[Tests][XPU] Skip modelopt_fp4 online MoE re-quantization test on XPU (#61723)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com> Co-authored-by: Kevin H. Luu <khluu000@gmail.com> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
co-authored by
Kevin H. Luu
Cyrus Leung
parent
8f111b22ee
commit
85c94c1706
@@ -1728,11 +1728,14 @@ def test_online_quantization(
|
||||
monkeypatch.setenv("VLLM_ROCM_USE_AITER", "1" if use_rocm_aiter else "0")
|
||||
rocm_aiter_ops.refresh_env_variables()
|
||||
|
||||
if current_platform.is_xpu() and quant_scheme in (
|
||||
"fp8_per_block",
|
||||
"fp8_per_channel",
|
||||
):
|
||||
pytest.skip(f"Skip test for online {quant_scheme} on XPU platform.")
|
||||
if current_platform.is_xpu():
|
||||
if quant_scheme in ("fp8_per_block", "fp8_per_channel"):
|
||||
pytest.skip(f"Skip test for online {quant_scheme} on XPU platform.")
|
||||
if model_name == MODELOPT_NVFP4_MOE_MODEL_NAME:
|
||||
pytest.skip(
|
||||
"modelopt_fp4 quantization (base format of "
|
||||
f"{MODELOPT_NVFP4_MOE_MODEL_NAME}) is not supported on XPU platform."
|
||||
)
|
||||
|
||||
runner_kwargs = dict(extra_runner_kwargs)
|
||||
kv_cache_dtype = runner_kwargs.get("kv_cache_dtype", "auto")
|
||||
|
||||
Reference in New Issue
Block a user