https://rocm.blogs.amd.com/

Skip to main content [ ] [ ]
[                    ] Ctrl+K
AMD Logo
ROCm(tm) Blogs

  * GitHub
  * Community
  * Documentation
  * Infinity Hub
  * Support
  * Feedback

 

ROCm Blogs

Artificial intelligence

  * Stable diffusion (AITemplate)
  * Fine-tune Llama 2 with LoRA
  * LLMs and Text Generation Inference
  * LoRA & efficient fine-tuning
  * LLM fine-tuning with JAX
  * Accelerating XGBoost
  * Pytorch Lightning
  * LLM Training with Megatron-DeepSpeed
  * Pre-training BERT (PyTorch)
  * Pre-training BERT (TensorFlow)

Acknowledgements

  * Blog contributors

Contents

 AMD ROCm(tm) Blogs

Applications & models

Stable diffusion (AITemplate)

Efficient image generation with Stable Diffusion models and
AITemplate using AMD GPUs

 
Fine-tune Llama 2 with LoRA

Fine-tune Llama 2 with LoRA: Customizing a large language model for
question-answering

 
LLMs and Text Generation Inference

Efficient deployment of LLMs with Text Generation Inference

 
LoRA & efficient fine-tuning

Using LoRA for efficient fine-tuning: fundamental principles

 
LLM fine-tuning with JAX

LLM distributed supervised fine-tuning with JAX

 
Finite difference: Laplacian, part 4

Performance benchmarking across various AMD GPUs and cache size
limitations

 
More ...
 
PyTorch Lightning

PyTorch Lightning on AMD GPUs

 
LLM training with Megatron-DeepSpeed

Pre-training a large language model with Megatron-DeepSpeed on
multiple AMD GPUs

 
Pre-training BERT (PyTorch)

Efficient image generation with Stable Diffusion models and ONNX
Runtime using AMD GPUs

 
3D scene mapping using NeRF

Two-dimensional images to three-dimensional scene mapping using NeRF
on an AMD GPU

 

Software tools & optimizations

Register pressure

Register pressure in AMD CDNA2 GPUs

 
Jacobi solver

Implementation of the Jacobi solver with both HIP and OpenMP
offloading

 
Matrix cores

Accelerating GEMM computations using AMD's matrix core technology

 
GPU-aware MPI

Leveraging various GPU-aware MPI implementations with ROCm

 
MI200 memory space

Overview of the AMD Instinct MI200 memory space

 
More ...
 

Stay informed

  * Subscribe to our RSS feed
  * Watch our GitHub repo

 

next

Efficient image generation with Stable Diffusion models and
AITemplate using AMD GPUs

Contents

  * Terms and Conditions
  * Privacy
  * Trademarks
  * Statement on Forced Labor
  * Fair and Open Competition
  * UK Tax Strategy
  * Cookie Policy
  * Cookie Settings

(c) 2023 Advanced Micro Devices, Inc