feat(mac): Add VLM MTP toggle to model settings#1654
Merged
Conversation
The 0.4.1 server and web dashboard already support VLM MTP (vlm_mtp_enabled / vlm_mtp_draft_model / vlm_mtp_draft_block_size), but the native app's Advanced page doesn't expose a toggle for it, so the feature can only be enabled from the web dashboard or by editing model_settings.json. This commit surfaces it in the native app, mirroring the existing Native MTP and DFlash plumbing: the settings DTO and patch body, the profile-eligible keys, the server load, profile-dict persistence, and a toggle row that reveals an assistant-drafter picker and a draft-block-size field when enabled. Fixes jundot#1648.
Owner
|
Thanks for adding this. I checked the merged result against current main, and the Mac app build/tests pass. The DTO/profile paths match the existing web settings, and storing the drafter model id is consistent with the engine_pool resolution path. One thing I'll fold into a follow-up commit: the existing TurboQuant/DFlash/SpecPrefill rows should also disable while VLM MTP is on, matching the web modal, so the native UI can't stage a server-rejected combination. This looks good to me, and I'm going to merge it. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The 0.4.1 server and web dashboard already support VLM MTP (vlm_mtp_enabled / vlm_mtp_draft_model / vlm_mtp_draft_block_size), but the native app's Advanced page doesn't expose a toggle for it, so the feature can only be enabled from the web dashboard or by editing model_settings.json. This commit surfaces it in the native app, mirroring the existing Native MTP and DFlash plumbing: the settings DTO and patch body, the profile-eligible keys, the server load, profile-dict persistence, and a toggle row that reveals an assistant-drafter picker and a draft-block-size field when enabled.
Fixes #1648.