[CI/Build] Fix LoRA test (#19350)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
@@ -11,14 +11,6 @@ MODEL_PATH = "microsoft/phi-2"
|
||||
PROMPT_TEMPLATE = "### Instruct: {sql_prompt}\n\n### Context: {context}\n\n### Output:" # noqa: E501
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def v1(run_with_both_engines_lora):
|
||||
# Simple autouse wrapper to run both engines for each test
|
||||
# This can be promoted up to conftest.py to run for every
|
||||
# test in a package
|
||||
pass
|
||||
|
||||
|
||||
def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
|
||||
prompts = [
|
||||
PROMPT_TEMPLATE.format(
|
||||
@@ -59,7 +51,7 @@ def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
|
||||
|
||||
# Skipping for V1 for now as we are hitting,
|
||||
# "Head size 80 is not supported by FlashAttention." error.
|
||||
@pytest.mark.skip_v1
|
||||
@pytest.mark.skip(reason="Head size 80 is not supported by FlashAttention")
|
||||
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.
|
||||
|
||||
Reference in New Issue
Block a user