8卡 fastertransformer 推理报错RuntimeError: [FT][ERROR] Assertion fail: /home/young.ruan/FasterTransformer/src/fastertransformer/th_op/glm/GlmOp.h:539
Author: rGitcyCreated Nov 22, 2023Updated Nov 22, 2023
您好，使用THUDM/Fastertransformer 8卡推理报错，脚本为FasterTransformer/examples/pytorch/glm/benchmark-generation.sh
报错信息如下：
RuntimeError: [FT][ERROR] Assertion fail: /home/young.ruan/FasterTransformer/src/fastertransformer/th_op/glm/GlmOp.h:539
Source: zai-org/GLM-130B