Mikhail Komarov

I use ollama for auto-completion. Regarding your question, qwen2.5-coder is suitable for auto-completion (https://ollama.com/library/qwen2.5-coder ). But you can also add "supportsFIM": true in the settings of any model, and it...

Finished writing /v1/audio/transcription. Approximate logic of the code: A request comes in for /v1/audio/transcription Converted to 16-bit Wav format using ffmpeg (I couldn't find another way except calling subprocess.run, so...

I'll try to make whisper-server not stop immediately after receiving a request tomorrow. I'll also look at llama_runner_manager.py and llama-runner-thread.py files later.

I wrote a raw version and added it to my fork. We need to run tests. I will add /v1/audio/translations in the near future. https://github.com/hardWorker254/llama-runner-tools-fix I will also double-check the...

I have Fedora 42 also and does not have this issue. You can change howdy config(sudo howdy config) to my. Don't forget to replace device_path to your value. \# Howdy...

Add any Ollama model (Local tab). You can do this without even having an ollama.

You just add the model to bypass the introductory window. You can delete it after and add what you need.

@vrtnis When is the new binary release coming out? I'm looking forward to the new update. Also, thanks for your hard work and the existence of void!