Skip to content

Releases: software-mansion/react-native-executorch

v0.5.2

29 Aug 08:41
9cb5f03
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.5.1...v0.5.2

v0.5.1

22 Aug 09:06
66edaee
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.5.0...v0.5.1

v0.5.0 🚀

21 Aug 14:57
1236776
Compare
Choose a tag to compare

Announcing React Native ExecuTorch v0.5.0 ⚛️

What’s new?

🏎️ A full native code rewrite based on C++ JSI bindings enabling zero-copy data transfer between native code and JS
🔥 Up to 2x faster Whisper transcription on iOS
📷 CLIP - extract semantic meaning of images
🚴 Significant improvements to the performance of text embeddings
🧘 Rewrite of the STT streaming API delivering better qualitative results & DX
🐐 Specify LLM structured output schemas using zod
👌 LLMs now correctly handle Unicode/emoji in outputs

⚠️ Breaking changes

  • Multiple model instances: JSI bindings remove the static singleton limitation. You can now create and run multiple instances of the same model simultaneously.
  • We've replaced separate URL imports with bundled model objects. Instead of manually specifying modelSource, tokenizerSource, and tokenizerConfigSource, just pass a single object like LLAMA_3_2_1B. The individual URLs are still accessible as properties if you need them.
import {
  useLLM,
  LLAMA3_2_1B,
} from 'react-native-executorch';

// Current API:
const llm = useLLM({ model: LLAMA3_2_1B });

// Previous API:
const llama = useLLM({
  modelSource: LLAMA3_2_1B,
  tokenizerSource: LLAMA3_2_TOKENIZER,
  tokenizerConfigSource: LLAMA3_2_TOKENIZER_CONFIG,
});

v0.4.8

29 Jul 07:21
829375d
Compare
Choose a tag to compare

What's Changed

  • fix: Executorchmodule BigInt64Array handling by @jakmro in #470
  • fix: error messages formatting by @jakmro in #476

Full Changelog: v0.4.7...v0.4.8

v0.4.7

09 Jul 13:59
edf188c
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.4.6...v0.4.7

v0.4.6

25 Jun 12:26
Compare
Choose a tag to compare

Full Changelog: v0.4.5...v0.4.6

  • Changed version of executorch.aar to point to a specific release

v0.3.4

25 Jun 13:00
dea16ea
Compare
Choose a tag to compare

Relase Notes:

  • changed version of executorch.aar to point to specific release

v0.4.5

18 Jun 13:31
Compare
Choose a tag to compare
  • Fixes and new non-breaking features in useLLM and LLMModule (#406)

Full Changelog: v0.4.4...v0.4.5

v0.4.4

17 Jun 10:01
Compare
Choose a tag to compare
  • Fixes multilingual Whisper not using the multilingual token (#398)

Full Changelog: v0.4.3...v0.4.4

v0.4.3

05 Jun 14:27
Compare
Choose a tag to compare
  • Removed left over react-native-audio-api dependency
  • Fixed error when transcribing audio file shorter than windowSize + overlapSeconds (single chunk file) with transcribe method
  • Fixed being able to run inference on LLMs models when they are already generating a response.

Full Changelog: v0.4.2...v0.4.3