Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
zozbot234
17 hours ago
|
parent
|
context
|
favorite
| on:
Apple is fighting for TSMC capacity as Nvidia take...
You can cluster Mac Studios using Thunderbolt connections and enable RDMA for distributed inference. This will be slower than a single node but is still the best bang-for-the-buck wrt. doing inference on very-large-sized models.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: