refactor(sdk): drop default-quant from model-manager - #1252
Merged
Mengsheng Wu (mengshengwu) merged 14 commits intoJul 30, 2026
Conversation
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
…n fetch Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Mengsheng Wu (mengshengwu)
force-pushed
the
refactor/model-manager-drop-default-quant
branch
from
July 30, 2026 14:23
45e5ec2 to
eb321fb
Compare
Mengsheng Wu (mengshengwu)
marked this pull request as ready for review
July 30, 2026 14:29
Mengsheng Wu (mengshengwu)
deleted the
refactor/model-manager-drop-default-quant
branch
July 30, 2026 14:40
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
DEFAULT_QUANTuntagged-GGUF sentinel,pick_default_quantauto-select, andError::NoDownloadedQuant. Untagged GGUFs are silently dropped during manifest inference;Store::get_paths(bare-name)keeps a cache-side priority fallback (documented in-code as not a hub-side default).is_defaultfromgeniex_QuantCandidate.geniex_model_querynow returns a priority-sorted list; callers grab the head.is_defaultfield and its plumbing. Pythonensure_cachedpickscandidates[0].choosePrecisionpre-fills fromcandidates[0](SDK-sorted head) instead of the removed flag; no more(default)label.paths.rsintostore.rs, extractfile_infohelper inmanifest_builder.rs, drop deadDownloadInfo/VoidPtr/ unused log-level wrappers, hideresume/validationmods.Test plan
pull org/repo-GGUF:defaultfor a repo that used to rely on the sentinel (e.g.Qwen/Qwen2-1.5B-Instruct-GGUF) → must fail withQuantNotFound(was: succeeded and pulled the untagged fp16).geniex model query Qwen/Qwen2-1.5B-Instruct-GGUF→ candidate list must not include adefaultentry; head isQ4_0.geniex model pull Qwen/Qwen2-1.5B-Instruct-GGUFwith no:quant→ interactive picker pre-selects the head (Q4_0) and shows no(default)label.