biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Chore] Separate out optional dependency checks from vllm.utils (#27207)

Browse Source 
Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: dongbo910220 <32610838+dongbo910220@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
dongbo910220
2025-10-22 22:44:21 +08:00
committed by GitHub
parent 49c00fe304
commit 3ae082c373
22 changed files with 60 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/model_executor/layers/quantization/mxfp4.py
View File

@@ -48,11 +48,9 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import is_layer_s
from vllm.model_executor.utils import set_weight_attrs
from vllm.platforms import current_platform
from vllm.scalar_type import scalar_types
from vllm.utils import (
has_triton_kernels,
round_up,
)
from vllm.utils import round_up
from vllm.utils.flashinfer import has_flashinfer
from vllm.utils.import_utils import has_triton_kernels
from vllm.utils.torch_utils import is_torch_equal_or_newer
logger = init_logger(__name__)