Skip to content

Mark LavaSR roadmap evidence complete #68

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Tinnci merged 1 commit into from
Jul 12, 2026
Merged

Mark LavaSR roadmap evidence complete #68

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion ROADMAP.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ Release-preparation status:
Release scope deliberately excludes new heavyweight evaluators, new model weights, and a new
self-contained backend.

## Priority 1: Stabilize LavaSR With Broader Evidence
## Completed: Stabilize LavaSR With Broader Evidence

`lavasr-compat` should not be marked stable from a single parity path. The next validation slice is:

Expand All @@ -49,6 +49,12 @@ Promotion criteria:
- passing stability and parity evidence on the supported runtime path;
- known limitations visible in model listings.

The release-tag and follow-up T4 workflows now cover verified real weights, CUDA smoke, failure-case
matrices, strict digital-silence preservation, deterministic repeated inference, versioned
Comment on lines +52 to +53
regression thresholds, and same-backend parity across refs. The backend remains experimental because
real-speech full-reference metrics did not justify stable promotion, not because the stability
evidence is missing.

## Completed: Produce Real Evaluation Evidence

The harness is implemented; the missing value is a repeatable evidence set.
Expand Down