Fix Web Demo dependencies and runtime crashes#1977
Open
study8677 wants to merge 3 commits intoQwenLM:mainfrom
Open
Fix Web Demo dependencies and runtime crashes#1977study8677 wants to merge 3 commits intoQwenLM:mainfrom
study8677 wants to merge 3 commits intoQwenLM:mainfrom
Conversation
- Add `qwen-vl-utils==0.0.14` to `requirements_web_demo.txt`. - Fix crash in `_parse_text` when input is not a string (e.g. file path tuple). - Fix vLLM generation call to pass inputs as a list to avoid iterating over dictionary keys.
- 在 `requirements_web_demo.txt` 中添加 `qwen-vl-utils==0.0.14`。 - 修复 `_parse_text` 在输入非字符串（如文件路径元组）时的崩溃问题。 - 修复 vLLM 后端调用 `model.generate` 时未将输入包装为列表的问题。
…4791253137052509546 Fix web demo dependencies and crashes
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
📝 Change Summary
This PR fixes several critical issues in
web_demo_mm.pythat caused the Web Demo to fail during startup and inference.After these changes, the Web Demo can reliably launch and correctly handle multimodal inference workflows.
🛠️ Fix Details
Add missing dependency
qwen-vl-utils==0.0.14torequirements_web_demo.txt.ImportErrorat runtime.Fix crash when uploading files
_parse_textfunction to properly handle and convert input types..split()directly, causingAttributeError: 'tuple' object has no attribute 'split'.Fix vLLM inference input format
inputsdictionary as a list ([inputs]) when callingmodel.generate.vllmrequires inputs to be provided as a list. Passing a dictionary directly causes vLLM to incorrectly iterate over keys, leading to malformed inputs and failed generation.