FP32模式下通过源码编译安装问题

[zejunwang1]

根据 https://github.com/bytedance/lightseq/blob/master/docs/inference/build.md 中的步骤在 FP32 模式下成功编译， 安装 python 版 lightseq 时报错：

import lightseq.inference Traceback (most recent call last): File "", line 1, in ImportError: /home/wangzejun/nlp-tools/transformer_tools/lightseq-master/lightseq/inference.cpython-37m-x86_64-linux-gnu.so: undefined symbol: fatbinData

请问一下有解决办法吗？

[Taka152]

Thanks for your feedback, you could try building from tag v2.2.0. The latest build of master may be unstable.

[zejunwang1]

Thanks for your feedback, you could try building from tag v2.2.0. The latest build of master may be unstable.

Thanks. I have solved this problem by building with different versions of the source. In FP32 mode, bert inference time usage as follows:

---

totally processing 1000 sentences lightseq inference time per sentence: 0.0032167024612426757s

---

about 3ms per sentence.