressed support - ModelBuilder #4281

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions src/sagemaker/serve/model_server/tgi/prepare.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,16 +17,16 @@ def _copy_jumpstart_artifacts(model_data: str, js_id: str, code_dir: Path) -> bo
"""Placeholder Docstring"""
logger.info("Downloading JumpStart artifacts from S3...")
with _tmpdir(directory=str(code_dir)) as js_model_dir:
# TODO: remove if block after 10/30 once everything is shifted to uncompressed
if model_data.endswith("tar.gz"):
subprocess.run(["aws", "s3", "cp", model_data, js_model_dir])

js_model_data_loc = model_data.get("S3DataSource").get("S3Uri")
# TODO: leave this check here until we are sure every js model has moved to uncompressed
if js_model_data_loc.endswith("tar.gz"):
subprocess.run(["aws", "s3", "cp", js_model_data_loc, js_model_dir])
logger.info("Uncompressing JumpStart artifacts for faster loading...")
tmp_sourcedir = Path(js_model_dir).joinpath(f"infer-prepack-{js_id}.tar.gz")
with tarfile.open(str(tmp_sourcedir)) as resources:
resources.extractall(path=code_dir)
else:
subprocess.run(["aws", "s3", "cp", model_data, js_model_dir, "--recursive"])
subprocess.run(["aws", "s3", "cp", js_model_data_loc, js_model_dir, "--recursive"])
return True


Expand Down