NoRaincheck

LLMs - in Review (2024)

LLMs - in Review (2024)

December 2024

2024 was the first year where I took LLMs seriously. I successfully hosted a Llama 70b parameter model in production which was used as with continue.dev for a self-hosted co-pilot replacement, along with a code autocomplete like Qwen Coder or Deepseek, these were fine replacements and surprisingly robust. Huggingface’s TGI along with Triton Server were the main heroes for this project, (Triton was used to serve onnx models for embeddings) though I’ve yet to find a “good” embedding model. At this stage in time, most of the vector database solutions “feel” the same and can all seemingly be trivially hosted via Kubernetes.

Tools used:

Optimising usage of LLMs at scale is still a massive challenge, particularly when opening up for general access. The space is still new so there are still lots of patterns especially related to agentic patterns which need to be explored. On that particular note, this particular blog post from Anthropic is something I’m looking at working on in the new year. At the same time, I’ve been experimenting with mlflow for LLM evaluations which has worked reasonably well, though I’ve pretty disappointed at mlflow from a self-hosting perspective, especially if only a tracking server is required. Maybe this is an open source project for the future.

<< Previous Post

|

Next Post >>

🎲 Random post

|

All posts

#LLM #Self-Hosting #Production #ML #Embeddings #ONNX