Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dippatel1994
18 days ago
|
parent
|
context
|
favorite
| on:
Real-time LLM Inference on Standard GPUs: 3k token...
Exactly! Any optimization for local inference is a welcome change IMHO!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
