feat: support lazy loading the lora module for reducing the loading p… #434
Conversation
This file contains 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
|
It seems that caching the handle from safe_open might be a better solution, but need to consider the file handle reference management that used by multiple layers, I will refine it later. |
thincal
force-pushed
the
feat/support-lazy-loading-lora-module
branch
from
bad816f
to
9b1ac96
Compare
Still keep cache the filenames instead of filehandles, since that 1) safe_open needs the device info which differs during loading the lora modules, 2) safe_open is lazy loading until specific tensor loaded by get_tensor invoked, which is already the optimized behavior for our case. |
|
@tgaddair could you help review this change ? |
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Outdated suggestions cannot be applied.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.
What does this PR do?
Fixes #433
Before submitting
to it if that's the case.
Who can review?
@tgaddair