Resource Center

Announcing Titan Takeoff 0.7.0

5 minute introduction to the Titan Takeoff Inference Server

Structured generation with LLMs: Regex and JSON schema

OpenAI’s leadership crisis: A catalyst for a smarter AI strategy

Regex controlled generation of Llama 13B in Titan Takeoff Inference Server

Deploying multiple LLMs to one GPU: Titan Takeoff Model Management

When should I fine tune my LLM - Low effort strategies that beat fine-tuning

Supercharge Inference Server Throughput with Rust!

Harmonizing multi-GPUs: Efficient scaling of LLM inference

*Exciting news: TitanML raises a $2.8 million pre-seed funding round to make large language model deployment far faster, cheaper, easier and more sustainable*

In the fast lane! Speculative decoding - 10x larger model, no extra cost

Deploying LLMs on small devices: An introduction to quantization

The future of generative AI: Vision and challenges

5 reasons why 2024 will be the year of the self-hosted LLM

TitanML's Titan Playground