[MoE Refactor] Combine CompressedTensorsWNA16MarlinMoEMethod with CompressedTensorsWNA16MoEMethod (#44570)

Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Signed-off-by: Dobrzyniewicz, Agata <agata.dobrzyniewicz@intel.com>
Signed-off-by: Tushar Jain <tushar00jain@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Agata Dobrzyniewicz <160237065+adobrzyn@users.noreply.github.com>
Co-authored-by: Tushar Jain <8455015+tushar00jain@users.noreply.github.com>
Co-authored-by: Tushar Jain <tushar00jain@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
This commit is contained in:
bnellnm
2026-07-31 14:13:03 -07:00
committed by GitHub
co-authored by Claude Taneem Ibrahim Agata Dobrzyniewicz Tushar Jain Tushar Jain Wentao Ye Jiangyun Zhu
parent 0c4dc7c488
commit 454ea5b526
14 changed files with 545 additions and 855 deletions
@@ -928,12 +928,12 @@ def test_compressed_tensors_mxfp8_moe_setup(vllm_runner):
(None, 32, 64, 128, (False, 64, True)),
],
)
def test_wna16_marlin_moe_w2_scale_sharding(actorder, group_size, part, full, expected):
from vllm.model_executor.layers.quantization.compressed_tensors.compressed_tensors_moe.compressed_tensors_moe_wna16_marlin import ( # noqa: E501
CompressedTensorsWNA16MarlinMoEMethod,
def test_wna16_moe_w2_scale_sharding(actorder, group_size, part, full, expected):
from vllm.model_executor.layers.quantization.compressed_tensors.compressed_tensors_moe.compressed_tensors_moe_wna16 import ( # noqa: E501
CompressedTensorsWNA16MoEMethod,
)
result = CompressedTensorsWNA16MarlinMoEMethod._w2_scale_sharding(
result = CompressedTensorsWNA16MoEMethod._w2_scale_sharding(
actorder, group_size, part, full
)
assert result == expected
+6
View File
@@ -91,11 +91,17 @@ def test_map_wna16_backend_supports_triton():
def test_wna16_oracle_rejects_incompatible_quant_structures(
backend, quant_config, may_have_zp, may_have_bias, expected
):
from tests.kernels.moe.utils import make_dummy_moe_config
moe_config = make_dummy_moe_config()
reason = _backend_incompatibility_reason(
backend=backend,
moe_config=moe_config,
quant_config=quant_config,
may_have_zp=may_have_zp,
may_have_bias=may_have_bias,
allow_tile_padding=True,
)
assert reason is not None