[Misc] Fix Current vLLM config is not set. warnings, assert to avoid issues in the future (#31747)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com> Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
co-authored by
Luka Govedič
parent
5d3b6097ad
commit
6cdf015c3c
@@ -124,7 +124,12 @@ def _quantize_dequantize_fp8_ds_mla(
|
||||
reason="FlashMLASparseBackend requires CUDA 9.0 or higher",
|
||||
)
|
||||
def test_sparse_backend_decode_correctness(
|
||||
dist_init, batch_name, kv_cache_dtype, tensor_parallel_size, workspace_init
|
||||
default_vllm_config,
|
||||
dist_init,
|
||||
batch_name,
|
||||
kv_cache_dtype,
|
||||
tensor_parallel_size,
|
||||
workspace_init,
|
||||
):
|
||||
if current_platform.is_rocm():
|
||||
pytest.skip("ROCm does not support fp8_ds_mla data type for kv cache.")
|
||||
|
||||
Reference in New Issue
Block a user