alexandercheema

3 bulan yang laludiscuss

lol bro there is already a big OSS project called exo: https://github.com/exo-explore/exo

alexandercheema

5 bulan yang laludiscuss

Isn't Claude Code for Infrastructure just...Claude Code?

alexandercheema

5 bulan yang laludiscuss

Is there one for Kimi K2.5?

alexandercheema

9 bulan yang laludiscuss

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 bulan yang laludiscuss

Yes, these models are mostly compute-bound so benefit even more from the compute on the DGX Spark.

alexandercheema

9 bulan yang laludiscuss

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.

alexandercheema

Submissions

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

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

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

comments