mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-10 00:45:01 +08:00
24 lines
709 B
Python
24 lines
709 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
import pytest
|
|
|
|
from vllm.platforms import current_platform
|
|
|
|
if not current_platform.is_cpu():
|
|
pytest.skip("skipping CPU-only tests", allow_module_level=True)
|
|
|
|
MODELS = [
|
|
"TheBloke/TinyLlama-1.1B-Chat-v1.0-AWQ",
|
|
"TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ", # with g_idx
|
|
]
|
|
DTYPE = ["bfloat16"]
|
|
|
|
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("dtype", DTYPE)
|
|
def test_ipex_quant(vllm_runner, model, dtype):
|
|
with vllm_runner(model, dtype=dtype) as llm:
|
|
output = llm.generate_greedy(["The capital of France is"], max_tokens=32)
|
|
assert output
|
|
print(output)
|