Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
freediver
on Aug 27, 2024
|
parent
|
context
|
favorite
| on:
Cerebras launches inference for Llama 3.1; benchma...
The problem with this is tok/sec does not tell you what time to first token is. I've seen (with Groq) where this is large for large prompts, nullifying the advantage of faster tok/sec.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: