Support calling mlock() on loaded model data on Linux and macOS #453
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This is enabled by a new --mlock command line option. Using mlock() disables swapping and memory compression for the model data. Doing so can be useful on systems where the model takes up a large fraction of system RAM. In my experience, macOS is quite eager to start compressing llama.cpp's memory, which then makes it halt for a few seconds while it decompresses, even with a model that uses "only" 25GB out of 32GB. Of course, this comes at the cost of forcing the system to swap or compress other processes' memory instead, so it needs to be used with care and shouldn't be enabled by default. In theory it should be possible to support this on Windows as well using VirtualLock(), but I'm not much of a Windows user.
ggerganov
reviewed
Mar 24, 2023
ggerganov
approved these changes
Mar 24, 2023
|
Just curious, if I load 2 models that are mlocked, such that their total memory exceeds my system memory, what would the behaviour be? Would this be OOM? Also, what is the cleanup behaviour? I.e. if llama.cpp exits, will there be an munlock? What if my program exits prematurely i.e. by ctrl-C? |
Deadsg
pushed a commit
to Deadsg/llama.cpp
that referenced
this pull request
Dec 19, 2023
Fix incorrect token_logprobs (due to indexing after sorting)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is enabled by a new
--mlockcommand line option.Using mlock() disables swapping and memory compression for the model data. Doing so can be useful on systems where the model takes up a large fraction of system RAM. In my experience, macOS is quite eager to start compressing llama.cpp's memory, which then makes it halt for a few seconds while it decompresses, even with a model that uses "only" 25GB out of 32GB.
Of course, this comes at the cost of forcing the system to swap or compress other processes' memory instead, so it needs to be used with care and shouldn't be enabled by default.
In theory it should be possible to support this on Windows as well using VirtualLock(), but I'm not much of a Windows user.