Skip to content

Commit e3d56f8

Browse files
authored
Fix the clone url of README
1 parent 850a57d commit e3d56f8

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -49,7 +49,7 @@ We provide a docker file, which bases on Triton image `nvcr.io/nvidia/tritonserv
4949

5050
```bash
5151
mkdir workspace && cd workspace
52-
git clone https://gitlab-master.nvidia.com/liweim/transformer_backend.git
52+
git clone https://github.com/triton-inference-server/fastertransformer_backend.git
5353
nvidia-docker build --tag ft_backend --file transformer_backend/Dockerfile .
5454
nvidia-docker run --gpus=all -it --rm --volume $HOME:$HOME --volume $PWD:$PWD -w $PWD --name ft-work ft_backend
5555
cd workspace
@@ -120,4 +120,4 @@ The model configuration for Triton server is put in `all_models/transformer/conf
120120
- vocab_size: size of vocabulary
121121
- decoder_layers: number of transformer layers
122122
- batch_size: max supported batch size
123-
- is_fuse_QKV: fusing QKV in one matrix multiplication or not. It also depends on the weights of QKV.
123+
- is_fuse_QKV: fusing QKV in one matrix multiplication or not. It also depends on the weights of QKV.

0 commit comments

Comments
 (0)