Attention Decode on AMD MI450 GPUs: A Gluon Kernel Optimization Guide(rocm.blogs.amd.com)61 points by matt_d 3 months ago | 6 comments
Client-side GPU load balancing with Redis and Lua(galileo.ai)44 points by lneiman 10 months ago | 7 comments
AMD Radeon Pro W7700 Running on Raspberry Pi(jeffgeerling.com)9 points by ingve 1 year ago | 1 comments
Qwen3.8-27B at 256K on a 24GB RTX PRO 4000 SFF (432 GB/s): 50 tok/s with MTP(piszczek.pl)31 points by pich 2 months ago | 24 comments
Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs(baseten.co)215 points by philipkiely 1 year ago | 142 comments
Ryzen 7 Mini-PC makes a power-efficient VM host(michael.stapelberg.ch)32 points by signa11 2 years ago | 14 comments