Systems Blogs#
DI Series: Serving Kimi-K3 MXFP4 Wide-EP Disaggregated on AMD Instinct MI300X and MI325X
Learn how to serve a 1.4 TiB Kimi-K3 MXFP4 mixture-of-experts model disaggregated across AMD Instinct MI300X and MI325X GPUs.
Completing the GPU Performance Picture: Understanding TAF Alongside Peak FLOPs and MAF
Learn how Typical Attained FLOPs complements Peak FLOPs and Max-Achievable FLOPs, including the methodology and MI325X results
ROCm 10.1: Breaking the Data-Movement Bottleneck
ROCm 10.1 targets the data-movement bottleneck with AMD Infinity Storage, NUMA-aware memory, and a modernized stack.
Local Quantization and Multi-Backend Deployment with AMD Quark on Strix Halo
Quantize a 35B MoE model directly on AMD Strix Halo with AMD Quark, export to GGUF and safetensors, validate with llama.cpp and vLLM, and deploy through Lemonade.
Hyperloom: A Multi-Agent Harness for Autonomous Inference Optimization on AMD GPUs
Hyperloom is a multi-agent harness that autonomously optimizes LLM inference on AMD Instinct GPUs, reaching a median 1.73x throughput gain.
veRL on AMD: Production-Ready RL Post-Training on ROCm
Run veRL RL post-training on AMD Instinct GPUs with a turnkey ROCm container, AITER-accelerated rollout, and validated accuracy on MI300 and MI355.
DI Series: Scaling GLM-5.1-FP8 to 64 MI300X GPUs
Scale GLM-5.1-FP8 long-context serving beyond a single node on AMD Instinct MI300X with WideEP prefill-decode disaggregation and MoRI.
AUP Learning Cloud: Streamlining AI Education on AMD
An all-in-one ROCm JupyterHub platform that deploys GPU-ready AI teaching environments on AMD hardware with one installer and open-source teaching labs.
Introducing AMD CDNA™ 5 and the AMD Helios™ Rackscale Solution
Introducing AMD CDNA 5, the AMD Instinct MI455X GPU, and the AMD Helios rackscale solution: an open, integrated platform for rack-scale AI.
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.
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.
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.