| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-09-25 | 1.2 kB | |
| v0.10.3 source code.tar.gz | 2026-09-25 | 20.3 MB | |
| v0.10.3 source code.zip | 2026-09-25 | 22.5 MB | |
| Totals: 3 Items | 42.9 MB | 0 | |
Patch release moving to v0.10.4-libs, whose XNNPACK backend fixes PReLU models returning NaN and Kokoro TTS being killed on iPhone, plus LLM and install fixes. LLMRunner.generate no longer takes echo; the prompt is never echoed.
What's Changed
- fix(libs): stop shipping backends the app opted out of by @msluszniak in https://github.com/software-mansion/react-native-executorch/pull/1466
- fix(llm): keep every terminal token out of the chat response by @msluszniak in https://github.com/software-mansion/react-native-executorch/pull/1486
- fix(llm): chunk prefill at the bound the graph declares by @msluszniak in https://github.com/software-mansion/react-native-executorch/pull/1491
- fix(llm): pin the model load mode instead of inheriting upstream defaults by @msluszniak in https://github.com/software-mansion/react-native-executorch/pull/1492
- fix(install): make the native lib download work on Windows by @msluszniak in https://github.com/software-mansion/react-native-executorch/pull/1494
Full Changelog: https://github.com/software-mansion/react-native-executorch/compare/v0.10.2...v0.10.3
