Skip to content

refactor(sdk): drop default-quant from model-manager - #1252

Merged
Mengsheng Wu (mengshengwu) merged 14 commits into
mainfrom
refactor/model-manager-drop-default-quant
Jul 30, 2026
Merged

refactor(sdk): drop default-quant from model-manager#1252
Mengsheng Wu (mengshengwu) merged 14 commits into
mainfrom
refactor/model-manager-drop-default-quant

Conversation

@mengshengwu

Copy link
Copy Markdown
Contributor

Summary

  • Rust core: remove DEFAULT_QUANT untagged-GGUF sentinel, pick_default_quant auto-select, and Error::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).
  • FFI + header: drop is_default from geniex_QuantCandidate. geniex_model_query now returns a priority-sorted list; callers grab the head.
  • Bindings (Go / Python / Kotlin / JNI): drop is_default field and its plumbing. Python ensure_cached picks candidates[0].
  • CLI choosePrecision pre-fills from candidates[0] (SDK-sorted head) instead of the removed flag; no more (default) label.
  • Housekeeping in touched files: fold paths.rs into store.rs, extract file_info helper in manifest_builder.rs, drop dead DownloadInfo / VoidPtr / unused log-level wrappers, hide resume / validation mods.

Test plan

  • pull org/repo-GGUF:default for a repo that used to rely on the sentinel (e.g. Qwen/Qwen2-1.5B-Instruct-GGUF) → must fail with QuantNotFound (was: succeeded and pulled the untagged fp16).
  • geniex model query Qwen/Qwen2-1.5B-Instruct-GGUF → candidate list must not include a default entry; head is Q4_0.
  • geniex model pull Qwen/Qwen2-1.5B-Instruct-GGUF with no :quant → interactive picker pre-selects the head (Q4_0) and shows no (default) label.

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>
@mengshengwu
Mengsheng Wu (mengshengwu) force-pushed the refactor/model-manager-drop-default-quant branch from 45e5ec2 to eb321fb Compare July 30, 2026 14:23
@mengshengwu
Mengsheng Wu (mengshengwu) marked this pull request as ready for review July 30, 2026 14:29
@mengshengwu
Mengsheng Wu (mengshengwu) merged commit 01e417f into main Jul 30, 2026
32 checks passed
@mengshengwu
Mengsheng Wu (mengshengwu) deleted the refactor/model-manager-drop-default-quant branch July 30, 2026 14:40
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.

1 participant