Victor Nogueira
Victor Nogueira
> Does this error also happen when configuring Wllama with `n_threads: 1`? (forcing it to single-thread)
> I got the vague notion that .gguf files have template information within them? > > Currently I use Transformers.js to turn a conversation dictionary into a templated string, and...
That was a great investigation!
A wonderful tool that you've created, @flatsiedatsie! Watched closely how much effort you've put into it. And the final result is working pretty well! Transitions and loaders made the UX...
Oh yes, I've noticed it while reading the About section on the website ✌️ Fair enough!
Thanks for using this provider! That's an interesting issue. Haven't seen anything like this before. There haven't been any changes on the GPG key since the first release. And I...
That's a great point. It might be the cause indeed, because, although [it's there](https://search.opentofu.org/provider/aminueza/minio), we haven't officially registered this provider to OpenTofu. But this issue just showed it's a good...
The support for `/v1/responses` endpoint has been added in LM Studio v0.3.29: https://lmstudio.ai/blog/lmstudio-v0.3.29
Hi, @awtsmoos! As far as I know, this isn't possible in llama.cpp (which Wllama is based on). I recall this being a feature in [AirLLM](https://github.com/lyogavin/airllm), but unfortunately, AirLLM can't be...