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

[V1] V1 Enablement Oracle (#13726)

Browse Source 
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
Robert Shaw
2025-03-15 01:02:20 -04:00
committed by GitHub
parent 8c0d15d5c5
commit d4d93db2c5
96 changed files with 1537 additions and 512 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/kernels/test_encoder_decoder_attn.py
View File

@@ -22,6 +22,16 @@ from vllm.config import VllmConfig, set_current_vllm_config
from vllm.forward_context import set_forward_context
from vllm.platforms import current_platform
@pytest.fixture(scope="function", autouse=True)
def use_v0_only(monkeypatch):
"""
Encoder-decoder is only supported on V0, so set
VLLM_USE_V1=0 for all tests in the module.
"""
monkeypatch.setenv('VLLM_USE_V1', '0')
# List of support backends for encoder/decoder models
LIST_ENC_DEC_SUPPORTED_BACKENDS = [_Backend.XFORMERS, _Backend.FLASH_ATTN]
HEAD_SIZES = [64, 256]