Sean Fang

The FLOPS is currently implemented by the lookup table. You can add more as per your needs. https://github.com/exo-explore/exo/blob/1e4524b5c0fc1bf74aab20b9ef2ae1e1b1b7de1a/exo/topology/device_capabilities.py#L82-L84

### FLOPS showing Dose it shows `NVIDIA GEFORCE RTX 3080 (10 GB)` on your linux machine? It has to be exactly the same so the lookup table can work. If...

I agree with supporting one exo instance that uses multiple GPUs. This approach would allow us to shard more when only one model is inferencing. What do you think?

Hi @FFAMax , After install the package, are you able to load the model into the GPU? I had the same issue, but after install that, it still doesn't work....

I'm working on this issue! can you assign this to me🙏🏻

Hello @geohot , I'm working on this, can you assign this to me? While I checked the [latest version](https://github.com/python/mypy/releases/tag/v1.13.0) of `mypy` , it is now 1.13.0 , should we go...

Hello @AlexCheema, I would like to work on this, could you assign it to me? Thank you🙏🏻

Hi @AlexCheema, Thanks for checking in! I've made some progress, the core functionality is implemented, you can see it [here](https://github.com/Sean-fn/exo/commit/53ea5767a18631b9c967c4c0fa46d0548f852042) , but as this is my first open-source contribution, I'm...

Hello, team! I'm excited to contribute to this project. My background is primarily in Python, with more focus on machine learning, particularly in: - Computer vision - Natural language processing...