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

[ez] Remove checks for torch version <= 2.8 (#33209)

Browse Source 
Signed-off-by: angelayi <yiangela7@gmail.com>
This commit is contained in:
Angela Yi
2026-01-28 13:03:56 -08:00
committed by GitHub
parent 59bcc5b6f2
commit 4197168ea5
11 changed files with 30 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/layers/quantization/mxfp4.py
View File

@@ -56,7 +56,6 @@ from vllm.scalar_type import scalar_types
from vllm.utils.flashinfer import has_flashinfer
from vllm.utils.import_utils import has_triton_kernels
from vllm.utils.math_utils import round_up
from vllm.utils.torch_utils import is_torch_equal_or_newer
logger = init_logger(__name__)
@@ -89,7 +88,6 @@ def get_mxfp4_backend_with_lora() -> Mxfp4Backend:
# If FlashInfer is not available, try either Marlin or Triton
triton_kernels_supported = (
has_triton_kernels()
and is_torch_equal_or_newer("2.8.0")
# NOTE: triton_kernels are only confirmed to work on SM90 and SM100
# SM110 fails with this error: https://github.com/vllm-project/vllm/issues/29317
# SM120 needs this fix: https://github.com/triton-lang/triton/pull/8498
@@ -151,7 +149,6 @@ def get_mxfp4_backend(with_lora_support: bool) -> Mxfp4Backend:
# If FlashInfer is not available, try either Marlin or Triton
triton_kernels_supported = (
has_triton_kernels()
and is_torch_equal_or_newer("2.8.0")
# NOTE: triton_kernels are only confirmed to work on SM90 and SM100
# SM110 fails with this error: https://github.com/vllm-project/vllm/issues/29317
# SM120 needs this fix: https://github.com/triton-lang/triton/pull/8498