Recent Posts - Page 17#
From Theory to Kernel: Implement FlashAttention-v2 with CK-Tile
Learn how to implement FlashAttention-v2 with CK-Tile: minimize memory overhead, maximize compute efficiency, and scale on AMD GPUs
Introducing ROCm-DS: GPU-Accelerated Data Science for AMD Instinct™ GPUs
Accelerate data science with ROCm-DS: AMD’s GPU-optimized toolkit for faster data frames and graph analytics using hipDF and hipGRAPH
AMD Integrates llm-d on AMD Instinct MI300X Cluster For Distributed LLM Serving
AMD Integrates llm-d on AMD Instinct MI300X Cluster For Distributed LLM Serving
Accelerate DeepSeek-R1 Inference: Integrate AITER into SGLang
Boost DeepSeek-R1 with AITER: Step-by-step SGLang integration for high-performance MoE, GEMM, and attention ops on AMD GPUs
Step-Video-T2V Inference with xDiT on AMD Instinct MI300X GPUs
Learn how to accelerate text-to-video generation using Step-Video-T2V, a 30B parameter T2V model, on AMD MI300X GPUs with ROCm—enabling scalable, high-fidelity video generation from text
Accelerated JPEG decoding on AMD Instinct™ GPUs with rocJPEG
Learn how to decompress JPEG files at breakneck speeds for your AI, vision, and content delivery workloads using rocJPEG and AMD Instinct GPUs.
DataFrame Acceleration: hipDF and hipDF.pandas on AMD GPUs
This blog post demonstrates how hipDF significantly enhances and accelerates data manipulation, aggregation, and transformation tasks on AMD hardware using ROCm.
Unleash Full GPU Potential: Overlap Communication and Computation with Triton-Distributed
Unlock the full power of AMD GPUs—write portable, efficient kernels with Triton-Distributed, overlapping computation and communication with ease and flexibility
CuPy and hipDF on AMD: The Basics and Beyond
Learn how to deploy CuPy and hipDF on AMD GPUs. See their high-performance computing advantages, and use CuPy and hipDF in a detailed example of an investment portfolio allocation optimization using the Markowitz model.
Optimizing DeepseekV3 Inference on SGLang Using ROCm Profiling Tools
Dive into kernel-level profiling of DeepseekV3 on SGLang—identify GPU bottlenecks and boost large language model performance using ROCm
Boosting Llama 4 Inference Performance with AMD Instinct MI300X GPUs
Learn how to boost your Llama 4 inference performance on AMD MI300X GPUs using AITER-optimized kernels and advanced vLLM techniques
Beyond Text: Accelerating Multimodal AI Inference with Speculative Decoding on AMD Instinct™ MI300X GPUs
This blog shows you how to speedup your multimodal models with AMD’s open-source PyTorch tools for speculative decoding on MI300X GPUs