mirror of
https://github.com/vllm-project/vllm-ascend.git
synced 2025-10-20 13:43:53 +08:00
787010a637
V1 is enabled by default, no need to set it by hand now. This PR remove
the useless setting in example and tests
- vLLM version: v0.9.2
- vLLM main:
9ad0a4588b
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
23 lines
931 B
Python
23 lines
931 B
Python
import pytest
|
|
from modelscope import snapshot_download # type: ignore
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
from tests.e2e.singlecard.test_ilama_lora import (EXPECTED_LORA_OUTPUT,
|
|
MODEL_PATH, do_sample)
|
|
|
|
|
|
@pytest.mark.parametrize("distributed_executor_backend", ["mp"])
|
|
def test_ilama_lora_tp2(distributed_executor_backend, ilama_lora_files):
|
|
with VllmRunner(snapshot_download(MODEL_PATH),
|
|
enable_lora=True,
|
|
max_loras=4,
|
|
max_model_len=1024,
|
|
max_num_seqs=16,
|
|
tensor_parallel_size=2,
|
|
distributed_executor_backend=distributed_executor_backend
|
|
) as vllm_model:
|
|
output = do_sample(vllm_model.model, ilama_lora_files, lora_id=2)
|
|
|
|
for i in range(len(EXPECTED_LORA_OUTPUT)):
|
|
assert output[i] == EXPECTED_LORA_OUTPUT[i]
|