1 Pull request merged by 1 person

• downgrade grpcio, grpcio-tools to 1.70.0

  #800 merged Mar 21, 2025

1 Pull request opened by 1 person

• Intel Arc Support

  #791 opened Mar 19, 2025

12 Issues opened by 9 people

• error "Item size 2 for PEP 3118 buffer format string B does not match the dtype B item size 1"

  #799 opened Mar 21, 2025

• cpu mode is need 4 Dependency

  #798 opened Mar 20, 2025

• How to Prioritize Thunderbolt 5 Connection in Exo?

  #796 opened Mar 20, 2025

• I get the following error when I start exo. How can I fix it?

  #795 opened Mar 20, 2025

• I get the following error when I start exo. How can I fix it?

  #794 opened Mar 20, 2025

• grpc problem

  #793 opened Mar 20, 2025

• Broken `from exo import DEBUG` when built in isolated Nix environment on OS X

  #792 opened Mar 19, 2025

• Program Encounters Error After Long Runtime

  #790 opened Mar 19, 2025

• Inference speed is too slow on linux

  #789 opened Mar 18, 2025

• Can someone help this noob (2 node cluster unresponsive)

  #788 opened Mar 17, 2025

• 一个节点可以看到另一个节点，但不是相互的。

  #787 opened Mar 17, 2025

• 2 mac cluster ,different ip adress.

  #786 opened Mar 16, 2025

18 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Not working on WSL (debian) on Windows 11

  #536 commented on Mar 16, 2025 • 0 new comments

• Question: How to link Ubuntu 24.04 (Kernel: 6.8.0-51-generic) with Apple Silicone machines.

  #642 commented on Mar 16, 2025 • 0 new comments

• Support for Windows Platform

  #606 commented on Mar 16, 2025 • 0 new comments

• GTX 1060 6GB on Fedora 41 - detected but reporting 0.0TFLOPS

  #773 commented on Mar 17, 2025 • 0 new comments

• Why is there no DeepSeek model download

  #757 commented on Mar 17, 2025 • 0 new comments

• Jetson devices reload the model and the inference speed is too slow (llama3.2-1b, 8bit)

  #777 commented on Mar 18, 2025 • 0 new comments

• Flooding GRPC errors when downloading models

  #655 commented on Mar 18, 2025 • 0 new comments

• Feature request: Download models only once, then distribute it to nodes

  #483 commented on Mar 20, 2025 • 0 new comments

• [BOUNTY - $100] Vision Model Integration Test

  #328 commented on Mar 20, 2025 • 0 new comments

• nvidia nvml destory the start in docker without nvidia gpu

  #557 commented on Mar 21, 2025 • 0 new comments

• Nodes do not find each other

  #520 commented on Mar 21, 2025 • 0 new comments

• Required ports to open?

  #740 commented on Mar 21, 2025 • 0 new comments

• Android device loading model reports CLANG error

  #152 commented on Mar 22, 2025 • 0 new comments

• [BOUNTY - $500] Llama.cpp inference engine

  #167 commented on Mar 22, 2025 • 0 new comments

• [Bounty] PyTorch & HuggingFace Interface

  #139 commented on Mar 19, 2025 • 0 new comments

• feat: Use uv for Python Environment Management to Improve Install Speed

  #333 commented on Mar 20, 2025 • 0 new comments

• feature: headscale support

  #739 commented on Mar 18, 2025 • 0 new comments

• Structural generation and function calling / tool use

  #771 commented on Mar 21, 2025 • 0 new comments