polvalente
Nx Core Team
Nx, EXLA and Torchx 0.12 have just been published!
This update set comes with the new Nx.block abstraction and the EXLA.CustomCall protocol, which together will allow users to provide native C or CUDA implementations for certain sections of Nx code.
EMLX 0.3 (the official MLX backend for Nx) is also out, with:
- Support for the more recent concurrency model provided by MLX
- EMLX.Fast for a few fused operations (used in the upcoming emlx_axon library, pending Axon and Bumblebee releases in the next few days)
- Support for quantized types
- A zero-copy implementation of `Nx.to_binary/1`.
Trending in News & Updates
Today we’re releasing Oban for Python. Not an Oban client in Python. Not a pythonx wrapper embedded in Elixir. Nope, it’s a fully operati...
New
I’m a bit excited to announce that Localize and friends are now at release 1.0. Even though it’s a 1.0 release, it stands on 8 years of w...
New
I’ll be using this thread to share Hologram patch release announcements. Minor releases will continue to get dedicated threads with blog ...
New
Hologram v0.11 is out! Two headline features this release. First, Elixir regexes now run in the browser. They were server-only until now,...
New
Just published search_ash 0.5.0 (with search_core 0.4.0) on Hex.
What’s new: synonyms
You can now declare a synonym dictionary per lang...
New
MdexMultilineCells is an MDEx plugin enabling multi-line cells in Markdown tables with full
inline/block Markdown rendering and automati...
New
This release unifies configuration for queues, repos, and services, swaps opaque timing integers for readable durations, and backports pe...
New
Other Trending Topics
I am happy to introduce the very α version of the new programming language compiled to BEAM.
Welcome Cure.
It has literally three kille...
New
Hobbes is a low-level distributed database for the Elixir programming language.
Hobbes provides a simple, safe, and scalable storage lay...
New
ExRatatui lets you cook up rich terminal UIs in Elixir, powered by Rust’s ratatui via Rustler NIFs. Build interactive terminal applicatio...
New
Hello everyone. After busy few months I am happy to announce v0.1.0 of Emerge & Solve.
They are GUI (Emerge) and State management (S...
New
Corex is an accessible, unstyled UI component library for Phoenix that integrates Zag.js state machines using Vanilla JavaScript and Live...
New
There are three potential reasons for members of this forum to have a look at https://vutuv.de
You are tired or annoyed of LinkedIn.
Yo...
New
Categories:
Sub Categories:
Forums
Popular Tags
- #ecto
- #liveview
- #troubleshooting
- #learning-elixir
- #deployment
- #library
- #erlang
- #testing
- #genserver
- #mix
- #absinthe
- #remote-other
- #otp
- #plug
- #how-to-question
- #macros
- #postgres
- #elixirconf
- #channels
- #exunit
- #discussion
- #code-sync
- #javascript
- #podcasts
- #onsite
- #dialyzer
- #docker
- #authentication
- #umbrella
- #full-time-contract
- #podcasts-by-brainlid
- #ecto-query
- #blog-post
- #elixir-ls
- #ai
- #elixirconf-us
- #phoenix_html
- #iex
- #graphql
- #genstage
- #websockets
- #supervisor
- #advent-of-code
- #distillery
- #processes
- #api
- #forms
- #hex
- #security
- #metaprogramming










Showing Posts 1 to 10- Show Best Posts
- Show All (oldest first)
- Show All (newest first)
Chapaman
polvalente
emlx_axon has been published!
By using it (see this benchmark for an example), we can accelerate certain Bumblebee models without rewriting code for performance when using EMLX! For example, the Qwen3-0.6B-4bit model goes from ~10 tokens/s to ~42 tokens/s on my machine just by using the provided Axon node rewrites!
manhvu
Hi @polvalente, I’m trying to bring Nx + EMLX to iOS. Do you have any suggestions?
Currently, I support inference first, and plan to add basic on-device training later.
polvalente
@manhvu , @GenericJam was able to run EMLX on device, which means all of Nx can run! We’re working to upstream what he needs so that no patches are needed, just config!
manhvu
Thanks for the response. I added support for Nx to my framework, and over the next few days I’ll verify and test everything.
For inference, I currently support both the Nx ecosystem and ONNX Runtime (for cross-platform support), but I’ll add Nx support on Android again soon.
GenericJam
The answer is EMLX on iOS and Vulkan on Android. These changes should be upstream shortly.
manhvu
EMLX for iOS because it can use Core ML. I’m not sure about Vulkan yet; it doesn’t seem stable enough. I’m still looking for a way to use the mobile GPU on both iOS and Android for on-device training for edge AI.
GenericJam
You can try this GitHub - GenericJam/nx_vulkan: Vulkan compute Nx.Backend — cross-platform GPU acceleration for Nx · GitHub
Example lib GitHub - GenericJam/nxeigen_probe: Reference Mob app — cross-platform YOLOv8n via EMLX (iOS) + NxVulkan (Android) · GitHub
manhvu
Nice, you’ve done that
I looked for the best solution, but it sounds like I need to separate them. Currently, only WebGPU can run on both platforms, so I’ll try to adapt Nx to it.
GenericJam
It looks like @polvalente was right all along and NxIREE is the way to harness Vulkan.