update readme for dgx spark support

2026-09-11 21:08:48 -04:00 · 2026-04-23 12:43:18 +01:00
3 changed files with 21 additions and 6 deletions
@@ -1,3 +1,13 @@
-*   @ToxicPine
-*   @AlexCheema
-*   @GeluVrabie
+# default reviewers
+*         @evanev7
+
+# filetypes
+*.svelte  @ciaranbor
+*.swift   @ciaranbor @AlexCheema
+*.nix     @evanev7
+*.rs      @evanev7
+
+# folders
+bench     @rltakashige @ciaranbor
+nix       @evanev7
+src       @evenev7 @rltakashige
@@ -5,10 +5,14 @@
 Apple Silicon MacOS
 - Mac Studio: M3 Ultra
 - Mac Mini: M4 Pro
- Macbook Pro: M5, M4 Max
+- Macbook Pro: M5 Max, M5 Pro, M5, M4 Max
+
+Linux CPU Support

 ## Tier 2 support - checked occasionally, should run without crashing

+Linux CUDA Support
+- Nvidia DGX Spark

 ## Tier 3 support - minimal support and testing, but no theoretical reason it shouldnt work

@@ -20,8 +24,6 @@ Apple Silicon MacOS
 Linux CUDA Support
 - Nvidia DGX Spark

-Linux CPU Support
-
 ## Tier 2

 Linux Vulkan Support -- depends heavily on ecosystem
@@ -193,6 +193,9 @@ This starts the exo dashboard and API at http://localhost:52415/

 **Important note for Linux users:** Currently, exo runs on CPU on Linux. GPU support for Linux platforms is under development. If you'd like to see support for your specific Linux hardware, please [search for existing feature requests](https://github.com/exo-explore/exo/issues) or create a new one.

+**Connectivity:**
+If you intend to connect a linux device directly to a mac (thunderbolt, ethernet) without a router, both devices need IPv4 addresses. The MacOS app assigns these, the linux equivalent varies by distro. For ubuntu, run `avahi-autoipd` on the relevant interface. For example for the DGX Spark, you may run `sudo avahi-autoipd -D -w enP7s7` to start the avahi IPv4 daemon on the Spark's ethernet port.
+
 **Configuration Options:**

 - `--no-worker`: Run exo without the worker component. Useful for coordinator-only nodes that handle networking and orchestration but don't execute inference tasks. This is helpful for machines without sufficient GPU resources but with good network connectivity.