polvalente
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`.
Where Next?
Trending in News & Updates
Other Trending Topics
Latest on Elixir Forum
Sponsor Spotlight
Deploy Phoenix to your own VPS with PaaS ease: push-to-deploy, zero downtime, auto SSL, managed Postgres. 14-day free trial at potions.io
Categories:
Sub Categories:
Forums
Popular Tags
- #ecto
- #liveview
- #troubleshooting
- #learning-elixir
- #library
- #deployment
- #erlang
- #testing
- #genserver
- #mix
- #absinthe
- #remote-other
- #otp
- #plug
- #how-to-question
- #macros
- #postgres
- #elixirconf
- #channels
- #exunit
- #discussion
- #code-sync
- #podcasts
- #javascript
- #onsite
- #dialyzer
- #docker
- #authentication
- #umbrella
- #full-time-contract
- #podcasts-by-brainlid
- #ai
- #ecto-query
- #elixirconf-us
- #blog-post
- #elixir-ls
- #phoenix_html
- #iex
- #graphql
- #genstage
- #websockets
- #supervisor
- #advent-of-code
- #distillery
- #processes
- #elixirconf-eu
- #api
- #forms
- #metaprogramming
- #hex
Our Sponsors
Supporting innovation across the BEAM ecosystem.
We build reliable cloud platforms for business-critical systems.
Catch errors, track performance, monitor hosts and more.
Error tracking, logs, uptime, and Just Enough APM. Built for developers.
Elixir, Erlang & BEAM conferences from Code Sync - join us in 2026!
Practical resources that improve the lives of professional developers.
Bringing learning, work and compliance together since 1987.
The deployment platform built for Elixir: PaaS ease, VPS control.
The team behind Membrane, Popcorn, LiveDebugger. Available for hire.
Courses that'll move you from confusion to "Aha, now I get it!"
Showing Posts 11 to 2- Show Best Posts
- Show All (oldest first)
- Show All (newest first)
manhvu
Yes, it sounds like he was right.
Currently, I’m trying to bring CubeCL in as a backend for Nx. These days, Rust is quite good for ML/AI and big data, so I want to work with a combination of Elixir and Rust.
GenericJam
It looks like @polvalente was right all along and NxIREE is the way to harness Vulkan.
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
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
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
The answer is EMLX on iOS and Vulkan on Android. These changes should be upstream shortly.
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.
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
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
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!