Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
naasking
14 days ago
|
parent
|
context
|
favorite
| on:
The efficient frontier of LLM inference
There's actually already a fork that implements the preliminaries:
https://github.com/ggml-org/llama.cpp/discussions/21961
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://github.com/ggml-org/llama.cpp/discussions/21961