Understanding memory usage #1876
-
Beta Was this translation helpful? Give feedback.
Answered by
africalimedrop
Jun 15, 2023
Replies: 2 comments
-
Suspect this will help answer; bolded relevant part:
|
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
KerfuffleV2
-
thanks. makes sense.
…On Thu, Jun 15, 2023 at 11:28 AM africalimedrop ***@***.***> wrote:
Suspect this will help answer; bolded relevant part:
- --no-mmap: Do not memory-map the model. *By default, models are
mapped into memory, which allows the system to load only the necessary
parts of the model as needed.* However, if the model is larger than
your total amount of RAM or if your system is low on available memory,
using mmap might increase the risk of pageouts, negatively impacting
performance. Disabling mmap results in slower load times but may reduce
pageouts if you're not using --mlock. Note that if the model is larger
than the total amount of RAM, turning off mmap would prevent the model from
loading at all.
—
Reply to this email directly, view it on GitHub
<#1876 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/A6NWEK6C2DTOSVSKNTLAWRTXLNH43ANCNFSM6AAAAAAZIA6OFM>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Suspect this will help answer; bolded relevant part:
--no-mmap
: Do not memory-map the model. By default, models are mapped into memory, which allows the system to load only the necessary parts of the model as needed. However, if the model is larger than your total amount of RAM or if your system is low on available memory, using mmap might increase the risk of pageouts, negatively impacting performance. Disabling mmap results in slower load times but may reduce pageouts if you're not using--mlock
. Note that if the model is larger than the total amount of RAM, turning off mmap would prevent the model from loading at all.