wehub-resource-sync
33 lines
1.2 KiB
Python
33 lines
1.2 KiB
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
|
|
"Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4", # without g_idx
|
|
"RedHatAI/Qwen3-1.7B-quantized.w4a16", # with zp
|
|
"OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc",
|
|
"Qwen/Qwen3-0.6B-FP8", # FP8 W8A16 block-quantized linear
|
|
"Qwen/Qwen3-30B-A3B-FP8", # FP8 W8A16 block-quantized MoE
|
|
"openai/gpt-oss-20b", # MXFP4 W4A16
|
|
"QuixiAI/Qwen3-30B-A3B-AWQ", # AWQ W4A16 MoE
|
|
"Qwen/Qwen3-30B-A3B-GPTQ-Int4", # GPTQ W4A16 MoE
|
|
"RedHatAI/Qwen3-30B-A3B-quantized.w4a16", # compressed-tensors W4A16 MoE
|
|
]
|
|
DTYPE = ["bfloat16"]
|
|
|
|
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("dtype", DTYPE)
|
|
def test_cpu_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)
|