Skip to content

Conversation

peerschuett
Copy link
Contributor

@peerschuett peerschuett commented Jul 24, 2025

vLLM doesnt work at the moment, because of the MaxTokens parameter. It is currently set to -1, but vLLM requires it to be >0.
We have removed the MaxTokens parameter initially and now need to test if this is the best solution.

grafik

@peerschuett peerschuett self-assigned this Jul 24, 2025
@peerschuett
Copy link
Contributor Author

I tested LM Studio, ollama and vLLM with this setting and they all generate responses.

@SommerEngineering SommerEngineering requested a review from a team as a code owner August 10, 2025 14:21
@SommerEngineering SommerEngineering merged commit b75d90b into MindWorkAI:main Aug 10, 2025
@peerschuett peerschuett deleted the vLLM branch August 11, 2025 07:55
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.

2 participants