🖼️00Attention Decode on AMD MI450 GPUs: A Gluon Kernel Optimization GuideHacker News·about 2 months ago#pjwLwqg3#rocm#kernel#memory#attention#mi450#wmma+2 more🧰Tag tools✨Add tagLearn how to design a high-performance attention decode kernel on AMD MI450 GPUs using Gluon.15s0Read later0Read More
🖼️00AMD shipped Nvidia's new AI laptop over a year ago, and the software is finally catching up XDA ·Adam Conway·4 months ago#HshR6ahn#xda-developers#rocm#nvidia#cuda#halo#tikoo+3 more🧰Tag tools✨Add tagNvidia's RTX Spark is competing in a space that AMD kickstarted over a year ago.15s0Read later0Read More
🖼️00AMD ROCm Performance Jumps 75x in 14 Days Post-DeepSeek v4DEV Community·gentic news·5 months ago#JnHIVqE3#ai#machinelearning#research#deeplearning#performance#b200+5 more🧰Tag tools✨Add tagAMD ROCm stack improved 75x in 14 days post-DeepSeek v4 via fused operations. Still needs 5x more to match B200 performance.15s0Read later0Read More
🖼️00RTX 5080 Sighted, ROCm 7.2.3 Released, & AMD RDNA4 Linux Drivers EmergeDEV Community·soy·5 months ago#Wl6XUKjy#rtx#gpu#nvidia#hardware#rocm#linux+5 more🧰Tag tools✨Add tagFrom Dev RSS Feed: RTX 5080 Sighted, ROCm 7.2.3 Released, & AMD RDNA4 Linux Drivers Emerge15s0Read later0Read More
🖼️00AMD — Deep DiveDEV Community·GAUTAM MANAK·5 months ago#UfSTy9Cc#example#github#key#developer#include#rocm+6 more🧰Tag tools✨Add tagA comprehensive deep-dive into AMD — latest news, products, code examples, and what it means for developers.15s0Read later0Read More
📰00Breaking the MoE Speculative Trap: 460 t/s on AMD Strix HaloDEV Community·Agustin Sacco·5 months ago#SLitsEFB#ai#rocm#performance#model#strix#halo+4 more🧰Tag tools✨Add tagBreaking the MoE Speculative Trap: 460 t/s on AMD Strix Halo Mixture-of-Experts (MoE)...15s0Read later0Read More
