Skip to content

[CI/Build] Enable phi2 lora test #20540

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 2 commits into from
Jul 7, 2025
Merged

[CI/Build] Enable phi2 lora test #20540

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
06e47b9
Done
jeejeelee Jul 7, 2025
bd2317b
Fix pre-commit
jeejeelee Jul 7, 2025
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
5 changes: 0 additions & 5 deletions tests/lora/test_phi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project

import pytest

import vllm
from vllm.lora.request import LoRARequest

Expand Down Expand Up @@ -49,9 +47,6 @@ def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
return generated_texts


# Skipping for V1 for now as we are hitting,
# "Head size 80 is not supported by FlashAttention." error.
@pytest.mark.skip(reason="Head size 80 is not supported by FlashAttention")
def test_phi2_lora(phi2_lora_files):
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

Consider adding a comment explaining why this test was previously skipped and the reason for enabling enforce_eager=True. This provides valuable context for future maintainers.

Suggested change
def test_phi2_lora(phi2_lora_files):
# The phi-2 LoRA test runs in eager mode to avoid a FlashAttention
# incompatibility with head size 80.
def test_phi2_lora(phi2_lora_files):

# We enable enforce_eager=True here to reduce VRAM usage for lora-test CI,
# Otherwise, the lora-test will fail due to CUDA OOM.
Expand Down