multithread tensor loading fixes #854
Merged
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
Many code paths were defaulting to 0, which launch max threads regardless of the --threads parameter.
For consistency, since std::thread::hardware_concurrency can return double the number of cores on SMT machines.
wbruna
force-pushed
the
fixes_tensor_loading_multithread
branch
from
206bfde to
d4534a7
Compare
|
Thank you for your contribution. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
While debugging #838 , I noticed that some models were being loaded with the maximum number of threads regardless of the
--threadsparameter, so I adjusted those calls to pass the thread number. For textual inversions, I kept the processing threads at 1, since the thread spawning was giving me higher latency than just processing those smaller files directly.Edit: removed the fix for #838