Executorch
PulseAugur coverage of Executorch — every cluster mentioning Executorch across labs, papers, and developer communities, ranked by signal.
- 2026-09-10 product_launch React Native Executorch released version 0.10.0, achieving up to 92x speed improvement. source
2 day(s) with sentiment data
-
React Native Executorch achieves 92x speed boost with new TypeScript pipelines
The React Native Executorch project has released version 0.10.0, achieving a significant speed improvement of up to 92x. This update replaces monolithic native modules with inspectable TypeScript pipelines. The new vers…
-
Meta releases Muse Glimmer, a 30B agent model for efficient local operation
Meta has released Muse Glimmer, a 30 billion parameter multimodal agent model designed for efficient local operation with a 128K context window. The model employs a hybrid attention mechanism, combining local attention …
-
CropCop: Auditable 120-Class Plant-Health Model Developed
Researchers have developed CropCop, a plant-health recognition system capable of classifying 120 distinct plant health conditions. The system's development involved reconstructing a benchmark dataset from over 117,000 i…
-
Meta releases open-source agentic model Muse Glimmer for local use
Meta has released Muse Glimmer, an open-source agentic model designed for local execution on personal computers and Macs. This 30-billion parameter model, licensed under Apache 2.0, is optimized for "always-on" agent wo…
-
Meta's Muse Glimmer 30B model brings powerful AI agents to consumer GPUs
Meta has released Muse Glimmer, a 30-billion-parameter open-weight model optimized for local AI agent workflows, capable of running on a single consumer GPU. This model, released under an Apache 2.0 license, offers comp…
-
Meta releases Muse Glimmer, a 30B open-weight model for local AI agents
Meta has released Muse Glimmer, a 30-billion-parameter open-weight model optimized for local agentic workflows. This model is designed to run on consumer hardware, such as a single GPU, making it accessible for personal…
-
Qwen3 LLM runs up to 4.52x faster on Apple Silicon with ExecuTorch MLX delegate
A recent technical exploration demonstrates significant speed improvements when running the Qwen3-0.6B language model on Apple Silicon using ExecuTorch's experimental MLX delegate. The MLX delegate, which leverages Appl…
-
New research enables faster, more efficient LLMs on mobile devices
Researchers have developed new methods for deploying large language models on mobile devices, focusing on reducing latency and memory usage. One approach, MobileLLM-Flash, uses hardware-in-the-loop architecture search a…