rltakashige

Results 4 comments of rltakashige

how to load model in exo

Probably quite a bit easier in EXO 1.0 - just select it from the dropdown.

Two M3 Ultra are running the model qwen3-coder-480b-a35b-8bit. An error is thrown when using VS Code Client.

I've also seen this issue when running DeepSeek V3.1 in pipeline parallel (it does not happen in tensor parallel). Have not encountered this in Qwen Coder, but do want to...

Network discovery over VPN

https://github.com/exo-explore/exo/issues/879#issuecomment-3670942858

exo labs seems to be suffering form a possible memory leak

Seems to be more of an issue when running transformers. This is noted. Please reraise if this is an issue.