lanarky

LLM Microservice Framework

A Python web framework specifically designed to build LLM microservices with built-in support for FastAPI and streaming capabilities.

The web framework for building LLM microservices

GitHub

978 stars
15 watching
74 forks
Language: Python
last commit: about 2 years ago
Linked from 1 awesome list

fastapillmopsmicroservicespython3web

Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
msoedov/langcornA framework for serving large language models with a robust and efficient API909
internlm/lagentA lightweight framework for building agent-based applications using LLMs and transformer architectures1,924
lsm/micromonoEnables seamless development of microservices with monolithic structure without changing the codebase.643
dreadnode/riggingA framework for leveraging language models in production code216
bytedance/lynx-llmA framework for training GPT4-style language models with multimodal inputs using large datasets and pre-trained models231
ray-project/llmperfA tool for evaluating the performance of large language model APIs678
mikrl/django-llmAn app for building and executing large language model workflows within Django web applications54
ai-hypercomputer/maxtextA high-performance LLM written in Python/Jax for training and inference on Google Cloud TPUs and GPUs.1,557
melih-unsal/demogptA comprehensive toolset for building Large Language Model (LLM) based applications1,733
jackmpcollins/magenticA tool to integrate Large Language Models into Python code seamlessly2,104
wgryc/phasellmA framework for managing and testing large language models to evaluate their performance and optimize user experiences.451
llukas22/llm-rs-pythonAn unofficial Python interface to the Rust-based Large Language Model library73
ailab-cvc/seedAn implementation of a multimodal language model with capabilities for comprehension and generation585
luogen1996/lavinAn open-source implementation of a vision-language instructed large language model513
r2d4/openlmLibrary that provides a unified API to interact with various Large Language Models (LLMs)367