apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-05-07 16:08:58 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fix typos (#3684)

Browse Source
This commit is contained in:
co63oc
2025-09-01 17:50:17 +08:00
committed by GitHub
parent 0513a78ecc
commit d6369b4d51
67 changed files with 85 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/features/graph_optimization.md
+1 -1
View File
@@ -44,7 +44,7 @@ CudaGrpah can be enabled by setting `--use-cudagraph` or `--graph-optimization-c
The `graph_opt_level` parameter within `--graph-optimization-config` is used to configure the graph optimization level, with the following available options:
+ `0`: Use Dynamic compute graph, default to 0
+ `1`: Use Static compute graph, during the initialization phase, Paddle API will be used to convert the dynamic image into a static image
+ `2`: Base on Static compute graph, use the complier(CINN, Compiler Infrastructure for Neural Networks) of Paddle to compile and optimize
+ `2`: Base on Static compute graph, use the compiler(CINN, Compiler Infrastructure for Neural Networks) of Paddle to compile and optimize
In general, static graphs have lower Kernel Launch overhead than dynamic graphs, and it is recommended to use static graphs.
For adapted models, FastDeploy's CudaGraph *can support both dynamic and static graphs* simultaneously.
docs/get_started/installation/Enflame_gcu.md
+1 -1
View File
@@ -62,7 +62,7 @@ python -m pip install paddlepaddle==3.1.1 -i https://www.paddlepaddle.org.cn/pac
python -m pip install paddle-custom-gcu==3.1.1 -i https://www.paddlepaddle.org.cn/packages/stable/gcu/
# For source compilation, refer to: https://github.com/PaddlePaddle/PaddleCustomDevice/blob/develop/backends/gcu/README_cn.md
```
For latest paddle verion on iluvatar. Refer to [PaddlePaddle Installation](https://www.paddlepaddle.org.cn/)
For latest paddle version on iluvatar. Refer to [PaddlePaddle Installation](https://www.paddlepaddle.org.cn/)
6. Install FastDeploy and dependencies
```bash
docs/usage/kunlunxin_xpu_deployment.md
+1 -1
View File
@@ -89,4 +89,4 @@ for chunk in response:
print('\n')
```
For detailed OpenAI protocol specifications, see [OpenAI Chat Compeltion API](https://platform.openai.com/docs/api-reference/chat/create). Differences from the standard OpenAI protocol are documented in [OpenAI Protocol-Compatible API Server](../online_serving/README.md).
For detailed OpenAI protocol specifications, see [OpenAI Chat Completion API](https://platform.openai.com/docs/api-reference/chat/create). Differences from the standard OpenAI protocol are documented in [OpenAI Protocol-Compatible API Server](../online_serving/README.md).
docs/zh/features/sampling.md
+1 -1
View File
@@ -1,6 +1,6 @@
# 采样策略
采样策略用于决定如何从模型的输出概率分布中选择下一个token。FastDeploy目前支持 Top-p 、 Top-k_Top-p 和 Min-p Samping 多种采样策略。
采样策略用于决定如何从模型的输出概率分布中选择下一个token。FastDeploy目前支持 Top-p 、 Top-k_Top-p 和 Min-p Sampling 多种采样策略。
1. Top-p 采样
docs/zh/usage/kunlunxin_xpu_deployment.md
+1 -1
View File
@@ -89,4 +89,4 @@ for chunk in response:
print('\n')
```
OpenAI 协议的更多说明可参考文档 [OpenAI Chat Compeltion API](https://platform.openai.com/docs/api-reference/chat/create)，以及与 OpenAI 协议的区别可以参考 [兼容 OpenAI 协议的服务化部署](../online_serving/README.md)。
OpenAI 协议的更多说明可参考文档 [OpenAI Chat Completion API](https://platform.openai.com/docs/api-reference/chat/create)，以及与 OpenAI 协议的区别可以参考 [兼容 OpenAI 协议的服务化部署](../online_serving/README.md)。