1.1.2

index bdb3c29..15556db 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -3198,7 +3198,7 @@ checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe" [[package]] name = "onde" -version = "1.1.1" +version = "1.1.2" dependencies = [ "anyhow", "cc",

index 654bc52..87b56ba 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "onde" -version = "1.1.1" +version = "1.1.2" edition = "2021" description = "On-device inference engine for Apple silicon." license = "MIT OR Apache-2.0"

index edcabbf..b4a75fe 100644 --- a/sdk/dart/CHANGELOG.md +++ b/sdk/dart/CHANGELOG.md @@ -1,3 +1,9 @@ +## 1.1.2 + +- tvOS support: 0.5B model default, memory-optimized model builder, snapshot cache repair +- New `configure_cache_dir` FFI function for sandboxed platforms +- New `qwen25_0_5b_config()` free function + ## 1.1.1 * **Apple SDK compatibility:** Pulls in the Onde Rust core `1.1.1` Apple deployment-target build fixes so downstream macOS consumers do not inherit newer-than-expected minimum OS metadata from the packaged native binaries.

index 0fc000a..49cd475 100644 --- a/sdk/dart/pubspec.yaml +++ b/sdk/dart/pubspec.yaml @@ -2,7 +2,7 @@ name: onde_inference description: >- On-device LLM inference for Flutter & Dart. Run Qwen 2.5 models locally with Metal on iOS and macOS, CPU on Android and desktop. No cloud, no API key. -version: 1.1.1 +version: 1.1.2 repository: https://github.com/ondeinference/onde homepage: https://ondeinference.com documentation: https://ondeinference.com/sdk/dart

index cf12aeb..04c5692 100644 --- a/sdk/dart/rust/Cargo.lock +++ b/sdk/dart/rust/Cargo.lock @@ -3399,7 +3399,7 @@ checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe" [[package]] name = "onde" -version = "1.1.1" +version = "1.1.2" dependencies = [ "anyhow", "cc",

index 30538de..ce59788 100644 --- a/sdk/kotlin/gradle.properties +++ b/sdk/kotlin/gradle.properties @@ -10,7 +10,7 @@ kotlin.code.style=official # Maven publishing coordinates — keep in sync with Cargo.toml [package] version GROUP=com.ondeinference POM_ARTIFACT_ID=onde-inference -VERSION_NAME=1.1.1 +VERSION_NAME=1.1.2

index 7b5ec7b..0034af2 100644 --- a/sdk/react-native/CHANGELOG.md +++ b/sdk/react-native/CHANGELOG.md @@ -1,3 +1,9 @@ +## 1.1.2 + +- tvOS support: 0.5B model default, memory-optimized model builder, snapshot cache repair +- New `configure_cache_dir` FFI function for sandboxed platforms +- New `qwen25_0_5b_config()` free function + ## 1.0.0 This is the first stable release. Onde has already been running in real App Store apps for a while, so it felt like time to leave `0.x` behind.

index fed7060..eae3698 100644 --- a/sdk/react-native/package.json +++ b/sdk/react-native/package.json @@ -1,6 +1,6 @@ { "name": "@ondeinference/react-native", - "version": "1.1.1", + "version": "1.1.2", "description": "On-device LLM inference for React Native. Run Qwen 2.5 models locally with Metal on iOS, CPU on Android. No cloud, no API key.", "main": "build/index.js", "types": "build/index.d.ts",

index cce970e..7c3b601 100644 --- a/sdk/react-native/rust/Cargo.lock +++ b/sdk/react-native/rust/Cargo.lock @@ -3215,7 +3215,7 @@ checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe" [[package]] name = "onde" -version = "1.1.1" +version = "1.1.2" dependencies = [ "anyhow", "cc", @@ -3489,7 +3489,7 @@ dependencies = [ [[package]] name = "onde-react-native" -version = "1.1.1" +version = "1.1.2" dependencies = [ "jni", "log",

index 9538123..ba0ea7e 100644 --- a/sdk/react-native/rust/Cargo.toml +++ b/sdk/react-native/rust/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "onde-react-native" -version = "1.1.1" +version = "1.1.2" edition = "2021" publish = false

index 2362871..4380816 100644 --- a/src/inference/engine.rs +++ b/src/inference/engine.rs @@ -409,8 +409,8 @@ impl ChatEngine { // so the auto device mapper allocates far less memory. #[cfg(target_os = "tvos")] { - use mistralrs_core::AutoDeviceMapParams; use mistralrs::DeviceMapSetting; + use mistralrs_core::AutoDeviceMapParams; builder = builder .with_max_num_seqs(1)