Skip to content
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

Fix llama 8b fp8 benchmarking test #894

Merged
merged 5 commits into from
Feb 3, 2025
Merged

Conversation

aviator19941
Copy link
Collaborator

@aviator19941 aviator19941 commented Jan 31, 2025

Benchmarking test for fp8 was failing the Export phase, but was expected to fail for the Benchmarking phase and was getting killed.

Signed-off-by: aviator19941 <avinash.sharma@amd.com>
Signed-off-by: aviator19941 <avinash.sharma@amd.com>
Signed-off-by: aviator19941 <avinash.sharma@amd.com>
Signed-off-by: aviator19941 <avinash.sharma@amd.com>
@aviator19941 aviator19941 force-pushed the fix_8b_fp8_benchmarking_test branch from 8b2e83c to 533d4c9 Compare February 1, 2025 04:03
Signed-off-by: aviator19941 <avinash.sharma@amd.com>
self.artifacts_dir_2048 = Path("/shark-dev/8b")
self.irpa_path = self.artifacts_dir / "fp16/llama3.1_8b_fp16.irpa"
self.irpa_path_fp8 = self.artifacts_dir / "f8/llama3.1_8b_fp8.irpa"
self.artifacts_dir = Path("/shark-dev/8b")
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we have a separate PR to update the 70B/405B instruct paths as well?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yeah will be a separate PR

@aviator19941 aviator19941 merged commit d1a3f3d into main Feb 3, 2025
32 of 33 checks passed
@aviator19941 aviator19941 deleted the fix_8b_fp8_benchmarking_test branch February 3, 2025 04:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants