38 lines
1.2 KiB
Python
38 lines
1.2 KiB
Python
"""Compare the outputs of HF and vLLM for Mistral models using greedy sampling.
|
|
|
|
Run `pytest tests/models/test_mistral.py --forked`.
|
|
"""
|
|
import pytest
|
|
|
|
MODELS = [
|
|
"mistralai/Mistral-7B-Instruct-v0.1",
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("dtype", ["bfloat16"])
|
|
@pytest.mark.parametrize("max_tokens", [128])
|
|
def test_models(
|
|
hf_runner,
|
|
vllm_runner,
|
|
example_long_prompts,
|
|
model: str,
|
|
dtype: str,
|
|
max_tokens: int,
|
|
) -> None:
|
|
hf_model = hf_runner(model, dtype=dtype)
|
|
hf_outputs = hf_model.generate_greedy(example_long_prompts, max_tokens)
|
|
del hf_model
|
|
|
|
vllm_model = vllm_runner(model, dtype=dtype)
|
|
vllm_outputs = vllm_model.generate_greedy(example_long_prompts, max_tokens)
|
|
del vllm_model
|
|
|
|
for i in range(len(example_long_prompts)):
|
|
hf_output_ids, hf_output_str = hf_outputs[i]
|
|
vllm_output_ids, vllm_output_str = vllm_outputs[i]
|
|
assert hf_output_str == vllm_output_str, (
|
|
f"Test{i}:\nHF: {hf_output_str!r}\nvLLM: {vllm_output_str!r}")
|
|
assert hf_output_ids == vllm_output_ids, (
|
|
f"Test{i}:\nHF: {hf_output_ids}\nvLLM: {vllm_output_ids}")
|