feat: ExecuTorch 1.3 with MLX (iOS) and Vulkan (Android) backends + Gemma 4 E2B by NorbertKlockiewicz · Pull Request #1223 · software-mansion/react-native-executorch

deps: bump executorch to 1.3 and add mlx libraries

NorbertKlockiewicz

committed

Add MLX backend support with metadata-driven chunked prefill

NorbertKlockiewicz

and

claude

committed

Update prebuilt binaries to 1.3 with MLX (iOS) and Vulkan (Android)

NorbertKlockiewicz

and

claude

committed

Add Gemma 4 E2B to the model registry (MLX default on iOS)

NorbertKlockiewicz

and

claude

committed

Add Gemma 4 E2B (Vulkan on Android) and fix dynamic-shape generation budget

NorbertKlockiewicz

and

claude

committed

Update Android binaries to 1.3 Vulkan build with Gemma4 SDPA + RMSNorm

NorbertKlockiewicz

and

claude

committed

Consolidate Gemma 4 E2B tokenizers and pin MLX multimodal to HF URLs

NorbertKlockiewicz

and

claude

committed

Address review: single Gemma 4 E2B export with platform defaults, LLM Multimodal category

NorbertKlockiewicz

and

claude

committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: ExecuTorch 1.3 with MLX (iOS) and Vulkan (Android) backends + Gemma 4 E2B#1223

feat: ExecuTorch 1.3 with MLX (iOS) and Vulkan (Android) backends + Gemma 4 E2B#1223
mkopcins merged 8 commits into
mainfrom
@nk/mlx-support

Commits on Jun 11, 2026

deps: bump executorch to 1.3 and add mlx libraries

Add MLX backend support with metadata-driven chunked prefill

Update prebuilt binaries to 1.3 with MLX (iOS) and Vulkan (Android)

Add Gemma 4 E2B to the model registry (MLX default on iOS)

Add Gemma 4 E2B (Vulkan on Android) and fix dynamic-shape generation budget

Update Android binaries to 1.3 Vulkan build with Gemma4 SDPA + RMSNorm

Consolidate Gemma 4 E2B tokenizers and pin MLX multimodal to HF URLs

Address review: single Gemma 4 E2B export with platform defaults, LLM Multimodal category