Posts tagged GenAI
Training Transformers and Hybrid models on AMD Instinct MI300X Accelerators
- 10 December 2024
This blog is contributed by Zyphra: a Palo Alto-based AI research lab and AMD Instinct Partner.
Transformer based Encoder-Decoder models for image-captioning on AMD GPUs
- 03 December 2024
Image captioning, or the GenAI-based automatic generation of concise textual descriptions of images, has immensely important real-world applications. For example, image captioning can provide visually impaired users with textual descriptions of images for improved accessibility, image captioning can add textual descriptions to products in e-commerce applications and help children map images to their textual descriptions in early childhood educational apps. Image captioning can automatically describe objects and events in security camera footage in surveillance applications and can enable robots to auto-generate textual captions for objects and events they encountered in human-robot interaction (HRI) applications, and many more applications. Image captioning is a sequence-to-sequence (seq2seq) machine learning task: a model converting a sequence from one domain (in this case, the image), to another (its textual description). In image captioning the image is partitioned into a sequence of patches. This sequence of image patches is then converted by the model to a corresponding sequence of text tokens.
SGLang: Fast Serving Framework for Large Language and Vision-Language Models on AMD Instinct GPUs
- 13 November 2024
In the rapidly evolving landscape of artificial intelligence, the ability to deploy large language models (LLMs) and vision-language models (VLMs) efficiently is crucial for real-time applications. SGLang is an open-source framework designed to meet these demands by delivering fast backend runtime, a flexible frontend language, and extensive model support for a variety of LLMs and VLMs.
Distributed Data Parallel Training on AMD GPU with ROCm
- 01 November 2024
With the increase in complexity and size of machine learning models, the demand for computational resources grows. Training on a single GPU can become a bottleneck for deep learning applications, especially with large datasets and models that are slow to train on a single GPU. Parallelized training addresses this challenge. Out of the various forms of parallelized training, this blog focuses on Distributed Data Parallel (DDP), a key feature in PyTorch that accelerates training across multiple GPUs and nodes.
CTranslate2: Efficient Inference with Transformer Models on AMD GPUs
- 24 October 2024
Transformer models have revolutionized natural language processing (NLP) by delivering high-performance results in tasks like machine translation, text summarization, text generation, and speech recognition. However, deploying these models in production can be challenging due to their high computational and memory requirements. CTranslate2 addresses these challenges by providing a custom runtime that implements various optimization techniques to accelerate Transformer models during inference.
Inference with Llama 3.2 Vision LLMs on AMD GPUs Using ROCm
- 23 October 2024
Meta’s Llama models now support multimodal capabilities, expanding their functionality beyond traditional text-only applications. The Llama 3.2 models are available in a range of sizes, including medium-sized 11B and 90B multimodal models for vision-text reasoning tasks, and lightweight 1B and 3B text-only models designed for edge and mobile devices.
Speed Up Text Generation with Speculative Sampling on AMD GPUs
- 15 October 2024
As the size of transformer models grow, so does the cost of conducting inference, impacting latency and throughput. Compression methods such as quantization and distillation, as well as hardware-aware optimizations such as Flash Attention and Triton, have been proposed to cut down the computation cost at different levels. However, these models either compromise on accuracy or require major changes to the model implementation.
Multinode Fine-Tuning of Stable Diffusion XL on AMD GPUs with Hugging Face Accelerate and OCI’s Kubernetes Engine (OKE)
- 15 October 2024
As the scale and complexity of generative AI and deep learning models grow, multinode training, basically dividing a training job across several processors, has become an essential strategy to speed up training and fine-tuning processes of large generative AI models like SDXL. By distributing the training workload across multiple GPUs on multiple nodes, multinode setups can significantly accelerate the training process. In this blog post we will show you, step-by step, how to set-up and fine-tune a Stable Diffusion XL (SDXL) model in a multinode Oracle Cloud Infrastructure’s (OCI) Kubernetes Engine (OKE) on AMD GPUs using ROCm.
Leaner LLM Inference with INT8 Quantization on AMD GPUs using PyTorch
- 03 October 2024
With the scale of large language models (LLMs) reaching hundred of billions of parameters, the ways we represent data within these enormous models dramatically impacts the resources required to train them (e.g. the number of GPUs needed for inference). In our previous blogs (JAX mixed precision training; PyTorch AMP), we already demonstrated how mixed precision training can accelerate LLMs training process. In this blog post we will push things further and show you how quantization into an even lower precision data formats can speed up inference, saving time and memory, without sacrificing the overall performance of the model. Quantization is a technique where the precision of a model’s parameters is reduced from a 32-bit floating point (FP32) or a 16-bit floating point (FP16) to an 8-bit integer (INT8). Standard models typically use 32-bit floating-point (FP32) precision. However, this higher precision is not always necessary for inference tasks. By converting model weights and activations to lower precision formats like INT8 (8-bit integer), we can achieve faster computations and lower memory usage, effectively reducing the model size by three-fourths (from 32-bit) or half (from 16-bit) with only a slight accuracy reduction, which is often outweighed by the speed gains.
Optimize GPT Training: Enabling Mixed Precision Training in JAX using ROCm on AMD GPUs
- 06 September 2024
This blog builds on the nanoGPT model we discussed in A Guide to Implementing and Training Generative Pre-trained Transformers (GPT) in JAX on AMD GPUs. Here we will show you how to incorporate mixed precision training to the JAX-implemented nanoGPT model we discussed in our previous blog.
Accelerate PyTorch Models using torch.compile on AMD GPUs with ROCm
- 11 July 2024
PyTorch 2.0 introduces torch.compile(), a tool to vastly accelerate PyTorch code and models. By converting PyTorch code into highly optimized kernels, torch.compile delivers substantial performance improvements with minimal changes to the existing codebase. This feature allows for precise optimization of individual functions, entire modules, and complex training loops, providing a versatile and powerful tool for enhancing computational efficiency.
Accelerating models on ROCm using PyTorch TunableOp
- 03 July 2024
In this blog, we will show how to leverage PyTorch TunableOp to accelerate models using ROCm on AMD GPUs. We will discuss the basics of General Matrix Multiplications (GEMMs), show an example of tuning a single GEMM, and finally, demonstrate real-world performance gains on an LLM (gemma) using TunableOp.
A Guide to Implementing and Training Generative Pre-trained Transformers (GPT) in JAX on AMD GPUs
- 02 July 2024
2 July, 2024 by Douglas Jia.
Mamba on AMD GPUs with ROCm
- 28 June 2024
28, Jun 2024 by Sean Song, Jassani Adeem, Moskvichev Arseny.
Unlocking Vision-Text Dual-Encoding: Multi-GPU Training of a CLIP-Like Model
- 24 April 2024
24 Apr, 2024 by Sean Song.
Transforming Words into Motion: A Guide to Video Generation with AMD GPU
- 24 April 2024
24 Apr, 2024 by Douglas Jia.
Interacting with Contrastive Language-Image Pre-Training (CLIP) model on AMD GPU
- 16 April 2024
16, Apr 2024 by Sean Song.
Instruction fine-tuning of StarCoder with PEFT on multiple AMD GPUs
- 16 April 2024
16 Apr, 2024 by Douglas Jia.
Enhancing LLM Accessibility: A Deep Dive into QLoRA Through Fine-tuning Llama Model on a single AMD GPU
- 15 April 2024
15, Apr 2024 by Sean Song.
Enhancing LLM Accessibility: A Deep Dive into QLoRA Through Fine-tuning Llama 2 on a single AMD GPU
- 15 April 2024
15, Apr 2024 by Sean Song.
Building semantic search with SentenceTransformers on AMD
- 04 April 2024
4 Apr, 2024 by Fabricio Flores.
Scale AI applications with Ray
- 01 April 2024
1, Apr 2024 by Vicky Tsang<vicktsan>, {hoverxref}Logan Grado, {hoverxref}Eliot Li
Large language model inference optimizations on AMD GPUs
- 15 March 2024
15, Mar 2024 by Seungrok Jung.
Efficient image generation with Stable Diffusion models and ONNX Runtime using AMD GPUs
- 23 February 2024
23 Feb, 2024 by Douglas Jia.
Two-dimensional images to three-dimensional scene mapping using NeRF on an AMD GPU
- 07 February 2024
7, Feb 2024 by Vara Lakshmi Bayanagari.
Using LoRA for efficient fine-tuning: Fundamental principles
- 05 February 2024
5, Feb 2024 by Sean Song.
Fine-tune Llama model with LoRA: Customizing a large language model for question-answering
- 01 February 2024
1, Feb 2024 by Sean Song.
Fine-tune Llama 2 with LoRA: Customizing a large language model for question-answering
- 01 February 2024
1, Feb 2024 by Sean Song.
Pre-training BERT using Hugging Face & TensorFlow on an AMD GPU
- 29 January 2024
29, Jan 2024 by Vara Lakshmi Bayanagari.
Pre-training BERT using Hugging Face & PyTorch on an AMD GPU
- 26 January 2024
26, Jan 2024 by Vara Lakshmi Bayanagari.
Efficient image generation with Stable Diffusion models and AITemplate using AMD GPUs
- 24 January 2024
24 Jan, 2024 by Douglas Jia.
Efficient deployment of large language models with Text Generation Inference on AMD GPUs
- 24 January 2024
24 Jan, 2024 by Douglas Jia.