search

johnmai-dev / ChatMLX

🤖✨ChatMLX is a modern, open-source, high-performance chat application for MacOS based on large language models.
Apache License 2.0
625 stars 43 forks source link

Show Currently Using CPU or Not #19

Open owenzhao opened 3 weeks ago

owenzhao commented 3 weeks ago

Sometimes ChatMLX shows answers slowly and CPU gets near 100% with 0 GPU usage. Then I know the acceleration didn't work.

After I quit ChatMLX and restart it, everything works fine again.

So maybe ChatMLX can remind me when the performance is down.

johnmai-dev commented 3 weeks ago

Can you tell me which model you are using? It might be an issue triggered by MLX

owenzhao commented 3 weeks ago

I didn't notice which model at that time. But I only have those models.

Screenshot 2024-10-17 at 11 11 05 AM
owenzhao commented 3 weeks ago

I just have tried all models above and all can use GPU now.

I removed a model with "vision" yesterday as it didn't work with ChatMLX. It was begin with Phi-3.5 and downloaded from MLX community. Maybe the performance dropped after the error showing in that model?