LlamaFactory

Transformers

Transformers is a model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. It provides a wide range of pre-trained models and a simple interface for fine-tuning and deploying custom models.

headroom

Headroom is a compression tool designed to reduce the size of data inputs for Large Language Models (LLMs). It can compress tool outputs, logs, files, and RAG chunks, resulting in significant reductions in token count. This can lead to improved performance and efficiency in various applications. Headroom is available as a library, proxy, and MCP server, making it a versatile solution for different use cases.

BigML

BigML is a cloud-based platform for building, training, and deploying machine learning models. It provides a simple and intuitive interface for data scientists and developers to create and deploy machine learning models at scale.

Langfuse

Langfuse is an open-source AI engineering platform that provides a comprehensive suite of tools for evaluating and observing large language models (LLMs). It offers features such as LLM evaluations, observability, metrics, prompt management, and a playground for testing and experimentation. Langfuse also integrates with popular tools and platforms like OpenTelemetry, LangChain, OpenAI SDK, and LiteLLM.

unsloth

Unsloth is an open‑source Python package that streamlines the training and inference of open‑weight large language models on a single GPU. It supports popular model families such as Kimi, Gemma, Qwen, DeepSeek, and GLM, wrapping the fine‑tuning workflow in an easy‑to‑use notebook interface. By leveraging custom optimized kernels, Unsloth dramatically reduces memory usage and training time compared to standard setups, making sizable model fine‑tuning practical for freelancers and small teams. The tool is accessible via the web and can be deployed in cloud or SaaS environments, offering free access and email support for ML engineers and researchers.

vllm

vllm is an open‑source inference and serving engine designed for large language models. It focuses on maximizing throughput while keeping GPU memory usage low, enabling faster batch processing of prompts. The project provides a Python API and integrates tightly with popular frameworks like PyTorch and HuggingFace Transformers, making it easy to deploy LLMs in production or research environments.