{ROCm]: gpt-oss fusion/padding fixes (#38043)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Rohan Potdar
2026-03-27 12:19:15 -04:00
committed by GitHub
co-authored by Andreas Karatzas
parent 21d2b53f88
commit 0e9358c11d
3 changed files with 4 additions and 19 deletions
@@ -6,7 +6,6 @@ import torch
from vllm.logger import init_logger
from vllm.platforms import current_platform
from vllm.triton_utils import triton
from vllm.utils.import_utils import has_triton_kernels
from vllm.utils.torch_utils import direct_register_custom_op, is_torch_equal_or_newer
@@ -85,14 +84,6 @@ def _swizzle_mxfp4(quant_tensor, scale, num_warps=8):
return quant_tensor, InFlexData(), scale
def get_padding_alignment():
return (
256
if triton.runtime.driver.active.get_current_target().arch in ("gfx950",)
else 128
)
def _dequant_mxfp4(
x: torch.Tensor, scale: torch.Tensor, float_dtype: torch.dtype
) -> torch.Tensor: