Tuesday, January 07, 2025

NVIDIA GB10: Smallest AI Supercomputer; NeMo AI platform

 NVIDIA Puts Grace Blackwell on Every Desk and at Every AI Developer’s Fingertips | NVIDIA Newsroom

NVIDIA Project DIGITS With New GB10 Superchip Debuts as World’s Smallest AI Supercomputer Capable of Running 200B-Parameter Models

NVIDIA unveiled NVIDIA® Project DIGITS, a personal AI supercomputer that provides AI researchers, data scientists and students worldwide with access to the power of the NVIDIA Grace Blackwell platform.

Project DIGITS will be available in May from NVIDIA and top partners, starting at $3,000.

Developers can fine-tune models with the NVIDIA NeMo™ framework, accelerate data science with NVIDIA RAPIDS™ libraries and run common frameworks such as PyTorch, Python and Jupyter notebooks....



NVIDIA NeMo™ is an end-to-end platform for developing custom generative AI—including large language models (LLMs), vision language models (VLMs), video models, and speech AI—anywhere.

Deliver enterprise-ready models with precise data curation, cutting-edge customization, retrieval-augmented generation (RAG), and accelerated performance with NeMo, part of NVIDIA AI Foundry—a platform and service for building custom generative AI models with enterprise data and domain-specific knowledge.
Nvidia CEO Huang New Chips, AI, Musk, Meeting Trump - YouTube


...groundbreaking RTX 50 series GPUs powered by the Blackwell architecture.
...revolutionary advancements in AI, accelerated computing,
and industrial digitalization transforming every industry.






DIGITS: Deep learning GPU Intelligence Training System


GB10 “AI superchip"... . 1 petaflop (1,000 TOPS) of performance for $3000
size of Mac Mini (or Mini PC)





+ 

Posted by at No comments:

Generative AI @ AWS

 What is Generative AI? - Gen AI Explained - AWS

Generative AI - Digital and Classroom Training | AWS

Diffusion models

...create new data by iteratively making controlled random changes to an initial data sample.
They start with the original data and add subtle changes (noise),
progressively making it less similar to the original.
This noise is carefully controlled to ensure the generated data remains coherent and realistic.

After adding noise over several iterations, the diffusion model reverses the process.
Reverse denoising gradually removes the noise
to produce a new data sample that resembles the original.

The generative adversarial networks (GANs) 

...work by training two neural networks in a competitive manner.
The first network, known as the generator, generates fake data samples by adding random noise.
The second network called the discriminator, tries to distinguish between real data and the fake data produced by the generator.

During training, the generator continually improves its ability to create realistic data while the discriminator becomes better at telling real from fake.
This adversarial process continues until the generator produces data that is so convincing that the discriminator can't differentiate it from real data.

GANs are widely used in generating realistic images, style transfer, and data augmentation tasks.

Variational autoencoders (VAEs)

...learn a compact representation of data called latent space.
The latent space is a mathematical representation of the data.
You can think of it as a unique code representing the data based on all its attributes. 
For example, if studying faces, the latent space contains numbers representing eye shape, nose shape, cheekbones, and ears.

VAEs use two neural networks—the encoder and the decoder. 

The encoder neural network maps the input data to a mean and variance for each dimension of the latent space. It generates a random sample from a Gaussian (normal) distribution. This sample is a point in the latent space and represents a compressed, simplified version of the input data.

The decoder neural network takes this sampled point from the latent space and reconstructs it back into data that resembles the original input. Mathematical functions are used to measure how well the reconstructed data matches the original data.


Transformer-based models

...builds upon the encoder and decoder concepts of VAEs. Transformer-based models add more layers to the encoder to improve performance on text-based tasks like comprehension, translation, and creative writing.

Transformer-based models use a self-attention mechanism.
They weigh the importance of different parts of an input sequence when processing each element in the sequence.

Another key feature is that these AI models implement contextual embeddings. The encoding of a sequence element depends not only on the element itself but also on its context within the sequence.





Amazon Bedrock is a fully-managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies, along with a broad set of features to build generative artificial intelligence (generative AI) applications. Amazon Bedrock Titan foundation models are a family of FMs pre-trained by AWS on large datasets. They are powerful, general-purpose models built to support a variety of use cases. Use them as is or customize them with your own data.

Posted by at No comments:
Subscribe to: Posts (Atom)