Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
rurban
3 months ago
|
parent
|
context
|
favorite
| on:
Ask HN: What are you using for LLM inference in pr...
For LLM inference in production we use vLLM (with our own model).
idbnstra
3 months ago
[–]
did you fine tune another model, and if so which one?
rurban
3 months ago
|
parent
[–]
Not really fine tuned. But the base was Qwen. We are analyzing images
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: