Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
rcarmo
5 months ago
|
parent
|
context
|
favorite
| on:
Llama3 implemented from scratch
I'd like to see this using ONNX and streaming from storage (I have my reasons, but mostly about using commodity hardware for "slow" batch processing without a GPU)
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: