Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
skhameneh
79 days ago
|
parent
|
context
|
favorite
| on:
A guide to local coding models
ik_llama is almost always faster when tuned. However, when untuned I've found them to be very similar in performance with varied results as to which will perform better.
But vLLM and Sglang tend to be faster than both of those.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
But vLLM and Sglang tend to be faster than both of those.