Conversation
# Conflicts: # src-tauri/src/chat/mod.rs
There was a problem hiding this comment.
Adds UQFF (pre-quantised) model support alongside the existing GGUF and ISQ paths. A new UQFF_MODELS table (Qwen 3 family) feeds chat_list_models and resolve_model_id, dispatched through a new ResolvedModel::Uqff arm to ChatEngine::load_uqff_model. Download progress is now observable: blobs_dir_size gains an include_incomplete flag distinguishing completeness (ignore .part/.lock) from progress (count them), exposed via a new chat_download_progress command and polled from Settings to show a real percentage bar. CI clones a sibling onde checkout because Cargo.toml patches onde to a local path for the unreleased load_uqff_model API.
Start with mod.rs: the blobs_dir_size semantics split and the ResolvedModel dispatch are the core. Note the CI/Cargo.toml patch is explicitly temporary and must be reverted once onde publishes.
Automated review by siGit Code · commit e64c41a
There was a problem hiding this comment.
Adds UQFF (pre-quantised Qwen 3) model support: a new UQFF_MODELS table with per-model metadata, a ResolvedModel::Uqff variant and load path via onde's load_uqff_model, plus a download-progress command (chat_download_progress) that reads bytes-on-disk (including .part files) from the HF cache. The frontend polls this to turn the loading spinner into a real percentage. blobs_dir_size gains an include_incomplete flag so completeness checks exclude .part/.lock while progress includes them, with tests covering the threshold regression. CI temporarily clones the onde sibling checkout because Cargo.toml now patches onde to a local path — reviewers should note this and the patch must be reverted once onde ships UQFF.
Automated review by siGit Code Review · commit 15eef14
Co-authored-by: Sigit Code <sigit-code@getsiti.5mb.app> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
There was a problem hiding this comment.
This PR adds Qwen 3 UQFF (pre-quantised) model support: a static UQFF_MODELS table in chat/mod.rs feeds chat_list_models, a new ResolvedModel::Uqff variant routes loading through onde's load_uqff_model, and a [patch.crates-io] path dependency plus a CI clone step bridge the gap until onde publishes the API. It also adds a chat_download_progress command that reports bytes-on-disk from the HF cache (counting in-flight .part files), which Settings polls every second during a load to render a determinate progress bar; blobs_dir_size gains an include_incomplete flag so completeness checks ignore partial downloads. Version bumps across the platform configs round it out. Reviewers should look first at the CI/patch coupling to onde's main branch and the progress-vs-completeness cache logic.
Automated review by siGit Code Review · commit 0a62fb7 · see the review dashboard
What & why
Add support for UQFF model format.
Blocked by ondeinference/onde#10
How it was tested
Checklist
make lintpasses (clippy + tsc, no warnings)make fmtappliedmake buildcompiles