Dmitrii Ioksha

[doc-fix] Add accelerate required for notebook 3/3

2

Hello, when I followed notebook ["Fine-tuning a model with the Trainer API or Keras"](https://huggingface.co/learn/nlp-course/en/chapter3/3?fw=pt) I encountered this issue: Hope this PR will fix that in the docs

community: Finally add llama-cpp async support

1

Thank you for contributing to LangChain! - [x] **community**: "add LlamaCpp async support" - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..."...

### Your current environment ```text The output of `python collect_env.py` ``` Collecting environment information... PyTorch version: 2.2.1+cu118 Is debug build: False CUDA used to build PyTorch: 11.8 ROCM used to...

FILL IN THE PR DESCRIPTION HERE FIX #xxxx (*link existing issues this PR will resolve*) **BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE** --- PR...

[example] Add vLLM OpenAI-server example

2

I was struggling when I was trying to add Langfuse support inside OpenAI-compatible vLLM server. So here is an example what I found out and what worked for me and...

[feat] Add docker support

1

Hello! Thank you for your amazing repo. I was struggling a bit when I tried to run `Tiktokenizer` locally and that is why I created this PR to provide docker...