Hacker Times
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
WithinReason
4 months ago
|
parent
|
context
|
favorite
| on:
Hypura – A storage-tier-aware LLM inference schedu...
Have you ever generated access frequency statistics for the experts in these models, something like a histogram?
Gracana
4 months ago
[–]
ktransformers can do dynamic placement of experts and could presumably produce such a histogram, though currently its activation statistics are just a ".pt" file.
https://github.com/kvcache-ai/ktransformers/blob/main/doc/en...
FWIW I never got it to work and did not dig into it much.
Consider applying for YC's Fall 2026 batch!
Applications
are open till July 27.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
