TurboTransformers icon indicating copy to clipboard operation
TurboTransformers copied to clipboard

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Results 51 TurboTransformers issues
Sort by recently updated
recently updated
newest added

Is commercial support available for this project? If not, anyone who's familiar with the C++ part of this project interested in a paid gig to help integrate it?

我们有一个bert模型,但是是基于标准bert模型,做了一些网络结构上的修改,可以支持吗? 我现在运行模型,好像报错: AttributeError: 'RecursiveScriptModule' object has no attribute 'embeddings'

conformer is an upgraded version from transformer , which insert a convolution layer between each attention layer Is it easier to adapt to other models ?

您好,非常感谢您这边的分享,我在测试turbo_transoformers的时候发现一个问题,如果Q矩阵有负数,或者mask矩阵有True的时候,turbo_transformers和onmt的输出结果就无法对应上了,请问是否我测试方法有问题? ![image](https://user-images.githubusercontent.com/32027268/155834473-f10ed3bc-11f5-4280-b2de-4a1a33f0787f.png)

跑完build_and_run_unitest,unittest都pass了,但是运行benchmark gpu_fixed的时候,报code is not compiled with CUDA。

@feifeibear 您好,我看到TurboTransformers最新版本中已经要求transformers版本为4.11.1了,对于我们之前使用transformers4.6.1版本训练出来的模型想要使用TurboTransformers来加速,需要怎么做呢?还是说训练模型的Transformers版本必须和TurboTransformers保持一致呢?

目前支持大模型吗?比如30亿(enc dec 均36层) 或者上百亿的,transformer模型,有一些推理优化的性能指标吗?

hi 你好: 我想问一下,在使用turbo进行bert推理时,有能设置使用gpu的device_id相关的代码吗?大概在哪块?

enhancement