Skip to content

[CI/Build] Improve Llama GGUF test robustness #19287

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.

Sign up for GitHub

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 1 commit into from
Jun 7, 2025
Merged

[CI/Build] Improve Llama GGUF test robustness #19287

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion tests/models/quantization/test_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ def gguf_model(self):
LLAMA_CONFIG = GGUFTestConfig(
original_model="meta-llama/Llama-3.2-1B-Instruct",
gguf_repo="bartowski/Llama-3.2-1B-Instruct-GGUF",
gguf_filename="Llama-3.2-1B-Instruct-IQ4_XS.gguf",
gguf_filename="Llama-3.2-1B-Instruct-Q6_K.gguf",
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

Changing to Llama-3.2-1B-Instruct-Q6_K.gguf is a good step for improving test robustness due to its higher precision compared to IQ4_XS.

Could you please provide some information on the expected impact of this change on CI resources? Specifically:

  • How does the file size of Q6_K.gguf compare to IQ4_XS.gguf?
  • Have you observed any significant changes in test execution time or memory usage in CI after this change?

Including this in the PR description (perhaps in the 'Test Result' section) would be very helpful for assessing the overall impact.

)

QWEN2_CONFIG = GGUFTestConfig(
Expand Down