5825bbc1f7
Signed-off-by: Robert Shaw <robshaw@redhat.com> Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> Co-authored-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
40 lines
1017 B
Python
40 lines
1017 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
# Copyright © 2025, Oracle and/or its affiliates.
|
|
"""Tests RTN quantization startup and generation,
|
|
doesn't test correctness
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from tests.quantization.utils import is_quant_method_supported
|
|
|
|
MODELS = [
|
|
"ai21labs/Jamba-tiny-dev", # MoE model
|
|
]
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not is_quant_method_supported("rtn"),
|
|
reason="RTN is not supported on this GPU type.",
|
|
)
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("dtype", ["bfloat16"])
|
|
@pytest.mark.parametrize("max_tokens", [10])
|
|
def test_model_rtn_startup(
|
|
hf_runner,
|
|
vllm_runner,
|
|
example_prompts,
|
|
model: str,
|
|
dtype: str,
|
|
max_tokens: int,
|
|
) -> None:
|
|
with vllm_runner(
|
|
model,
|
|
enforce_eager=True,
|
|
dtype=dtype,
|
|
quantization="rtn",
|
|
allow_deprecated_quantization=True,
|
|
) as vllm_model:
|
|
vllm_model.generate_greedy(example_prompts, max_tokens)
|