[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
@@ -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()
|
||||
|
||||
Reference in New Issue
Block a user