Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@ English | [中文](README_zh.md) | [日本語](README_ja.md) | [Español](README
## News

- **[2026-09-30]** We released the **edge0 inference engines for four platforms — iOS, macOS, Android and Windows** — so users get the best inference experience across architectures and platforms. The source is open-sourced in this repo ([`ios/`](ios/) · [`macos/`](macos/) · [`android/`](android/) · [`windows/`](windows/)) — see each directory's README for details. The **unified inference framework** follows in **Q4 2026**; see the [Roadmap](#roadmap).
- **[2026-09-20]** `--prefill-ondemand` lands for `edge0 demo / chat / serve` ([#112](https://github.com/Edge0-AI/Edge0/pull/112)).
- **[2026-09-16]** Our technical report is on arXiv: [The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction](https://arxiv.org/abs/2609.18063).
- **[2026-09-08]** Initial open-source release of **edge0**, together with both model tiers — [`Edge0-35B-A3B-preview`](https://huggingface.co/Edge0/Edge0-35B-A3B-preview) and [`Edge0-8B-A1B-preview`](https://huggingface.co/Edge0/Edge0-8B-A1B-preview) — on Hugging Face and ModelScope.

Expand Down
1 change: 0 additions & 1 deletion README_es.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@
## Novedades

- **[2026-09-30]** Lanzamos los **motores de inferencia de edge0 para cuatro plataformas — iOS, macOS, Android y Windows** — de modo que los usuarios obtienen la mejor experiencia de inferencia en todas las arquitecturas y plataformas. El código fuente se ha liberado en este repositorio ([`ios/`](ios/) · [`macos/`](macos/) · [`android/`](android/) · [`windows/`](windows/)) — consulta el README de cada directorio para más detalles. El **framework de inferencia unificado** llegará en **Q4 2026**; consulta la [Hoja de ruta](#hoja-de-ruta).
- **[2026-09-20]** `--prefill-ondemand` llega a `edge0 demo / chat / serve` ([#112](https://github.com/Edge0-AI/Edge0/pull/112)).
- **[2026-09-16]** Nuestro informe técnico está en arXiv: [The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction](https://arxiv.org/abs/2609.18063).
- **[2026-09-08]** Primera versión de código abierto de **edge0**, junto con los dos niveles de modelos — [`Edge0-35B-A3B-preview`](https://huggingface.co/Edge0/Edge0-35B-A3B-preview) y [`Edge0-8B-A1B-preview`](https://huggingface.co/Edge0/Edge0-8B-A1B-preview) — en Hugging Face y ModelScope.

Expand Down
1 change: 0 additions & 1 deletion README_fr.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@
## Actualités

- **[2026-09-30]** Nous avons publié les **moteurs d'inférence edge0 pour quatre plateformes — iOS, macOS, Android et Windows** — afin d'offrir aux utilisateurs la meilleure expérience d'inférence à travers les architectures et les plateformes. Le code source est publié en open source dans ce dépôt ([`ios/`](ios/) · [`macos/`](macos/) · [`android/`](android/) · [`windows/`](windows/)) — consultez le README de chaque répertoire pour plus de détails. Le **framework d'inférence unifié** suivra au **T4 2026** ; voir la [Feuille de route](#feuille-de-route).
- **[2026-09-20]** `--prefill-ondemand` arrive pour `edge0 demo / chat / serve` ([#112](https://github.com/Edge0-AI/Edge0/pull/112)).
- **[2026-09-16]** Notre rapport technique est sur arXiv : [The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction](https://arxiv.org/abs/2609.18063).
- **[2026-09-08]** Première publication open source d'**edge0**, avec les deux gammes de modèles — [`Edge0-35B-A3B-preview`](https://huggingface.co/Edge0/Edge0-35B-A3B-preview) et [`Edge0-8B-A1B-preview`](https://huggingface.co/Edge0/Edge0-8B-A1B-preview) — sur Hugging Face et ModelScope.

Expand Down
1 change: 0 additions & 1 deletion README_ja.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@
## ニュース

- **[2026-09-30]** **4 つのプラットフォーム — iOS、macOS、Android、Windows — 向けの edge0 推論エンジン**をリリースしました。ユーザーはアーキテクチャとプラットフォームをまたいで最適な推論体験を得られます。ソースはこのリポジトリでオープンソース化されています([`ios/`](ios/) · [`macos/`](macos/) · [`android/`](android/) · [`windows/`](windows/))— 詳細は各ディレクトリの README を参照してください。**統合推論フレームワーク**は **2026 年 Q4** に控えています。[ロードマップ](#ロードマップ)を参照。
- **[2026-09-20]** `edge0 demo / chat / serve` に `--prefill-ondemand` が登場([#112](https://github.com/Edge0-AI/Edge0/pull/112))。
- **[2026-09-16]** 技術レポートが arXiv に掲載: [The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction](https://arxiv.org/abs/2609.18063)。
- **[2026-09-08]** **edge0** の初オープンソースリリース。両モデルティア — [`Edge0-35B-A3B-preview`](https://huggingface.co/Edge0/Edge0-35B-A3B-preview) と [`Edge0-8B-A1B-preview`](https://huggingface.co/Edge0/Edge0-8B-A1B-preview) — を Hugging Face と ModelScope で同時公開。

Expand Down
2 changes: 0 additions & 2 deletions README_zh.md
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,6 @@
体验。四端源码已开源至本仓库([`ios/`](ios/) · [`macos/`](macos/) ·
[`android/`](android/) · [`windows/`](windows/)),更多细节见各目录
README;**统一推理框架**将于 **2026 Q4** 发布,详见[路线图](#路线图)。
- **【2026-09-20】** `edge0 demo / chat / serve` 新增 `--prefill-ondemand`
([#112](https://github.com/Edge0-AI/Edge0/pull/112))。
- **【2026-09-16】** 技术报告上线 arXiv:[The Other Half of the Memory
Wall: Serving 35B MoEs from SSD with Trained Routing
Prediction](https://arxiv.org/abs/2609.18063)。
Expand Down
Loading