RapidAI / RapidAI/RapidDoc

paddleocr-vl 1.6 支持

Open
#49 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
230
Forks
41
PR merge metrics
No merged PRs in 30d

Description

使用外接vllm推理的模式, 目前直接按version v1.5 发送是能跑通的

但是vllm那边(0.22.1)下, 偶尔会出现

WARNING 06-08 01:02:26 [detokenizer.py:238] Encountered invalid prefix detokenization error for request chatcmpl-8abaeb0a81114b87-83b5a75f, resetting decode stream.

我猜应该只是vllm遇到生成token出错的原因, 可能不是rapiddoc的问题

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the external vLLM setup described in the issue with PaddleOCR-VL 1.6 and compare it with the current v1.5 request path. Confirm whether the warning is produced by RapidDoc or vLLM before defining the change; done means either adding verified 1.6 support or documenting that the warning is external.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.