[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com> Signed-off-by: Andreas Karatzas <akaratza@amd.com> Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
co-authored by
OpenAI Codex
parent
4f2f31b82e
commit
1ab2801dde
@@ -1,18 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""Pytest configuration for vLLM pooling tests."""
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.platforms import current_platform
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def siglip_attention_config():
|
||||
"""Return attention config for SigLIP tests on ROCm.
|
||||
|
||||
On ROCm, SigLIP tests require FLEX_ATTENTION backend.
|
||||
"""
|
||||
if current_platform.is_rocm():
|
||||
return {"backend": "FLEX_ATTENTION"}
|
||||
return None
|
||||
Reference in New Issue
Block a user