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

Convert formatting to use ruff instead of yapf + isort (#26247)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-05 15:06:22 +01:00
committed by GitHub
parent 17edd8a807
commit d6953beb91
1508 changed files with 115244 additions and 94146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
tests/quantization/test_auto_round.py
View File

@@ -1,11 +1,11 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Test model set-up and inference for quantized HF models supported
on the AutoRound.
on the AutoRound.
Validating the configuration and printing results for manual checking.
Validating the configuration and printing results for manual checking.
Run `pytest tests/quantization/test_auto_round.py`.
Run `pytest tests/quantization/test_auto_round.py`.
"""
import pytest
@@ -14,18 +14,19 @@ from vllm.platforms import current_platform
MODELS = [
"OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc", ##auto_round:auto_gptq
"Intel/Qwen2-0.5B-Instruct-int4-sym-AutoRound" ##auto_round:auto_awq
"Intel/Qwen2-0.5B-Instruct-int4-sym-AutoRound", ##auto_round:auto_awq
]
@pytest.mark.skipif(not current_platform.is_cpu()
and not current_platform.is_xpu()
and not current_platform.is_cuda(),
reason="only supports CPU/XPU/CUDA backend.")
@pytest.mark.skipif(
not current_platform.is_cpu()
and not current_platform.is_xpu()
and not current_platform.is_cuda(),
reason="only supports CPU/XPU/CUDA backend.",
)
@pytest.mark.parametrize("model", MODELS)
def test_auto_round(vllm_runner, model):
with vllm_runner(model) as llm:
output = llm.generate_greedy(["The capital of France is"],
max_tokens=8)
output = llm.generate_greedy(["The capital of France is"], max_tokens=8)
assert output
print(f"{output[0][1]}")