LLMs deployment. Hugging Face Text Generation Inference and alternatives

[@mateuszwozny363]

Nice work. I was wondering if Ollama could be another alternative for TGI?

[@bg-mq5hz]

Nicely explained. Thank you.

[@prashiltumbade9130]

Great overview!!! Another alternative to consider would be Nvidia Triton Inference Server

[@achmedzhanov_nail]

ollama is good alternative

[@DoomsdayDatabase]

Watching after a few months 🥲Hopefully not that different now