Add --max-tokens CLI argument to server#936
Open
nnorris7 wants to merge 1 commit into
Open
Conversation
The server's default max_tokens (256) is too low for conversational use and there was no way to change it without the client sending the value in every request. This adds a --max-tokens flag so operators can set a sensible default at launch time (e.g. --max-tokens 8192). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
max_tokensin the request, which is too low for conversational use (e.g. via Open WebUI)--max-tokensCLI flag so operators can set a higher default at launch time (e.g.--max-tokens 8192)max_tokensfrom clients still takes precedenceTest plan
python -m mlx_vlm.server --helpshows the new--max-tokensflag with default 256--max-tokens 8192uses 8192 when client omitsmax_tokensmax_tokensstill overrides the server default🤖 Generated with Claude Code