Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sakex
11 months ago
|
parent
|
context
|
favorite
| on:
Fast LLM Inference From Scratch (using CUDA)
Using Jax, you should be able to get good performance out of the box
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: