[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:
Andreas Karatzas
2026-08-11 14:19:16 -04:00
committed by GitHub
co-authored by OpenAI Codex
parent 4f2f31b82e
commit 1ab2801dde
56 changed files with 500 additions and 558 deletions
@@ -16,19 +16,6 @@ def add_attention_backend(server_args, attention_config):
server_args.extend(["--attention-backend", attention_config["backend"]])
@pytest.fixture(scope="module")
def rocm_aiter_fa_attention():
"""Return attention config for transcription/translation tests on ROCm.
On ROCm, audio tests require ROCM_AITER_FA attention backend.
"""
from vllm.platforms import current_platform
if current_platform.is_rocm():
return {"backend": "ROCM_AITER_FA"}
return None
@pytest.fixture
def mary_had_lamb():
path = AudioAsset("mary_had_lamb").get_local_path()