v0.1.2
Seto Elkahfi committed
Apr 8, 2026 at 23:01 UTC
bd4ea1b112f0bfb42bc1be0ead852317f663a8bf
2 files changed
+8
-1
sdk/dart/CHANGELOG.md
+7
@@ -1,3 +1,10 @@
1
+## 0.1.2
2
+
3
+* **Engine:** Switched all platform-specific `mistralrs` and `mistralrs-core` dependencies to the `setoelkahfi/mistral.rs` fork (branch `fix/all-platform-fixes`), picking up cross-platform stability fixes ahead of the upstream merge.
4
+* **License:** Dual-licensed under MIT OR Apache-2.0; added `LICENSE-APACHE` alongside the existing `LICENSE-MIT` for pub.dev compliance.
5
+* **Dependencies:** Upgraded `freezed_annotation` to `^3.1.0` and `freezed` to `^3.2.5`.
6
+* Removed a stale `ignore_for_file` directive from the generated Flutter Rust Bridge glue code.
7
+
8
## 0.1.1
9
10
* CI/CD: `release-sdk-dart.yml` publishes `onde_inference` to pub.dev on tag push.
sdk/dart/pubspec.yaml
+1
-1
@@ -2,7 +2,7 @@ name: onde_inference
2
description: >-
3
On-device LLM inference for Flutter & Dart. Run Qwen 2.5 models locally
4
with Metal on iOS and macOS, CPU on Android and desktop. No cloud, no API key.
5
-version: 0.1.1
5
+version: 0.1.2
6
repository: https://github.com/ondeinference/onde
7
homepage: https://ondeinference.com
8
issue_tracker: https://github.com/ondeinference/onde/issues