apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[Docs] fix PaddleOCR-VL docs bug (#4702)

Browse Source
This commit is contained in:
ming1753
2025-11-03 12:12:14 +08:00
committed by GitHub
parent b1dd508965
commit c657f8d16a
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/best_practices/PaddleOCR-VL-0.9B.md
View File

@@ -24,7 +24,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--max-model-len 16384 \
--max-num-batched-tokens 16384 \
--gpu-memory-utilization 0.8 \
--max-num-seqs 128 \
--max-num-seqs 128
```
**Example 2:** Deploying a 16K Context Service on a Single A100 GPU
```shell
@@ -36,7 +36,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--max-model-len 16384 \
--max-num-batched-tokens 16384 \
--gpu-memory-utilization 0.8 \
--max-num-seqs 256 \
--max-num-seqs 256
```
An example is a set of configurations that can run stably while also delivering relatively good performance. If you have further requirements for precision or performance, please continue reading the content below.

4
docs/zh/best_practices/PaddleOCR-VL-0.9B.md
View File

@@ -24,7 +24,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--max-model-len 16384 \
--max-num-batched-tokens 16384 \
--gpu-memory-utilization 0.8 \
--max-num-seqs 128 \
--max-num-seqs 128
```
**示例2：** A100上单卡部署16K上下文的服务
@@ -37,7 +37,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--max-model-len 16384 \
--max-num-batched-tokens 16384 \
--gpu-memory-utilization 0.8 \
--max-num-seqs 256 \
--max-num-seqs 256
```
示例是可以稳定运行的一组配置，同时也能得到比较好的性能。