Skip to content

Conversation

memoryCoderC
Copy link
Contributor

@memoryCoderC memoryCoderC commented Sep 23, 2025

添加cli命令serve用来启动apiserve

使用方式

使用fastdeploy命令执行相关操作

  1. serve 启动API server
  2. 启动参数与之前python -m fastdeploy.entrypoints.openai.api_server参数一致

接口使用方式

fastdeploy serve  参数

示例:
fastdeploy serve --model=/root/paddlejob/ERNIE-0.3B --port=8490 --engine-worker-queue-port=8491 --metrics-port=8492 --controller-port=8493 --num-gpu-blocks-override=1000 --tensor-parallel-size=1 --max-model-len=8192 --max-num-seqs=128 --timeout-graceful-shutdown=100

参数参考
https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/zh/parameters.md_

@Jiang-Jia-Jun Jiang-Jia-Jun merged commit 8b0ce8e into PaddlePaddle:develop Sep 24, 2025
26 of 28 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants