Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
imrozim
17 days ago
|
parent
|
context
|
favorite
| on:
Accelerating Gemma 4: faster inference with multi-...
Fair didn't think about batching makes more sense for self hosted models then.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: