biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Enable V1 LoRA by default (#15320)

Browse Source 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
This commit is contained in:
Varun Sundar Rabindranath
2025-04-01 04:53:56 -04:00
committed by GitHub
parent 30d6a015e0
commit 79455cf421
12 changed files with 125 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tests/lora/test_phi.py
View File

@@ -10,6 +10,14 @@ 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(
@@ -48,14 +56,6 @@ def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
return generated_texts
@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
# Skipping for V1 for now as we are hitting,
# "Head size 80 is not supported by FlashAttention." error.
@pytest.mark.skip_v1