Speed up torch engine w8a8 model init #1088
Merged
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
|
Hi @yinfan98 ! |
HIT-cwh
reviewed
Feb 1, 2024
lmdeploy/pytorch/models/q_modules.py
Outdated
| """Class method to create a QLinear instance from a floating-point | ||
| module.""" | ||
| module. initialization for dummy init.""" |
There was a problem hiding this comment.
It seems that initialization = True means real init and initialization = False means dummy init?
HIT-cwh
reviewed
Feb 1, 2024
Co-authored-by: whcao <41630003+HIT-cwh@users.noreply.github.com>
HIT-cwh
approved these changes
Feb 1, 2024
grimoire
approved these changes
Feb 2, 2024
|
Hi, @yinfan98 thanks very much for the contribution. |
|
@lvhan028 Sure, I will finish benchmark these days |
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Outdated suggestions cannot be applied.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.
When using w8a8 model, it will cost a bunch of time for model loading. I found that when using
this func cal the per_channel_quant to get the scale and quanted weight, but it is useless. Because the para not load to model yet, it is just cal for all the zero... so I fix it when init the model on inference stage.
And I tested it on internLM and internLM2