AI - Software Tools & Optimizations - Page 3#
Serve Kimi-K2.5-MXFP4 on MI355X with ATOM
Serve Kimi-K2.5-MXFP4 on MI355X with ATOM and gfx950 block-scaled FP4 kernels for optimized LLM inference.
Hyperloom - Autonomous Agentic Inference Optimization for AMD GPUs
Hyperloom is a new open-source, agentic system aimed at automating the time-consuming task of optimizing end-to-end inference workloads.
Introducing AMD ROCm™ Infera: Scaling Goodput for Agentic AI with Distributed Inference Orchestration
Explore how AMD ROCm Infera orchestrates distributed inference to scale goodput for agentic AI on AMD Instinct GPUs.
Spur: Modern GPU Job Scheduling for HPC and AI Workloads
Explore how Spur addresses pain points in GPU cluster management and how Spur-Cloud extends the platform into a complete GPU-as-a-Service solution.
Deploy an Imaging AMD Solution Blueprint on AMD Radeon™ GPUs
Learn how to deploy AMD Solution Blueprints on AMD Radeon™ GPUs by following a hands-on example of deploying the MRI Analysis Tool Solution Blueprint
Introducing ROCm™ AMD Infinity Context: A Purpose-Built KV Cache Tier for Distributed Inference
Explore ROCm AMD Infinity Context (AIC), AMD's open KV cache tier built on AMD Infinity Storage for distributed LLM inference.
Scaling MiniMax-M3 Inference with Distributed Serving and Operator Co-Design on AMD Instinct MI355X GPUs
Optimize MiniMax-M3 inference on AMD Instinct™ MI355X GPUs with ATOM online quantization, AITER sparse attention, FP8 KV cache, and EAGLE3.
Understanding Attention Algorithms and Their Backends for Image and Video Generation
Practical guide to attention backends in ComfyUI on AMD describing how to optimize performance, memory, and stability with the right configuration.
SPIR-V on ROCm: A Portable IR for AMD GPUs
Learn how SPIR-V brings compile-once, specialize-on-device portability to AMD GPUs — with a reproducible HIP benchmark, trade-off analysis, and quick-start guide.
When a Faster Kernel Doesn't Speed Up Serving: Profiling FP8 KV Cache on AMD Instinct MI308X
Learn how a 34% faster FP8 KV cache kernel delivered 0% E2E speedup, and how profiling attribution exposed the hidden dtype-cast cost on MI308X.
GEAK Agent-Driven Optimization of the DeepSeekV4 MLA Kernel
GEAK Agent accelerates DeepSeekV4 MLA kernel optimization with Triton and delivers SGLang E2E gains on AMD GPUs.
Serving NVFP4 Models on AMD Instinct™ MI355 Accelerators
Learn how to serve NVFP4 models on AMD Instinct™ MI355 using an emulation pipeline in vLLM — no format conversion needed.