Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
qeternity
on June 1, 2025
|
parent
|
context
|
favorite
| on:
Why DeepSeek is cheap at scale but expensive to ru...
It's not impressive nor efficient when you consider batch sizes > 1.
p12tic
on June 1, 2025
[–]
All of this is for batch size 1.
qeternity
on June 2, 2025
|
parent
[–]
I know. That was my point.
Throughput doesn't scale on CPU as well as it does on GPU.
p12tic
on June 3, 2025
|
root
|
parent
[–]
We both agree. Batch size 1 is only relevant to people who want to run models on their own private machines. Which is the case of OP.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
