Menu

#Attention

124 posts

Feed·
20 of 124 posts
Scaling AI Inference Across Multiple GPUs Using NVIDIA TensorRT with Multi-Device Inference Support
🖼️
0Read More

Scaling AI Inference Across Multiple GPUs Using NVIDIA TensorRT with Multi-Device Inference Support

NVIDIA Technical Blog·Peter Kisfaludi·3 days ago
#HGWgV5XX

Generative AI workloads are rapidly outgrowing the memory and compute budget of single GPUs. For inference developers building media generation pipelines…

15s
Co-Designing AI Model Attention for Fast, Interactive Long-Context Inference
🖼️
0Read More

Co-Designing AI Model Attention for Fast, Interactive Long-Context Inference

NVIDIA Technical Blog·Tanya Lenz·3 days ago
#iS84waEp
#developer#decode#prefill#attention#kvsl

As agentic and long-context workloads become common, the context lengths increase and attention consumes a larger share of inference time (Figure 1).

15s
Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300
🖼️
0Read More

Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300

NVIDIA Technical Blog·Michelle Horton·5 days ago
#c1C0aMDn
#developer#model#nvidia#qwen3#attention

Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open ecosystem.

15s
Alice GG • Attention is all you have
🖼️
0Read More

Alice GG • Attention is all you have

Hacker News·about 1 month ago
#7J0LaTMa

The Tetris effect is one of psychology’s most easy to reproduce experiments.Simply spend a bit of time playing the eponymous game every day for a few weeks.A...

15s
Attention Decode on AMD MI450 GPUs: A Gluon Kernel Optimization Guide
🖼️
0Read More

Attention Decode on AMD MI450 GPUs: A Gluon Kernel Optimization Guide

Hacker News·3 months ago
#pjwLwqg3
#rocm#kernel#memory#attention#mi450

Learn how to design a high-performance attention decode kernel on AMD MI450 GPUs using Gluon.

15s