Skip to content

GitLab

Unverified Commit a3ae45a3 authored by Juechen Liu's avatar Juechen Liu Committed by GitHub
Browse files

[Misc] fix tests failure by using current_platform (#25825) 


Signed-off-by: default avatarJuechen Liu <jueliu@meta.com>
parent 0307428d
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/attention/ops/triton_reshape_and_cache_flash.py
View file @ a3ae45a3
...@@ -137,7 +137,7 @@ def triton_reshape_and_cache_flash( ...@@ -137,7 +137,7 @@ def triton_reshape_and_cache_flash(
# heuristics instead of autotuning # heuristics instead of autotuning
TILE_SIZE = min(2048, triton.next_power_of_2(n)) TILE_SIZE = min(2048, triton.next_power_of_2(n))
if torch.version.hip or torch.version.xpu: if current_platform.is_rocm() or current_platform.is_xpu():
num_stages = 4 num_stages = 4
num_warps = 8 num_warps = 8
else: # cuda else: # cuda
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment