mosec VS text-generation-inference

Mosec - A high-performance serving framework for ML models, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine. Simple and faster alternative to NVIDIA Triton.

- Yes C++ would be better, but you can try mosec. It has a Python interface and helps you handle all the difficult things about Python multiprocessing. The web service part is implemented in Rust thus it's fast enough for machine learning services.

Contribute to open source projects: Modelz is built on top of envd, mosec, modelz-llm and many other open source projects. If you're interested in contributing to these projects, you can check out their GitHub repositories and start contributing.

You could first create the image with the framework you like (e.g. bentoml or https://github.com/mosecorg/mosec for light weight).

If you're interested in machine learning model serving, can check mosec: https://github.com/mosecorg/mosec

During the development of a machine learning serving project Mosec, I used a lot of multiprocessing to make it more efficient. I want to share some experiences and some researches related to Python multiprocessing.

That's a good example. I have met the same situation before. I have created a discussion in GitHub to track the DAG progress.

I wanted to write that TGI inference engine is not Open Source anymore, but they have reverted the license back to Apache 2.0 for the new version TGI v2.0: https://github.com/huggingface/text-generation-inference/rel...

Good news!

Setting up a server for multiple users is very different from setting up LLM for yourself. A safe bet would be to just use TGI, which supports continuous batching and is very easy to run via Docker on your server. https://github.com/huggingface/text-generation-inference

Okay, I actually got local co-pilot set up. You will need these 4 things.

1) CodeLlama 13B or another FIM model https://huggingface.co/codellama/CodeLlama-13b-hf. You want "Fill in Middle" models because you're looking at context on both sides of your cursor.

2) HuggingFace llm-ls https://github.com/huggingface/llm-ls A large language mode Language Server (is this making sense yet)

3) HuggingFace inference framework. https://github.com/huggingface/text-generation-inference At least when I tested you couldn't use something like llama.cpp or exllama with the llm-ls, so you need to break out the heavy duty badboy HuggingFace inference server. Just config and run. Now config and run llm-ls.

4) Okay, I mean you need an editor. I just tried nvim, and this was a few weeks ago, so there may be better support. My expereicen was that is was full honest to god copilot. The CodeLlama models are known to be quite good for its size. The FIM part is great. Boilerplace works so much easier with the surrounding context. I'd like to see more models released that can work this way.

A simple microservice would be https://github.com/huggingface/text-generation-inference .

Works flawlessly in Docker on my Windows machine, which is extremely shocking.

I am wondering what is the best / most cost-efficient way to serve llama V2. - llama.cpp (is it production ready or just for playing around?) ? - Triton inference server ? - HF text generation inference ?