Kimi K2.5 on 2 Mac Studios (<$20K) running at 24 TPStwitter.com6 points·by alexandercheema·5 mesi fa·4 comments
Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inferencetwitter.com8 points·by alexandercheema·9 mesi fa·1 comments
Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inferenceblog.exolabs.net5 points·by alexandercheema·9 mesi fa·0 comments
alexandercheema·3 mesi fa·discusslol bro there is already a big OSS project called exo: https://github.com/exo-explore/exo
alexandercheema·9 mesi fa·discussAppreciate you checking back so often. We have some exciting plans. Keep checking and it won't be long before something pops up :)
alexandercheema·9 mesi fa·discussYes, these models are mostly compute-bound so benefit even more from the compute on the DGX Spark.
alexandercheema·9 mesi fa·discussBlog author here. Actually, no. The model can be streamed into the DGX Spark, so we can run prefill of models much larger than 128GB (e.g. DeepSeek R1) on the DGX Spark. This feature is coming to EXO 1.0 which will be open-sourced soonTM.