#rocm

K3s is a lightweight, certified Kubernetes distribution designed for resource-constrained...

An engineering evaluation of speculative decoding methods in vLLM on AMD Instinct MI300X hardware, analyzing throughput, acceptance rates, and tradeoffs.

This week on AMD Mini-Challenge 3: citation-by-necessity RAG on ROCm Notes from building a...

A late‑2026 compatibility matrix plus known‑good commands for getting Unsloth LoRA fine‑tuning to actually converge on Radeon and MI GPUs with ROCm.

Originally published at norvik.tech Introduction Explore the implications of ROCmfix...

Docker is a platform that packages applications and their dependencies into isolated containers so...

Run OpenAI Whisper locally on AMD GPUs using ROCm without VRAM crashes or OOM errors. Complete setup...

Learn how to run Stable Diffusion and ComfyUI on AMD GPUs using ROCm. Step-by-step guide to...

Accelerating Inference with Speculative Decoding on AMD Hardware: A Technical Deep...

A step by step deployment of Gemma 4 E2B to a single AMD Instinct MI300X on AMD Developer Cloud, driven by Python MCP tools, and the throughput a 191.7 GiB card returns for its hourly rate.

One AMD Instinct MI300X on AMD Developer Cloud, managed entirely through a tag-scoped Python MCP server, with every figure read off the card rather than a spec sheet. fp8 e4m3fnuz runs 1.77x bf16; int8, which AMD rates identically to fp8, runs 0.69x; fp4 is not on this silicon at all. One droplet, $1.99 an hour, and two readings that were wrong the first time.

PyTorch is an open-source framework for building and training machine learning models, especially...