Release
Quantization-aware adapters, finally done properly
First-class quantization metadata, safer device movement across quantized models, auto-routing based on checkpoint info, and major test coverage expansion.
Release: InvarLock 0.3.0 — Safer device handling, smarter routing
Highlights
- Quantization metadata and detection (methods/config/capabilities).
- Safe device movement to avoid
.to()foot-guns on quantized models. - Smarter auto-adapter routing + broader tests.
0.3.0 is foundational if you’re working with quantized or pre-quantized checkpoints. Instead of treating quantization like a weird edge case, the framework can represent it, detect it, and route adapters appropriately—so you spend less time fighting “why did this load differently?” issues.
The safe device movement work is especially practical: it helps avoid a common class of runtime errors where models manage device placement internally and don’t tolerate generic .to() calls.
If you’ve been building guard/eval workflows across different quantization setups, this release is essentially the “make this feel normal” moment.
For more details, see CHANGELOG.md.
More from the blog
Continue through recent releases and implementation notes.
Release
Stable public contracts with stricter fail-closed verification
InvarLock 0.4.0 stabilizes contracts around policies, proof packs, and evaluation provenance while tightening verification, CI, and coverage enforcement.
Release
Coverage hardening across CLI, reporting, and observability paths
Coverage thresholds now enforce split-module branch floors for critical CLI/reporting paths.
Release
Targeted regression hardening for quantization and reporting paths
A focused hardening release: safer AWQ plugin discovery, stronger quantization clipping behavior, and broader report-schema acceptance for edge payloads.