[2026秋季][task08][lihaokun-2026]

[lihaokun-2026]

环境设置

source /usr/local/Ascend/ascend-toolkit/set_env.sh
export ASCEND_RT_VISIBLE_DEVICES=0
export ASCEND_GLOBAL_LOG_LEVEL=3
export TASK_QUEUE_ENABLE=1

npu-smi info

python - <<'PY'
import torch
import torch_npu
print(torch.__version__)
print(torch.npu.is_available())
x = torch.randn(2, 3).npu()
print(x + x)
PY

采用华为Ascend平台

triton代码对FPS计算进行kernel融合，在Ascend平台测试中得到了50x的大幅度提升。

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}