HackerTrans
TopNewTrendsCommentsPastAskShowJobs

alexandercheema

no profile record

Submissions

Kimi K2.5 on 2 Mac Studios (<$20K) running at 24 TPS

twitter.com
6 points·by alexandercheema·6 maanden geleden·4 comments

Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inference

twitter.com
8 points·by alexandercheema·9 maanden geleden·1 comments

Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inference

blog.exolabs.net
5 points·by alexandercheema·9 maanden geleden·0 comments

comments

alexandercheema
·4 maanden geleden·discuss
lol bro there is already a big OSS project called exo: https://github.com/exo-explore/exo
alexandercheema
·5 maanden geleden·discuss
Isn't Claude Code for Infrastructure just...Claude Code?
alexandercheema
·6 maanden geleden·discuss
Is there one for Kimi K2.5?
alexandercheema
·9 maanden geleden·discuss
Appreciate you checking back so often. We have some exciting plans. Keep checking and it won't be long before something pops up :)
alexandercheema
·9 maanden geleden·discuss
Yes, these models are mostly compute-bound so benefit even more from the compute on the DGX Spark.
alexandercheema
·9 maanden geleden·discuss
Blog 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.