Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm 2025-12-24 21:54:58 +00:00
parent a16596760c
commit d3fc0729f7
3 changed files with 3 additions and 5 deletions

View File

@ -46,13 +46,11 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
from vllm.model_executor.layers.quantization.utils.w8a8_utils import (
cutlass_block_fp8_supported,
)
from vllm.platforms import current_platform
from vllm.utils.deep_gemm import (
is_deep_gemm_supported,
)
from vllm.platforms import current_platform
from ..utils import TestBlockFP8Layer, TestFP8Layer
from .backend import TestBackend

View File

@ -96,7 +96,7 @@ def is_supported_and_can_implement_kernel(
_cc = current_platform.get_device_capability()
if _cc is not None:
compute_capability = _cc[0] * 10 + _cc[1]
# If the current platform uses compute_capability,
# make sure the kernel supports the compute cability.
if compute_capability is not None:

View File

@ -42,7 +42,7 @@ class AiterScaledMMLinearKernel(CutlassScaledMMLinearKernel):
+ "and `VLLM_ROCM_USE_AITER_LINEAR=1`. "
+ "`VLLM_ROCM_USE_AITER_LINEAR` default is True.",
)
if not c.input_symmetric:
return (
False,