Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
silverlake
on April 6, 2025
|
parent
|
context
|
favorite
| on:
The Llama 4 herd
I think BF16 and FP16 are 1979 TFPOPs, but FP8 is 2x faster at 3958 TFLOPs. So only 10% efficiency, down from 20%. That’s not good.
az226
on April 6, 2025
[–]
That’s with sparsity. So it’s 29% down from 40%.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: