A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
Fix triton_reshape_and_cache_flash.py triton import (#25522)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Sep 23, 2025 at 18:26 UTC
4f2954f7240b2b8f14a680e55c3caae163a404a9
1 file changed
+1
-2
vllm/attention/ops/triton_reshape_and_cache_flash.py
+1
-2
@@ -2,10 +2,9 @@
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
4
import torch
5
-import triton
6
-import triton.language as tl
5
6
from vllm.platforms import current_platform
7
+from vllm.triton_utils import tl, triton
8
9
10
@triton.jit