Nicolay Gerold
@nicolaygerold
Nicolay Gerold
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with LLMs faster and more controllable by co-designing the frontend language and the runtime system.
The core features of SGLang include:
The core features of SGLang include:
- A Flexible Front-End Language : This allows for easy programming of LLM applications with multiple ch
sgl-project • GitHub - sgl-project/sglang: SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
Prompting and Controllable Generation
They have a fast jsond ecoding feature with a finite state machine.
However development time, and maintenance can offset these savings. Hiring skilled data scientists, machine learning engineers, and DevOps professionals can be expensive and time consuming. Using available resources for “reimplementing” solutions hinder innovation and lead to a lack of focus. Since You not longer work on improving your model or pro... See more
Understanding the Cost of Generative AI Models in Production
How much do you think we’re going to get tons of specialization versus no, once the brain gets big enough and we do these fine tunings, that’s going to be it. It will be like AWS, GCP, and Azure.
Ali: I think the answer is closer to the latter. It’s going to have lots of specialization. Having said that, it’s not a dichotomy in the sense that maybe ... See more
Ali: I think the answer is closer to the latter. It’s going to have lots of specialization. Having said that, it’s not a dichotomy in the sense that maybe ... See more
Ali Ghodsi • AI Food Fights in the Enterprise
large prompts will prove to be an anti-pattern. They go against the common wisdom in software engineering.
Write small, testable, functions.
Imagine a world where LLMs are used for small, incremental steps.
That’s how engineering works. It’s taking a large problem and breaking it down into smaller problems.
This is how you test, validate and evaluate ... See more
Write small, testable, functions.
Imagine a world where LLMs are used for small, incremental steps.
That’s how engineering works. It’s taking a large problem and breaking it down into smaller problems.
This is how you test, validate and evaluate ... See more
Feed | LinkedIn
The locus cerulius releases epinephrine and has a lot of different functions. It creates alertness (can be experienced as stress, anxiety, excitement) while approaching food and activated the lateral hypothalamus to inhibit feeding. As we eat the mechanisms for calmness kick in, which is often impacted by the signals from the vagal nerve. People ba... See more
Andrew Huberman • How Foods and Nutrients Control Our Moods
Aversion and arousal as a push pull that drive emotions and is connected with an action (moving/leaning in or out).
Andrew Huberman • How Foods and Nutrients Control Our Moods
- Don’t get attached to beliefs . Everything is probabilistic, everything is a best guess until proven otherwise. New information should make you update, even if just a little. It’s easier to have blind spots when you deal in absolutes and are inflexible.
- Keep sending the signal to the people around you that you welcome constructive criticism and fe
Liberty • 453: Anthropic, Microsoft Athena AI Chip, Nvidia Strikes Back, Antitrust Catch-22, China vs Wind Power, Nobel Immigrants, EV, and JS Bach
Datasette is a tool for exploring and publishing data. It helps people take data of any shape, analyze and explore it, and publish it as an interactive website and accompanying API.
Datasette is aimed at data journalists, museum curators, archivists, local governments, scientists, researchers and anyone else who has data that they wish to share with... See more
Datasette is aimed at data journalists, museum curators, archivists, local governments, scientists, researchers and anyone else who has data that they wish to share with... See more
Datasette
Data and Data Storage
LLMs struggle when handling tasks which require extensive knowledge. This limitation highlights the need to supplement LLMs with non-parametric knowledge. This paper Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts analyze the effects of different types of non-parametric knowledge, such as textu... See more