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

[Hardware][CPU] using current_platform.is_cpu (#9536)

Browse Source
This commit is contained in:
wangshuai09
2024-10-22 15:50:43 +08:00
committed by GitHub
parent 0d02747f2e
commit 3ddbe25502
17 changed files with 60 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/encoder_decoder/test_e2e_correctness.py
View File

@ -7,8 +7,8 @@ from typing import List, Optional, Tuple
import pytest
from transformers import AutoModelForSeq2SeqLM
from vllm.platforms import current_platform
from vllm.sequence import SampleLogprobs
from vllm.utils import is_cpu
from ..conftest import DecoderPromptType
from ..models.utils import check_logprobs_close
@ -35,7 +35,7 @@ def vllm_to_hf_output(
@pytest.mark.parametrize("decoder_prompt_type", list(DecoderPromptType))
@pytest.mark.parametrize("enforce_eager", [True, False])
@pytest.mark.skipif(
is_cpu(),
current_platform.is_cpu(),
reason="CPU backend is not currently supported with encoder/decoder models"
)
def test_encoder_decoder_e2e(
@ -50,7 +50,7 @@ def test_encoder_decoder_e2e(
enforce_eager: bool,
) -> None:
'''
End-to-End (E2E) test for the encoder-decoder framework.
End-to-End (E2E) test for the encoder-decoder framework.
This test evaluates the encoder-decoder functionality using the BART
model. We compare the outputs of the Hugging Face and vLLM
implementations to ensure that both implementations produce consistent