[INC] fix w4a4 model (#50807)

Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
This commit is contained in:
Qiming Zhang
2026-08-03 14:28:58 +08:00
committed by GitHub
parent f5bb701fa2
commit 2755489a26
2 changed files with 4 additions and 3 deletions
+2 -2
View File
@@ -496,7 +496,7 @@ def test_qwen3_1p7b_mxfp4_autoround_uses_mxfp4_linear_scheme(
monkeypatch.setattr(
"vllm.model_executor.layers.quantization.inc.schemes."
"inc_mxfp4_linear.init_mxfp4_linear_kernel",
lambda: DummyKernel(),
lambda **kwargs: DummyKernel(),
)
from vllm.model_executor.layers.quantization.inc.schemes.inc_mxfp4_linear import ( # noqa: E501
@@ -614,7 +614,7 @@ def test_inc_mxfp4_linear_method_registers_and_processes_weights(
monkeypatch.setattr(
"vllm.model_executor.layers.quantization.inc.schemes."
"inc_mxfp4_linear.init_mxfp4_linear_kernel",
lambda: DummyKernel(),
lambda **kwargs: DummyKernel(),
)
monkeypatch.setattr(
"vllm.model_executor.parameter.get_tensor_model_parallel_rank",