Discover great AI tools
📢 NoticeWebsite launched:DeepToSeek AI tools directory is live. Submit great tools and get featured!
Curated on GitHub

Open Source Radar: Inference & Training

Scanning GitHub for open-source AI projects that are actually worth running: self-hostable, forkable, with a clear license. Star counts and languages are verified against each repository.

148Projects
8.8mTotal stars
10Categories
11 open-source projects
ray ray-project/ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

data-sciencedeep-learning
44.3k Python Apache-2.0Updated 2d ago
sglang sgl-project/sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

attentionblackwell
39k Python Apache-2.0Updated 2d ago
DeepSpeed deepspeedai/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

billion-parameterscompression
43.3k Python Apache-2.0Updated 2d ago
openvino openvinotoolkit/openvino

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

aicomputer-vision
11.2k C++ Apache-2.0Updated 2d ago
airllm lyogavin/airllm

AirLLM 2.8T LLM inference with single 4GB GPU

chinese-llmchinese-nlp
42.6k Jupyter Notebook Apache-2.0Updated 2d ago
BentoML bentoml/BentoML

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

ai-inferencedeep-learning
8.9k Python Apache-2.0Updated 3d ago
OpenLLM bentoml/OpenLLM

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

bentomlfine-tuning
12.6k Python Apache-2.0Updated 3d ago
litgpt Lightning-AI/litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

aiartificial-intelligence
13.8k Python Apache-2.0Updated 9d ago
llamafile mozilla-ai/llamafile

Distribute and run LLMs with a single file.

cross-platformgguf
26.7k C++ Updated 11d ago
T
transformers huggingface/transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

audiodeep-learning
169.2k Python Apache-2.0
V
vllm vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

cudainference
97.1k Python Apache-2.0