[V1] LoRA - Enable more V1 tests (#14315)

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
2025-03-06 11:55:42 +08:00
committed by GitHub
co-authored by Varun Sundar Rabindranath
parent f5f7f00cd9
commit 3dbd2d813a
5 changed files with 57 additions and 8 deletions
+8
View File
@@ -10,6 +10,14 @@ from vllm.platforms import current_platform
MODEL_PATH = "mistralai/Mixtral-8x7B-Instruct-v0.1"
@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,
prompts: list[str]) -> list[str]: