[CI][ROCm] Restrict MLA cross-layer KV cache test to supported backends on ROCm (#46401)
Signed-off-by: aarushjain29 <Aarushi.Jain2@amd.com>
This commit is contained in:
@@ -3,6 +3,8 @@
|
|||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
|
from vllm.platforms import current_platform
|
||||||
|
|
||||||
|
|
||||||
def test_mla_common_backend_rejects_cross_layer_kv_cache():
|
def test_mla_common_backend_rejects_cross_layer_kv_cache():
|
||||||
"""MLACommonBackend defaults to the identity permutation (layers dim
|
"""MLACommonBackend defaults to the identity permutation (layers dim
|
||||||
@@ -24,8 +26,13 @@ def test_mla_common_backend_rejects_cross_layer_kv_cache():
|
|||||||
|
|
||||||
@pytest.mark.parametrize(
|
@pytest.mark.parametrize(
|
||||||
"backend_path",
|
"backend_path",
|
||||||
|
# See: https://github.com/vllm-project/vllm/issues/46411
|
||||||
[
|
[
|
||||||
"vllm.v1.attention.backends.mla.triton_mla.TritonMLABackend",
|
"vllm.v1.attention.backends.mla.triton_mla.TritonMLABackend",
|
||||||
|
]
|
||||||
|
if current_platform.is_rocm()
|
||||||
|
else [
|
||||||
|
"vllm.v1.attention.backends.mla.triton_mla.TritonMLABackend",
|
||||||
"vllm.v1.attention.backends.mla.cutlass_mla.CutlassMLABackend",
|
"vllm.v1.attention.backends.mla.cutlass_mla.CutlassMLABackend",
|
||||||
"vllm.v1.attention.backends.mla.flashattn_mla.FlashAttnMLABackend",
|
"vllm.v1.attention.backends.mla.flashattn_mla.FlashAttnMLABackend",
|
||||||
"vllm.v1.attention.backends.mla.flashmla.FlashMLABackend",
|
"vllm.v1.attention.backends.mla.flashmla.FlashMLABackend",
|
||||||
|
|||||||
Reference in New Issue
Block a user