Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
MichaelMoser123
8 months ago
|
parent
|
context
|
favorite
| on:
TransMLA: Multi-head latent attention is all you n...
deepseek-v2,v3,r1 are all using multi-headed attention.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
