vllm/vllm/triton_utils/__init__.py
youkaichao 1aa427fdc1
[Kernels] Add Flash Linear Attention Kernels (#24518)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-09-10 00:04:41 +08:00

17 lines
543 B
Python

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm.triton_utils.importing import (HAS_TRITON, TritonLanguagePlaceholder,
TritonPlaceholder)
if HAS_TRITON:
import triton
import triton.language as tl
import triton.language.extra.libdevice as tldevice
else:
triton = TritonPlaceholder()
tl = TritonLanguagePlaceholder()
tldevice = TritonLanguagePlaceholder()
__all__ = ["HAS_TRITON", "triton", "tl", "tldevice"]