Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
_ea1k
on Nov 7, 2023
|
parent
|
context
|
favorite
| on:
QUIK is a method for quantizing LLM post-training ...
One thing that I've currently wondered about quantization... peft seems to require a GPU. Are there any current quantization approaches that make fine tuning more efficient purely on a CPU?
p1esk
on Nov 7, 2023
[–]
OpenVINO:
https://github.com/openvinotoolkit/openvino
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: