AI 解决方案

Day 0 Developer Guide: hipBLASLt Offline GEMM Tuning Script — ROCm Blogs

Day 0 Developer Guide: hipBLASLt Offline GEMM Tuning Script — ROCm Blogs

Learn how to improve model performance with hipBLASLt offline tuning in our easy-to-use Day 0 tool for developers to optimize GEMM efficiency

November 04, 2025

High-Accuracy MXFP4, MXFP6, and Mixed-Precision Models on AMD GPUs — ROCm Blogs

High-Accuracy MXFP4, MXFP6, and Mixed-Precision Models on AMD GPUs — ROCm Blogs

Learn to leverage AMD Quark for efficient MXFP4/MXFP6 quantization on AMD Instinct accelerators with high accuracy retention.

October 28, 2025

Nitro-E: A 304M Diffusion Transformer Model for High Quality Image Generation — ROCm Blogs

Nitro-E: A 304M Diffusion Transformer Model for High Quality Image Generation — ROCm Blogs

Nitro-E is an extremely lightweight diffusion transformer model for high-quality image generation with only 304M paramters.

October 23, 2025

Making Telcos Run Leaner and AI-Ready with AMD

Making Telcos Run Leaner and AI-Ready with AMD

Learn how telecommunication companies are running leaner and becoming AI-ready with AMD processors

October 20, 2025

AI in the Data Center: Strategies for Efficiency and Sustainability

AI in the Data Center: Strategies for Efficiency and Sustainability

Data centers already consume nearly 2% of global electricity, and AI adoption is set to accelerate that figure. Set your team up for success and scale…

October 17, 2025

Kimi-K2-Instruct: Enhanced Out-of-the-Box Performance on AMD Instinct MI355 Series GPUs — ROCm Blogs

Kimi-K2-Instruct: Enhanced Out-of-the-Box Performance on AMD Instinct MI355 Series GPUs — ROCm Blogs

Learn how AMD Instinct MI355 Series GPUs deliver competitive Kimi-K2 inference with faster TTFT, lower latency, and strong throughput.

October 15, 2025

Gumiho: A New Paradigm for Speculative Decoding — Earlier Tokens in a Draft Sequence Matter More — ROCm Blogs

Gumiho: A New Paradigm for Speculative Decoding — Earlier Tokens in a Draft Sequence Matter More — ROCm Blogs

Gumiho boosts LLM inference with early-token accuracy, blending serial + parallel decoding for speed, accuracy, and ROCm-optimized deployment.

October 13, 2025

GEMM Tuning within hipBLASLt– Part 2 — ROCm Blogs

GEMM Tuning within hipBLASLt– Part 2 — ROCm Blogs

Learn how to use hipblaslt-bench for offline GEMM tuning in hipBLASLt—benchmark, save, and apply custom-tuned kernels at runtime.

October 08, 2025

Copyright © 2022 破界远征沙盒工坊 All Rights Reserved.