docs: correct --gpu-split-auto CLI flag in server options - #439
Open
latent-9 wants to merge 1 commit into
Open
Conversation
The server-options example writes the override flag as `--gpu_split-auto`,
but tabbyAPI builds CLI flags by replacing underscores with hyphens
(common/args.py: `sub_field_name.replace("_", "-")`), so the actual flag
for the `gpu_split_auto` config field is `--gpu-split-auto`. Copy-pasting
`--gpu_split-auto False` fails with `unrecognized arguments`. The config
key name itself is unchanged.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Is your pull request related to a problem? Please describe.
docs/02.-Server-options.md(line 9) documents the boolean-override example with the flag--gpu_split-auto:That flag string does not exist.
common/args.pybuilds every CLI flag from the config field name by replacing underscores with hyphens:So the
gpu_split_autofield is exposed as--gpu-split-auto, not--gpu_split-auto. A user copy-pasting the documented example hits:Why should this feature be added?
This is a one-word docs fix. The example is meant to teach the boolean-override behavior, but as written it fails verbatim, which is confusing precisely for the users who follow the docs. The config key
gpu_split_auto(used inconfig.yml) is correct and unchanged — only the CLI arg string is fixed.Examples
--gpu_split-auto False→unrecognized arguments--gpu-split-auto False→ parses correctlyAdditional context
Docs-only, single line, no code change.