Get up and running with Llama 3, Mistral, Gemma, and other large language models.
GoMIT Licenseactive
Awesome LLM
Search 115 LLM projects →115 projects12 categories
- 48%active
- 26%steady
- 23%slowing
- 3%dormant
Sourced fromHannibal046/Awesome-LLM
Projects 1–60 of 115, most starred first
An open-source LLM app development platform with an intuitive interface that streamlines AI workflows, model management, and production deployment.
TypeScriptOtheractive
Reference: awesome-llm-apps
PythonApache License 2.0active
First open-sourced GPT-4o level model.
PythonMIT Licensesteady
First-generation reasoning models from DeepSeek.
MIT Licenseslowing
A high-throughput and memory-efficient inference and serving engine for LLMs.
PythonApache License 2.0active
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Apache License 2.0steady
A framework that specializes in efficient fine-tuning. On its GitHub page, you can find ready-to-use fine-tuning templates for various LLMs, allowing you to easily train your own data for free on the Google Colab cloud.
PythonApache License 2.0active
A Chinese collection of prompt examples to be used with the ChatGPT model.
MIT Licensesteady
Making large AI models cheaper, faster, and more accessible.
PythonApache License 2.0active
A distributed multi-model LLM serving system with web UI and OpenAI-compatible RESTful APIs.
PythonApache License 2.0steady
Formerly langchain-ChatGLM, local knowledge based LLM (like ChatGLM) QA app with langchain.
PythonApache License 2.0steady
DSPy: The framework for programming—not prompting—foundation models.
PythonMIT Licenseactive
Open Source LLM Engineering Platform 🪢 Tracing, Evaluations, Prompt Management, Evaluations and Playground.
TypeScriptOtheractive
SGLang is a fast serving framework for large language models and vision language models.
PythonApache License 2.0active
A Python/C#/Java library from Microsoft that supports prompt templating, function chaining, vectorized memory, and intelligent planning.
C#MIT Licenseactive
Fully open reproduction of DeepSeek-R1
PythonApache License 2.0steady
Confidently evaluate, test, and ship LLM applications with a suite of observability tools to calibrate language model outputs across your dev and production lifecycle.
PythonApache License 2.0active
An open-source library for evaluating task performance of language models and prompts.
PythonOthersteady
Ongoing research training transformer models at scale.
PythonOtheractive
A Device-Inference framework, including LLM Inference on device(Mobile Phone/PC/IOT)
C++Apache License 2.0active
Nvidia Framework for LLM Inference
PythonOtheractive
A framework for few-shot evaluation of language models.
PythonMIT Licenseactive
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
PythonApache License 2.0active
Use ChatGPT On Wechat via wechaty
TypeScriptslowing
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
PythonApache License 2.0steady
Gateway streamlines requests to 100+ open & closed source models with a unified API. It is also production-ready with support for caching, fallbacks, retries, timeouts, loadbalancing, and can be edge-deployed for minimum latency.
TypeScriptMIT Licenseactive
Fine-tune, serve, deploy, and monitor any open-source LLMs in production. Used in production at BentoML for LLMs-based applications.
PythonApache License 2.0active
Open-source framework for fine-tuning and evaluating LLMs. It simplifies the process of experimenting with different training configurations and makes it easy to reproduce and share results, supporting features like LoRA, QLoRA, DeepSpeed, PEFT, and multi-GPU setups.
PythonApache License 2.0active
MoE language model with 32B active and 1T total parameters.
Othersteady
Run LLMs and batch jobs on any cloud. Get maximum cost savings, highest GPU availability, and managed execution -- all with a simple interface.
PythonApache License 2.0active
A curated list of practical guide resources of LLMs
steady
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT).
PythonApache License 2.0active
Curated list of resources for ChatGPT and GPT-3 from OpenAI.
steady
Build your own conversational search engine using less than 500 lines of code by LeptonAI.
TypeScriptApache License 2.0steadyarchived
A high-throughput and low-latency inference and serving framework for LLMs and VLs
PythonApache License 2.0active
An open-source framework to evaluate, test and monitor ML and LLM-powered systems.
Jupyter NotebookApache License 2.0active
Blazingly fast LLM inference.
RustMIT Licenseactive
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
PythonApache License 2.0active
MIT Licensesteady
Efficient Triton Kernels for LLM Training.
PythonBSD 2-Clause "Simplified" Licenseactive
NVIDIA Framework for LLM Inference(Transitioned to TensorRT-LLM)
C++Apache License 2.0slowing
an expert-driven benchmark for Chineses LLMs.
active
Locally running websearch using LLM chains
GoApache License 2.0steadyarchived
a chat interface crafted with llama.cpp for running Alpaca models. No API keys, entirely self-hosted!
SvelteApache License 2.0steadyarchived
A native PyTorch Library for large model training.
PythonBSD 3-Clause "New" or "Revised" Licenseactive
An open-source GPU cluster manager for running LLMs
PythonApache License 2.0active
Open source AutoML tool for RAG. Optimize the RAG answer quality automatically. From generation evaluation datset to deploying optimized RAG pipeline.
TypeScriptOtheractive
Inference for text-embeddings in Rust, HFOIL Licence.
RustApache License 2.0active
LLM‑RL‑Visualized (中文) - 100+ LLM / RL Algorithm Maps📚.
PythonOtheractive
a lean, efficient, and easy-to-hack codebase to research LLMs.
PythonBSD 3-Clause "New" or "Revised" Licenseslowing
A small Python library for using language models to perform NLP tasks.
PythonApache License 2.0steady
Eval tools by OpenAI.
PythonMIT Licensesteady
a collection of demos and articles about the OpenAI GPT-3 API.
slowingarchived
AdalFlow: The library to build&auto-optimize LLM applications.
PythonMIT Licenseactive
Harness LLMs with Multi-Agent Programming
PythonMIT Licenseactive
An open-source LLM app for building multi-agent LLMs applications in an easy and lazy way, supports model deployment and fine-tuning.
PythonApache License 2.0active
Open-source LLM observability, prompt evaulation, and prompt optimzation platform.
TypeScriptApache License 2.0active
A library for accelerating Transformer model training on NVIDIA GPUs.
PythonApache License 2.0active
Reference: LLMDataHub
MIT Licenseslowing