Unleashed.Chat v0.1.1 is live!
Now hit 1k+ users, this release adds more scalable infrastructure
-Vector embeddings of nostr notes now stored in Redis–fast again!
-Key infra components are now automated
- App health monitoring and automatic remediation in case of container crashes or similar
What are you using for inference if I can ask, just curiosity
Please Login to reply.
Which interface?
No for the text generation inference (the server that runs the llms), I was researching the different options available, some cool ones are huggingface tgi, llama.cpp, vllm