xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 20:04:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Enable phi2 lora test (#20540)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-07-07 13:10:41 +08:00 committed by GitHub
parent 6e2c19ce22
commit 2e610deb72
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/lora/test_phi.py
View File

@ -1,8 +1,6 @@
# SPDX-License-Identifier: Apache-2.0 # SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import pytest
import vllm import vllm
from vllm.lora.request import LoRARequest from vllm.lora.request import LoRARequest
@ -49,9 +47,6 @@ def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
return generated_texts 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): def test_phi2_lora(phi2_lora_files):
# We enable enforce_eager=True here to reduce VRAM usage for lora-test CI, # We enable enforce_eager=True here to reduce VRAM usage for lora-test CI,
# Otherwise, the lora-test will fail due to CUDA OOM. # Otherwise, the lora-test will fail due to CUDA OOM.