Sep 215 Reasons Why 2024 Will Be The Year Of The Self-Hosted LLMIf 2023 has been the year of OpenAI and the API based LLM, I’m making the prediction that 2024 will be the year of the self hosted LLM. *Caveat: We work with a number of large and mid-sized enterprises on their LLM strategy, so we have a pretty good understanding…Llm5 min readLlm5 min read
Sep 20Building Applications with Titan Takeoff ServerThe release of various open-source Large Language Models (LLMs) this year has democratised the access to AI and its associated technologies. Colossal models like the Llama-2 70B or even the Falcon 180B represent incredible opportunities for those who can harness their power. While anyone can certainly download a copy of…Llm6 min readLlm6 min read
Sep 11End-to-End Training with DeterminedAI and Titan Takeoff: From Model Training to Efficient DeploymentSeamless Data Scientist Tools for Modern Deep Learning In today’s fast-evolving AI landscape, the role of a data scientist is both exhilarating and demanding. With foundation models paving the way for breakthroughs across text, image, and multimodal applications, the horizon is limitless. …Llm5 min readLlm5 min read
Sep 8Falcon 180B Integration with Multi-GPU Deployments: Titan Takeoff’s Solution for Large AI ModelsIn the AI realm, the launch of the open-source Falcon 180B model marks a pivotal milestone in AI evolution. As the excitement builds, there’s a crucial question: How can developers and businesses efficiently deploy such a behemoth of a model? …Multi Gpu2 min readMulti Gpu2 min read
Aug 23Deploy Large Language Models On Smaller, Cheaper Hardware With The Takeoff Inference ServerIntroduction Almost every tech team has been playing with LLMs this year, but deploying them efficiently, affordably and on available GPUs remains a huge challenge. Enter the Takeoff Inference Server: revolutionizing the deployment of LLMs on even smaller hardware instances without compromising performance. The Current Challenge Deploying LLMs typically demands high-end GPU instances and…Llm3 min readLlm3 min read
Jul 31Why We Open Sourced The Titan Takeoff Inference ServerOpen source has been the backbone of most technological advancements. It has eliminated the barriers and silos of proprietary software, enabling brilliant minds to not only use, but contribute to, the cutting edge of technology — fueling a beautiful technological flywheel. …Open Source3 min readOpen Source3 min read
Jul 24The Easiest Way to Fine-tune and Inference LLaMA 2.0 🦙🛫LLaMA 2.0 was released last week — setting the benchmark for the best open source (OS) language model. Here’s a guide on how you can try it out on your local hardware & fine-tune it on your data and use-cases. TitanML has three modules, two of which are perfect for…Llm5 min readLlm5 min read
Jul 24Shifting Sands: OpenAI’s Fluctuating Model Performance and the Impact on DevelopersIntroduction Building LLM applications can be challenging, however when you add in fluctuating model performance it can be as impossible as crossing a desert during a sandstorm. Recently, OpenAI, the provider of the two most widely used Large Language Models (LLMs), has faced criticisms for fluctuations in model performance, causing major…OpenAI3 min readOpenAI3 min read
Jul 17Introducing the Titan Takeoff Inference Server 🛫Super fast inference of LLMs! Experience unprecedented speed in inference of large language models (LLMs) — even on a CPU. Just last week, we showcased a Falcon 7B operating with real-time inference on a standard CPU (🤯). Our demonstration caught the attention of data scientists and ML engineers who were…ChatGPT3 min readChatGPT3 min read
Jun 27Why We Are Launching A Public BetaLast week, we shared some exciting news… we announced that we would be launching a public Beta. From private testing to public beta… Mark Zuckerberg said recently “Your ability to keep doing interesting things is your willingness to be embarrassed.” — As creators, we constantly find ways to improve our product — if we don’t, we’re…NLP3 min readNLP3 min read
