NVIDIA DGX Spark In-Depth Review: A New Standard for Local AI Inferencelmsys.org115 points·by yvbbrjdr·hace 9 meses·93 comments
LMRouter: Run Claude Code on Any LLM with One Commandgithub.com1 points·by yvbbrjdr·hace 11 meses·0 comments
Athena – An open source production-ready general AI agentgithub.com13 points·by yvbbrjdr·el año pasado·2 comments
yvbbrjdr·hace 9 meses·discussWe actually profiled one of the models, and saw that the last GeMM, which is completely memory bound, is taking a lot of time, which reduces the token speed by a lot.
yvbbrjdr·hace 9 meses·discussI see! Do you know what's causing the slowdown for ollama? They should be using the same backend..
yvbbrjdr·hace 9 meses·discussHi, author here. I crowd-sourced the devices for benchmarking from my friends. It just happened that none of my friend has this device.
yvbbrjdr·hace 9 meses·discussHi, author here. I crowd-sourced the devices for benchmarking from my friends. It just happened that one of my friend has this device.