Auto model picker + FP16/FP32 precision selector (Upload UI + backend)#77
Open
eshankiyer wants to merge 3 commits into
Open
Auto model picker + FP16/FP32 precision selector (Upload UI + backend)#77eshankiyer wants to merge 3 commits into
eshankiyer wants to merge 3 commits into
Conversation
…ith heuristic fallback)
…oggle, hint field
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds automatic model selection and a precision control to the Upload pipeline, based on current main.
Frontend (UploadPage.tsx / .css): the model dropdown now defaults to an "Auto - AI picks the best model" option; on run it calls the backend to choose the model. A plain-language precision toggle (Faster / FP16 quantized vs Highest precision / FP32) and an optional free-text hint field were added. Precision is sent with every inference request.
Backend: run-epai-inference reads a precision field and threads it through _start_auto_segmentation -> run_auto_segmentation, which exports BODYMAPS_PRECISION to the GPU inference subprocess (ShapeKit, being CPU-only, is pinned to fp32). New /api/suggest-model endpoint uses the existing local Ollama client to pick a model from a small catalog, with a deterministic heuristic fallback when the LLM is unavailable.
No existing files are reverted; the diff is scoped to these changes.